{ "version": "development_evaluation_pdfgeo-r23", "locked_at": "2026-09-12T13:09:36.456463+00:00", "gold_sha256": "4e13d0727b80b78305b5cc61d61ef82678a53846d9cb49bd3caacefa275f8394", "source_sha256": "c82faba844866c161c379c85065499678194ebd376d037e194d21c0ffc36d2b0", "candidate_pages_sha256": "fe45ce3af76b94435c9c76f0f57ec174e6e43120cf7b6028cdd1258d80ccdff3", "denominator_note": "Fixed sampled checks only. Purposive extra checks separate. Every complete page referenced is retained. Metadata candidate detections need role adjudication and are not an accuracy score.", "summary": { "pdftotext-default": { "phrase": { "denominator": 42, "verdicts": { "pass": 22, "fail": 20 }, "nonpass_ids": [ "p039-a", "p039-b", "p058-a", "p058-b", "p077-a", "p077-b", "p096-a", "p096-b", "p115-a", "p115-b", "p134-b", "p153-a", "p153-b", "p210-a", "p210-b", "p229-a", "p229-b", "p305-b", "p324-a", "p324-b" ] }, "forbidden_interleaving": { "denominator": 7, "verdicts": { "pass": 3, "unassessable": 4 }, "nonpass_ids": [ "p153-columns", "p210-gutter", "p210-timestamp", "p324-columns" ] }, "furniture": { "denominator": 21, "verdicts": { "fail": 21 }, "nonpass_ids": [ "p001-furniture", "p020-furniture", "p039-furniture", "p058-furniture", "p077-furniture", "p096-furniture", "p115-furniture", "p134-furniture", "p153-furniture", "p172-furniture", "p191-furniture", "p210-furniture", "p229-furniture", "p248-furniture", "p267-furniture", "p286-furniture", "p305-furniture", "p324-furniture", "p343-furniture", "p362-furniture", "p373-furniture" ] }, "page_label": { "denominator": 57, "verdicts": { "body_only": 48, "missing": 9 }, "nonpass_ids": [ "p039-label-1", "p058-label-1", "p077-label-1", "p115-label-1", "p153-label-1", "p153-label-2", "p229-label-1", "p229-label-2", "p324-label-1" ] }, "phrase_by_native_layer": { "absent_body": { "denominator": 8, "strict_passes": 0 }, "noisy_existing_layer": { "denominator": 8, "strict_passes": 1 }, "partial_body": { "denominator": 2, "strict_passes": 0 }, "sampled_text_present": { "denominator": 24, "strict_passes": 21 } }, "native_present_pages_phrase_subset": { "denominator": 32, "strict_passes": 22, "definition": "Exclude phrases on visually/native-established absent-body or partial-body pages; noisy existing-layer pages stay included." }, "secondary_case_punctuation_tolerant": { "denominator": 42, "passes": 26 } }, "pdftotext-layout": { "phrase": { "denominator": 42, "verdicts": { "pass": 19, "fail": 23 }, "nonpass_ids": [ "p039-a", "p039-b", "p058-a", "p058-b", "p077-a", "p077-b", "p096-a", "p096-b", "p115-a", "p115-b", "p134-a", "p134-b", "p153-a", "p153-b", "p210-a", "p210-b", "p229-a", "p229-b", "p286-a", "p286-b", "p305-b", "p324-a", "p324-b" ] }, "forbidden_interleaving": { "denominator": 7, "verdicts": { "pass": 1, "fail": 4, "unassessable": 2 }, "nonpass_ids": [ "p134-columns", "p153-columns", "p210-gutter", "p210-timestamp", "p286-cells", "p324-columns" ] }, "furniture": { "denominator": 21, "verdicts": { "fail": 21 }, "nonpass_ids": [ "p001-furniture", "p020-furniture", "p039-furniture", "p058-furniture", "p077-furniture", "p096-furniture", "p115-furniture", "p134-furniture", "p153-furniture", "p172-furniture", "p191-furniture", "p210-furniture", "p229-furniture", "p248-furniture", "p267-furniture", "p286-furniture", "p305-furniture", "p324-furniture", "p343-furniture", "p362-furniture", "p373-furniture" ] }, "page_label": { "denominator": 57, "verdicts": { "body_only": 45, "missing": 12 }, "nonpass_ids": [ "p039-label-1", "p058-label-1", "p077-label-1", "p115-label-1", "p115-label-2", "p134-label-1", "p134-label-2", "p153-label-1", "p153-label-2", "p229-label-1", "p229-label-2", "p324-label-1" ] }, "phrase_by_native_layer": { "absent_body": { "denominator": 8, "strict_passes": 0 }, "noisy_existing_layer": { "denominator": 8, "strict_passes": 1 }, "partial_body": { "denominator": 2, "strict_passes": 0 }, "sampled_text_present": { "denominator": 24, "strict_passes": 18 } }, "native_present_pages_phrase_subset": { "denominator": 32, "strict_passes": 19, "definition": "Exclude phrases on visually/native-established absent-body or partial-body pages; noisy existing-layer pages stay included." }, "secondary_case_punctuation_tolerant": { "denominator": 42, "passes": 21 } }, "pdfium-native": { "phrase": { "denominator": 42, "verdicts": { "pass": 23, "fail": 19 }, "nonpass_ids": [ "p039-a", "p039-b", "p058-a", "p058-b", "p077-a", "p077-b", "p096-a", "p096-b", "p115-a", "p115-b", "p153-a", "p153-b", "p210-a", "p210-b", "p229-a", "p229-b", "p305-b", "p324-a", "p324-b" ] }, "forbidden_interleaving": { "denominator": 7, "verdicts": { "pass": 3, "unassessable": 2, "fail": 2 }, "nonpass_ids": [ "p153-columns", "p210-gutter", "p210-timestamp", "p324-columns" ] }, "furniture": { "denominator": 21, "verdicts": { "fail": 21 }, "nonpass_ids": [ "p001-furniture", "p020-furniture", "p039-furniture", "p058-furniture", "p077-furniture", "p096-furniture", "p115-furniture", "p134-furniture", "p153-furniture", "p172-furniture", "p191-furniture", "p210-furniture", "p229-furniture", "p248-furniture", "p267-furniture", "p286-furniture", "p305-furniture", "p324-furniture", "p343-furniture", "p362-furniture", "p373-furniture" ] }, "page_label": { "denominator": 57, "verdicts": { "body_only": 48, "missing": 9 }, "nonpass_ids": [ "p039-label-1", "p058-label-1", "p077-label-1", "p115-label-1", "p153-label-1", "p153-label-2", "p229-label-1", "p229-label-2", "p324-label-1" ] }, "phrase_by_native_layer": { "absent_body": { "denominator": 8, "strict_passes": 0 }, "noisy_existing_layer": { "denominator": 8, "strict_passes": 1 }, "partial_body": { "denominator": 2, "strict_passes": 0 }, "sampled_text_present": { "denominator": 24, "strict_passes": 22 } }, "native_present_pages_phrase_subset": { "denominator": 32, "strict_passes": 23, "definition": "Exclude phrases on visually/native-established absent-body or partial-body pages; noisy existing-layer pages stay included." }, "secondary_case_punctuation_tolerant": { "denominator": 42, "passes": 28 } }, "pdfgeo-r23": { "phrase": { "denominator": 42, "verdicts": { "pass": 25, "fail": 17 }, "nonpass_ids": [ "p039-a", "p039-b", "p058-a", "p058-b", "p077-a", "p077-b", "p096-a", "p096-b", "p115-a", "p115-b", "p153-a", "p153-b", "p229-a", "p229-b", "p305-b", "p324-a", "p324-b" ] }, "forbidden_interleaving": { "denominator": 7, "verdicts": { "pass": 5, "unassessable": 2 }, "nonpass_ids": [ "p153-columns", "p324-columns" ] }, "furniture": { "denominator": 21, "verdicts": { "pass": 19, "fail": 2 }, "nonpass_ids": [ "p229-furniture", "p248-furniture" ] }, "page_label": { "denominator": 57, "verdicts": { "removed_metadata": 41, "missing": 9, "body_only": 7 }, "nonpass_ids": [ "p039-label-1", "p058-label-1", "p077-label-1", "p115-label-1", "p153-label-1", "p153-label-2", "p229-label-1", "p229-label-2", "p324-label-1" ] }, "phrase_by_native_layer": { "absent_body": { "denominator": 8, "strict_passes": 0 }, "noisy_existing_layer": { "denominator": 8, "strict_passes": 1 }, "partial_body": { "denominator": 2, "strict_passes": 0 }, "sampled_text_present": { "denominator": 24, "strict_passes": 24 } }, "native_present_pages_phrase_subset": { "denominator": 32, "strict_passes": 25, "definition": "Exclude phrases on visually/native-established absent-body or partial-body pages; noisy existing-layer pages stay included." }, "secondary_case_punctuation_tolerant": { "denominator": 42, "passes": 30 } } }, "checks": [ { "id": "p001-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 1, "expected": "United States Court of Appeals for the Federal Circuit", "original_line_breaks": "United States Court of Appeals\nfor the Federal Circuit", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Case: 23-1101 Document: 15 Page: 1 Filed: 05/09/2023 Nos. 2022-1974, 2023-1101 United States Court of Appeals for the Federal Circuit ECOFACTOR, INC., Plaintiff-Appellant, v. GOOGLE LLC, Defendant-Cross-Appellant.", "start": 0, "end": 213, "normalized_page_characters": 1038, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p001.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Case: 23-1101 Document: 15 Page: 1 Filed: 05/09/2023 Nos. 2022-1974, 2023-1101 United States Court of Appeals for the Federal Circuit ECOFACTOR, INC., Plaintiff-Appellant, v. GOOGLE LLC, Defendant-Cross-Appellant.", "start": 0, "end": 213, "normalized_page_characters": 1040, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p001.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Nos. 2022-1974, 2023-1101 United States Court of Appeals for the Federal Circuit ECOFACTOR, INC., Plaintiff-Appellant, v. GOOGLE LLC, Defendant-Cross-Appellant.", "start": 0, "end": 160, "normalized_page_characters": 1039, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p001.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Nos. 2022-1974, 2023-1101 United States Court of Appeals for the Federal Circuit ECOFACTOR, INC., v. GOOGLE LLC, Defendant-Cross-Appellant. ____________ On Appe", "start": 0, "end": 160, "normalized_page_characters": 986, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p001.txt" } } }, { "id": "p001-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 1, "expected": "On Appeal from the United States District Court Western District of Texas Case No. 6:20-cv-00075-ADA, Judge Alan D. Albright", "original_line_breaks": "On Appeal from the United States District Court Western District of Texas\nCase No. 6:20-cv-00075-ADA, Judge Alan D. Albright", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "C., Plaintiff-Appellant, v. GOOGLE LLC, Defendant-Cross-Appellant. ____________ On Appeal from the United States District Court Western District of Texas Case No. 6:20-cv-00075-ADA, Judge Alan D. Albright ____________ NON-CONFIDENTIAL JOINT APPENDIX ____________ Reza Mirzaie rmirzaie", "start": 147, "end": 431, "normalized_page_characters": 1038, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p001.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "C., Plaintiff-Appellant, v. GOOGLE LLC, Defendant-Cross-Appellant. ____________ On Appeal from the United States District Court Western District of Texas Case No. 6:20-cv-00075-ADA, Judge Alan D. Albright ____________ NON-CONFIDENTIAL JOINT APPENDIX ____________ Reza Mirzaie Robert A", "start": 147, "end": 431, "normalized_page_characters": 1040, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p001.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "C., Plaintiff-Appellant, v. GOOGLE LLC, Defendant-Cross-Appellant. ____________ On Appeal from the United States District Court Western District of Texas Case No. 6:20-cv-00075-ADA, Judge Alan D. Albright ____________ NON-CONFIDENTIAL JOINT APPENDIX ____________ Reza Mirzaie rmirzaie", "start": 94, "end": 378, "normalized_page_characters": 1039, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p001.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Circuit ECOFACTOR, INC., v. GOOGLE LLC, Defendant-Cross-Appellant. ____________ On Appeal from the United States District Court Western District of Texas Case No. 6:20-cv-00075-ADA, Judge Alan D. Albright ____________ NON-CONFIDENTIAL JOINT APPENDIX ____________ Plaintiff-Appellant, ", "start": 73, "end": 357, "normalized_page_characters": 986, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p001.txt" } } }, { "id": "p001-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 1, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "full_page": "pages/pdftotext-default/p001.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "full_page": "pages/pdftotext-layout/p001.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "full_page": "pages/pdfium-native/p001.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p001.txt" } } }, { "id": "p001-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 1, "expected": "Page: 1", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 5, "text": "Page: 1" } ] }, "full_page": "pages/pdftotext-default/p001.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": " Case: 23-1101 Document: 15 Page: 1 Filed: 05/09/2023" } ] }, "full_page": "pages/pdftotext-layout/p001.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 46, "text": "Case: 23-1101 Document: 15 Page: 1 Filed: 05/09/2023" } ] }, "full_page": "pages/pdfium-native/p001.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Case: 23-1101 Document: 15 Page: 1 Filed: 05/09/2023", "box": [ 135.56, 767.45, 476.43, 780.84 ], "kind": "running_header" } ] }, "full_page": "pages/pdfgeo-r23/p001.txt" } } }, { "id": "p001-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 1, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "none", "signals": [], "body_glyphs": 859, "image_area_fraction": 0.0, "flagged": false } } }, { "id": "p020-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 20, "expected": "other recordkeeping purposes, but may destroy such material (including electronic media containing such information)", "original_line_breaks": "other recordkeeping purposes, but may destroy such material (including electronic media\ncontaining such information)", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "006/09/21 Filed: Page 05/09/2023 Case 6:20-cv-00075-ADA Document Filed 10 of 25 other recordkeeping purposes, but may destroy such material (including electronic media containing such information) in its possession which it regards as surplusage. Notwithstanding, outside coun", "start": 37, "end": 313, "normalized_page_characters": 1850, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p020.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "00075-ADA 15 69 Document Page: 2006/09/21 Filed Filed: Page 05/09/2023 10 of 25 other recordkeeping purposes, but may destroy such material (including electronic media containing such information) in its possession which it regards as surplusage. Notwithstanding, outside coun", "start": 37, "end": 313, "normalized_page_characters": 1850, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p020.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "other recordkeeping purposes, but may destroy such material (including electronic media containing such information) in its possession which it regards as surplusage. Notwithstanding, outside coun", "start": 0, "end": 196, "normalized_page_characters": 1851, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p020.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "other recordkeeping purposes, but may destroy such material (including electronic media containing such information) in its possession which it regards as surplusage. Notwithstanding, outside coun", "start": 0, "end": 196, "normalized_page_characters": 1728, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p020.txt" } } }, { "id": "p020-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 20, "expected": "Each nonparty supplier shall be provided a copy of this order by the party seeking information from said supplier.", "original_line_breaks": "Each nonparty supplier shall be provided a copy of this order by the party seeking\ninformation from said supplier.", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " considered a “supplier” as that term is used in the context of this order. 18. Each nonparty supplier shall be provided a copy of this order by the party seeking information from said supplier. 19. Source Code. A supplier may designate documents, information, or things as ", "start": 795, "end": 1069, "normalized_page_characters": 1850, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p020.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " considered a “supplier” as that term is used in the context of this order. 18. Each nonparty supplier shall be provided a copy of this order by the party seeking information from said supplier. 19. Source Code. A supplier may designate documents, information, or things as ", "start": 795, "end": 1069, "normalized_page_characters": 1850, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p020.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " considered a “supplier” as that term is used in the context of this order. 18. Each nonparty supplier shall be provided a copy of this order by the party seeking information from said supplier. 19. Source Code. A supplier may designate documents, information, or things as ", "start": 678, "end": 952, "normalized_page_characters": 1851, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p020.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " considered a “supplier” as that term is used in the context of this order. 18. Each nonparty supplier shall be provided a copy of this order by the party seeking information from said supplier. 19. Source Code. A supplier may designate documents, information, or things as ", "start": 678, "end": 952, "normalized_page_characters": 1728, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p020.txt" } } }, { "id": "p020-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 20, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15" ], "full_page": "pages/pdftotext-default/p020.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101" ], "full_page": "pages/pdftotext-layout/p020.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "full_page": "pages/pdfium-native/p020.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p020.txt" } } }, { "id": "p020-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 20, "expected": "10", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 48, "text": "10" } ] }, "full_page": "pages/pdftotext-default/p020.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 56, "text": " 10" } ] }, "full_page": "pages/pdftotext-layout/p020.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 22, "text": "10 " } ] }, "full_page": "pages/pdfium-native/p020.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "10", "box": [ 300.0, 64.94, 312.0, 78.22 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p020.txt" } } }, { "id": "p020-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 20, "expected": "x", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 49, "text": "x" } ] }, "full_page": "pages/pdftotext-default/p020.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 58, "text": " x" } ] }, "full_page": "pages/pdftotext-layout/p020.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 24, "text": "x" } ] }, "full_page": "pages/pdfium-native/p020.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "x", "box": [ 303.96, 29.7, 309.96, 45.47 ], "kind": "page_number" } ] }, "full_page": "pages/pdfgeo-r23/p020.txt" } } }, { "id": "p020-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 20, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "none", "signals": [ "overprint_present" ], "body_glyphs": 1466, "image_area_fraction": 0.0, "flagged": false } } }, { "id": "p039-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 39, "expected": "It is my duty and responsibility to instruct you on the law you are to apply in this case. The law contained in these instructions is the only law you may follow.", "original_line_breaks": "It is my duty and responsibility to instruct you on the law you are to apply in this case. The law\ncontained in these instructions is the only law you may follow.", "native_layer_class": "absent_body", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case: 23-1101 Document: 15 Page: 39 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 2 of 41 Appx4", "start": 0, "end": 123, "normalized_page_characters": 123, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-default/p039.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case: 23-1101 Document: 15 Page: 39 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 2 of 41 Appx4", "start": 0, "end": 123, "normalized_page_characters": 123, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-layout/p039.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 2 of 41 Appx4 Case: 23-1101 Document: 15 Page: 39 Filed: 05/09/2023", "start": 0, "end": 123, "normalized_page_characters": 123, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p039.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "", "start": 0, "end": 0, "normalized_page_characters": 0, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p039.txt" } } }, { "id": "p039-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 39, "expected": "The testimony of the witnesses and other exhibits introduced by the parties constitute the evidence.", "original_line_breaks": "The testimony of the witnesses and other exhibits introduced by the parties constitute the evidence.", "native_layer_class": "absent_body", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": ": 39 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 2 of 41 Appx4", "start": 31, "end": 123, "normalized_page_characters": 123, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p039.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": ": 39 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 2 of 41 Appx4", "start": 31, "end": 123, "normalized_page_characters": 123, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p039.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 2 of 41 Appx4 Case: 23-1101 Document: 15 Page: 39 Filed: 05/09/2023", "start": 0, "end": 123, "normalized_page_characters": 123, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p039.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "", "start": 0, "end": 0, "normalized_page_characters": 0, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p039.txt" } } }, { "id": "p039-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 39, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx4" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx4" ], "full_page": "pages/pdftotext-default/p039.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx4" ], "full_page": "pages/pdftotext-layout/p039.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx4" ], "full_page": "pages/pdfium-native/p039.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p039.txt" } } }, { "id": "p039-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 39, "expected": "2", "arms": { "pdftotext-default": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-default/p039.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p039.txt" }, "pdfium-native": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdfium-native/p039.txt" }, "pdfgeo-r23": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p039.txt" } } }, { "id": "p039-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 39, "expected": "Appx4", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 11, "text": "Appx4" } ] }, "full_page": "pages/pdftotext-default/p039.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 8, "text": " Appx4" } ] }, "full_page": "pages/pdftotext-layout/p039.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 2, "text": "Appx4" } ] }, "full_page": "pages/pdfium-native/p039.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx4", "box": [ 284.3, 19.32, 322.41, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p039.txt" } } }, { "id": "p039-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 39, "expected": "Page 2 of 41", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 2 of 41" } ] }, "full_page": "pages/pdftotext-default/p039.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 3, "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 2 of 41" } ] }, "full_page": "pages/pdftotext-layout/p039.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 2 of 41" } ] }, "full_page": "pages/pdfium-native/p039.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 2 of 41", "box": [ 126.5, 743.81, 480.23, 754.06 ], "kind": "running_header" } ] }, "full_page": "pages/pdfgeo-r23/p039.txt" } } }, { "id": "p039-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 39, "expected_class": "absent_body", "needs_OCR": true, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "high", "signals": [ "no_body_text", "image_dominant_low_text", "image_region_without_text" ], "body_glyphs": 0, "image_area_fraction": 0.829, "flagged": true } } }, { "id": "p058-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 58, "expected": "I will now instruct you how to decide whether or not EcoFactor has proven that Google has infringed the Asserted Claims of the Asserted Patents.", "original_line_breaks": "I will now instruct you how to decide whether or not EcoFactor has proven that Google has\ninfringed the Asserted Claims of the Asserted Patents.", "native_layer_class": "absent_body", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": " 58 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 21 of 41 Appx23", "start": 32, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p058.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": " 58 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 21 of 41 Appx23", "start": 32, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p058.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 21 of 41 Appx23 Case: 23-1101 Document: 15 Page: 58 Filed: 05/09/2023", "start": 0, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p058.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "", "start": 0, "end": 0, "normalized_page_characters": 0, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p058.txt" } } }, { "id": "p058-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 58, "expected": "In reaching your decision on infringement, keep in mind that only the claims of a patent can be infringed.", "original_line_breaks": "In reaching your decision on infringement, keep in mind that only the claims of a patent can be\ninfringed.", "native_layer_class": "absent_body", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case: 23-1101 Document: 15 Page: 58 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 21 of 41 Appx23", "start": 0, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-default/p058.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case: 23-1101 Document: 15 Page: 58 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 21 of 41 Appx23", "start": 0, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-layout/p058.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 21 of 41 Appx23 Case: 23-1101 Document: 15 Page: 58 Filed: 05/09/2023", "start": 0, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p058.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "", "start": 0, "end": 0, "normalized_page_characters": 0, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p058.txt" } } }, { "id": "p058-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 58, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx23" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx23" ], "full_page": "pages/pdftotext-default/p058.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx23" ], "full_page": "pages/pdftotext-layout/p058.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx23" ], "full_page": "pages/pdfium-native/p058.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p058.txt" } } }, { "id": "p058-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 58, "expected": "21", "arms": { "pdftotext-default": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-default/p058.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p058.txt" }, "pdfium-native": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdfium-native/p058.txt" }, "pdfgeo-r23": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p058.txt" } } }, { "id": "p058-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 58, "expected": "Appx23", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 11, "text": "Appx23" } ] }, "full_page": "pages/pdftotext-default/p058.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 8, "text": " Appx23" } ] }, "full_page": "pages/pdftotext-layout/p058.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 2, "text": "Appx23" } ] }, "full_page": "pages/pdfium-native/p058.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx23", "box": [ 281.76, 19.32, 326.87, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p058.txt" } } }, { "id": "p058-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 58, "expected": "Page 21 of 41", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 21 of 41" } ] }, "full_page": "pages/pdftotext-default/p058.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 3, "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 21 of 41" } ] }, "full_page": "pages/pdftotext-layout/p058.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 21 of 41" } ] }, "full_page": "pages/pdfium-native/p058.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 21 of 41", "box": [ 124.66, 733.28, 483.98, 743.51 ], "kind": "running_header" } ] }, "full_page": "pages/pdfgeo-r23/p058.txt" } } }, { "id": "p058-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 58, "expected_class": "absent_body", "needs_OCR": true, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "high", "signals": [ "no_body_text", "image_dominant_low_text", "image_region_without_text", "low_alpha_ratio" ], "body_glyphs": 0, "image_area_fraction": 0.826, "flagged": true } } }, { "id": "p077-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 77, "expected": "It is now your duty to deliberate and to consult with one another in an effort to reach a verdict.", "original_line_breaks": "It is now your duty to deliberate and to consult with one another in an effort to reach a verdict.", "native_layer_class": "absent_body", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": ": 23-1101 Document: 15 Page: 77 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 40 of 41 Appx42", "start": 4, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p077.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": ": 23-1101 Document: 15 Page: 77 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 40 of 41 Appx42", "start": 4, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p077.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 40 of 41 Appx42 Case: 23-1101 Document: 15 Page: 77 Filed: 05/09/2023", "start": 0, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p077.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "", "start": 0, "end": 0, "normalized_page_characters": 0, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p077.txt" } } }, { "id": "p077-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 77, "expected": "When you go into the jury room to deliberate, you may take with you a copy of this charge, the exhibits that I have admitted into evidence, and your notes.", "original_line_breaks": "When you go into the jury room to deliberate, you may take with you a copy of this charge, the\nexhibits that I have admitted into evidence, and your notes.", "native_layer_class": "absent_body", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": " 77 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 40 of 41 Appx42", "start": 32, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p077.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": " 77 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 40 of 41 Appx42", "start": 32, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p077.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 40 of 41 Appx42 Case: 23-1101 Document: 15 Page: 77 Filed: 05/09/2023", "start": 0, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p077.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "", "start": 0, "end": 0, "normalized_page_characters": 0, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p077.txt" } } }, { "id": "p077-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 77, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx42" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx42" ], "full_page": "pages/pdftotext-default/p077.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx42" ], "full_page": "pages/pdftotext-layout/p077.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx42" ], "full_page": "pages/pdfium-native/p077.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p077.txt" } } }, { "id": "p077-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 77, "expected": "40", "arms": { "pdftotext-default": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-default/p077.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p077.txt" }, "pdfium-native": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdfium-native/p077.txt" }, "pdfgeo-r23": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p077.txt" } } }, { "id": "p077-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 77, "expected": "Appx42", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 11, "text": "Appx42" } ] }, "full_page": "pages/pdftotext-default/p077.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 8, "text": " Appx42" } ] }, "full_page": "pages/pdftotext-layout/p077.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 2, "text": "Appx42" } ] }, "full_page": "pages/pdfium-native/p077.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx42", "box": [ 279.84, 19.32, 324.95, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p077.txt" } } }, { "id": "p077-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 77, "expected": "Page 40 of 41", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 40 of 41" } ] }, "full_page": "pages/pdftotext-default/p077.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 3, "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 40 of 41" } ] }, "full_page": "pages/pdftotext-layout/p077.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 40 of 41" } ] }, "full_page": "pages/pdfium-native/p077.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 40 of 41", "box": [ 122.75, 732.8, 482.04, 743.04 ], "kind": "running_header" } ] }, "full_page": "pages/pdfgeo-r23/p077.txt" } } }, { "id": "p077-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 77, "expected_class": "absent_body", "needs_OCR": true, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "high", "signals": [ "no_body_text", "image_dominant_low_text", "image_region_without_text", "low_alpha_ratio" ], "body_glyphs": 0, "image_area_fraction": 0.826, "flagged": true } } }, { "id": "p096-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 96, "expected": "Transmit content data", "original_line_breaks": "Transmit\ncontent data", "native_layer_class": "noisy_existing_layer", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ent: 15 May 15, 2012 Page: 96 US 8,180,492 B2 Sheet 8 of 8 Fig 8 / Transmit O1 Content data Retrieve logged program -I-O preference data Retrieve logged / 106 user data Match Conten", "start": 31, "end": 212, "normalized_page_characters": 415, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p096.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "2023 U.S. Patent May 15, 2012 Sheet 8 of 8 US 8,180,492 B2 Fig 8 Transmit / O1 Content data Retrieve logged program -I-O preference data Retrieve logged / 106 user data Match Conten", "start": 49, "end": 230, "normalized_page_characters": 415, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p096.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "U.S. Patent May 15, 2012 Sheet 8 of 8 Fig 8 Transmit / O1 Content data Retrieve logged program preference data Retrieve logged user data Match Content data to u", "start": 0, "end": 160, "normalized_page_characters": 418, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p096.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Fig 8 Transmit / O1 Content data Retrieve logged - I - O program preference data Retrieve logged / 106 user data Match Con", "start": 0, "end": 122, "normalized_page_characters": 303, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p096.txt" } } }, { "id": "p096-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 96, "expected": "Match content data to user", "original_line_breaks": "Match content\ndata to user", "native_layer_class": "noisy_existing_layer", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ieve logged program -I-O preference data Retrieve logged / 106 user data Match Content data to user Transmit matching query to user ls actual user = identified user? Retrieve temperature", "start": 127, "end": 313, "normalized_page_characters": 415, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p096.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ieve logged program -I-O preference data Retrieve logged / 106 user data Match Content data to user Transmit matching query to user ls actual user = identified user? Retrieve temperature", "start": 145, "end": 331, "normalized_page_characters": 415, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p096.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "t data Retrieve logged program preference data Retrieve logged user data Match Content data to user - I - O / 106 Transmit matching query to user ls actual user = identified user? Retrie", "start": 64, "end": 250, "normalized_page_characters": 418, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p096.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "e logged - I - O program preference data Retrieve logged / 106 user data Match Content data to user Transmit matching query to user ls actual user = identified user? Retrieve temperature", "start": 40, "end": 226, "normalized_page_characters": 303, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p096.txt" } } }, { "id": "p096-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 96, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx61" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx61" ], "full_page": "pages/pdftotext-default/p096.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx61" ], "full_page": "pages/pdftotext-layout/p096.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx61" ], "full_page": "pages/pdfium-native/p096.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p096.txt" } } }, { "id": "p096-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 96, "expected": "Sheet 8 of 8", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 13, "text": "Sheet 8 of 8" } ] }, "full_page": "pages/pdftotext-default/p096.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 6, "text": "U.S. Patent May 15, 2012 Sheet 8 of 8 US 8,180,492 B2" } ] }, "full_page": "pages/pdftotext-layout/p096.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": "U.S. Patent May 15, 2012 Sheet 8 of 8 " } ] }, "full_page": "pages/pdfium-native/p096.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "U.S. Patent May 15, 2012 Sheet 8 of 8", "box": [ 99.49, 692.06, 354.12, 711.11 ], "kind": "running_header" } ] }, "full_page": "pages/pdfgeo-r23/p096.txt" } } }, { "id": "p096-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 96, "expected": "Appx61", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 55, "text": "Appx61" } ] }, "full_page": "pages/pdftotext-default/p096.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 56, "text": " Appx61" } ] }, "full_page": "pages/pdftotext-layout/p096.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 27, "text": "Appx61" } ] }, "full_page": "pages/pdfium-native/p096.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx61", "box": [ 284.64, 19.32, 329.75, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p096.txt" } } }, { "id": "p096-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 96, "expected_class": "noisy_existing_layer", "needs_OCR": true, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "high", "signals": [ "image_dominant_low_text", "image_region_without_text", "overprint_present" ], "body_glyphs": 253, "image_area_fraction": 0.826, "flagged": true } } }, { "id": "p115-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 115, "expected": "This application is a continuation of U.S. patent application Ser. No. 13/037,162", "original_line_breaks": "This application is a continuation of U.S. patent applica-\ntion Ser. No. 13/037,162", "native_layer_class": "noisy_existing_layer", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "g online. But because utilities are assumed to try to operate as efficiently as This application is a continuation of U.S. patent applica possible, the reserve capacity is likely to be the least efficient and most expensive and/or more pollu", "start": 464, "end": 705, "normalized_page_characters": 7405, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p115.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "g online. But because utilities are assumed to try to operate as efficiently as This application is a continuation of U.S. patent applica possible, the reserve capacity is likely to be the least efficient tion Ser. No. 137037,162, filed Feb.", "start": 555, "end": 796, "normalized_page_characters": 7405, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p115.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "AS TOOL TO VERIFY PEAK DEMAND REDUCTION CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. patent applica tion Ser. No. 137037,162, filed Feb. 28, 2011, now U.S. Pat. No. 8,131.506 which is a continuation of U", "start": 70, "end": 311, "normalized_page_characters": 7405, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p115.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "AS TOOL TO VERIFY PEAK DEMAND REDUCTION CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. patent applica tion Ser. No. 137037,162, filed Feb. 28, 2011, now U.S. Pat. No. 8,131.506 which is a continuation of U", "start": 54, "end": 295, "normalized_page_characters": 7294, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p115.txt" } } }, { "id": "p115-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 115, "expected": "Climate control systems such as heating and cooling systems for buildings", "original_line_breaks": "Climate control systems such as heating and cooling sys-\ntems for buildings", "native_layer_class": "noisy_existing_layer", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "curred. 2. Background with a factory that can offer demand reduction of 50 mega Climate control systems such as heating and cooling sys watts than they would be for the equivalent from residential tems for buildings (heating, ventila", "start": 2698, "end": 2931, "normalized_page_characters": 7405, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p115.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ontract 2. Background with a factory that can offer demand reduction of 50 mega Climate control systems such as heating and cooling sys watts than they would be for the equivalent from residential tems for buildings (heating, ventila", "start": 2789, "end": 3022, "normalized_page_characters": 7405, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p115.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "a computer net work to verify that demand reduction has occurred. 2. Background Climate control systems such as heating and cooling sys tems for buildings (heating, ventilation and cooling, or HVAC systems) have been controlled for d", "start": 1086, "end": 1319, "normalized_page_characters": 7405, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p115.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "a computer net work to verify that demand reduction has occurred. 2. Background Climate control systems such as heating and cooling sys tems for buildings (heating, ventilation and cooling, or HVAC systems) have been controlled for d", "start": 1070, "end": 1303, "normalized_page_characters": 7294, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p115.txt" } } }, { "id": "p115-gutter", "kind": "forbidden_interleaving", "scope": "fixed_sample", "physical_page": 115, "expected": { "id": "p115-gutter", "kind": "forbidden_interleaving", "before": "cooling sys-", "after": "tems for buildings", "forbidden": "30", "reason": "30 is a gutter line number, not a word between systems and for buildings." }, "arms": { "pdftotext-default": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdftotext-default/p115.txt" }, "pdftotext-layout": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdftotext-layout/p115.txt" }, "pdfium-native": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdfium-native/p115.txt" }, "pdfgeo-r23": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdfgeo-r23/p115.txt" } } }, { "id": "p115-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 115, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx80" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx80" ], "full_page": "pages/pdftotext-default/p115.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx80" ], "full_page": "pages/pdftotext-layout/p115.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx80" ], "full_page": "pages/pdfium-native/p115.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p115.txt" } } }, { "id": "p115-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 115, "expected": "1", "arms": { "pdftotext-default": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-default/p115.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p115.txt" }, "pdfium-native": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdfium-native/p115.txt" }, "pdfgeo-r23": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p115.txt" } } }, { "id": "p115-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 115, "expected": "2", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 12, "text": "2" } ] }, "full_page": "pages/pdftotext-default/p115.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p115.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 73, "text": "2 " } ] }, "full_page": "pages/pdfium-native/p115.txt" }, "pdfgeo-r23": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [ { "text": "2", "box": [ 406.91, 680.43, 411.93, 693.13 ] } ], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p115.txt" } } }, { "id": "p115-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 115, "expected": "Appx80", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 102, "text": "Appx80" } ] }, "full_page": "pages/pdftotext-default/p115.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 78, "text": " Appx80" } ] }, "full_page": "pages/pdftotext-layout/p115.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 135, "text": "Appx80" } ] }, "full_page": "pages/pdfium-native/p115.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx80", "box": [ 284.64, 19.32, 329.75, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p115.txt" } } }, { "id": "p115-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 115, "expected_class": "noisy_existing_layer", "needs_OCR": true, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "medium", "signals": [ "image_dominant_with_text", "image_region_with_text" ], "body_glyphs": 6112, "image_area_fraction": 0.826, "flagged": true } } }, { "id": "p134-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 134, "expected": "munication may in the form of a signal sent over the power lines themselves, or a wireless communication over a data", "original_line_breaks": "munication may in the form of a signal sent over the power\nlines themselves, or a wireless communication over a data", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Case: 23-1101 Document: 15 Page: 134 Filed: 05/09/2023 US 8,738,327 B2 3 munication may in the form of a signal sent over the power lines themselves, or a wireless communication over a data 4 By using these multiple data streams to compare the per formance of one syste", "start": 0, "end": 269, "normalized_page_characters": 6998, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p134.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "signal sent over the power By using these multiple data streams to compare the per lines themselves, or a wireless communication over a data formance of one system versus another, and one system ver network arranged by the utility. These meters allow utilities to sus the same", "start": 107, "end": 383, "normalized_page_characters": 6998, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p134.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "US 8,738,327 B2 3 munication may in the form of a signal sent over the power lines themselves, or a wireless communication over a data network arranged by the utility. These meters allow utilities to accomplish a n", "start": 0, "end": 214, "normalized_page_characters": 6998, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p134.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "3 munication may in the form of a signal sent over the power lines themselves, or a wireless communication over a data network arranged by the utility. These meters allow utilities to accomplish a n", "start": 0, "end": 198, "normalized_page_characters": 6887, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p134.txt" } } }, { "id": "p134-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 134, "expected": "relationship between the inside temperature and the outside temperature over time to derive a first prediction for the rate of", "original_line_breaks": "relationship between the inside temperature and the outside\ntemperature over time to derive a first prediction for the rate of", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ure and the outside 35 FIG. 7 is a flow chart illustrating the steps involved in temperature over time to derive a first prediction for the rate of generating a demand reduction event for a given Subscriber. change in inside temperature assuming that the operating FIG. 8 is a flow char", "start": 3485, "end": 3771, "normalized_page_characters": 6998, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p134.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ure and the outside 35 FIG. 7 is a flow chart illustrating the steps involved in temperature over time to derive a first prediction for the rate of generating a demand reduction event for a given Subscriber. change in inside temperature assuming that the operating FIG. 8 is a flow char", "start": 3485, "end": 3771, "normalized_page_characters": 6998, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p134.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "said remote processor from said thermostat, and wherein said processor uses the relationship between the inside temperature and the outside temperature over time to derive a first prediction for the rate of change in inside temperature assuming that the operating status of the HVAC sys", "start": 1643, "end": 1929, "normalized_page_characters": 6998, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p134.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "said remote processor from said thermostat, and wherein said processor uses the relationship between the inside temperature and the outside temperature over time to derive a first prediction for the rate of change in inside temperature assuming that the operating status of the HVAC sys", "start": 1627, "end": 1913, "normalized_page_characters": 6887, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p134.txt" } } }, { "id": "p134-columns", "kind": "forbidden_interleaving", "scope": "fixed_sample", "physical_page": 134, "expected": { "id": "p134-columns", "kind": "forbidden_interleaving", "before": "over the power", "after": "lines themselves", "forbidden": "By using these multiple data streams", "reason": "Right-column opening cannot interrupt the left-column sentence." }, "arms": { "pdftotext-default": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdftotext-default/p134.txt" }, "pdftotext-layout": { "verdict": "fail", "anchor_pairs": 1, "contaminations": [ { "before_start": 119, "after_start": 190, "intervening_text": " By using these multiple data streams to compare the per " } ], "full_page": "pages/pdftotext-layout/p134.txt" }, "pdfium-native": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdfium-native/p134.txt" }, "pdfgeo-r23": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdfgeo-r23/p134.txt" } } }, { "id": "p134-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 134, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx99" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx99" ], "full_page": "pages/pdftotext-default/p134.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx99" ], "full_page": "pages/pdftotext-layout/p134.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx99" ], "full_page": "pages/pdfium-native/p134.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p134.txt" } } }, { "id": "p134-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 134, "expected": "3", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 10, "text": "3" } ] }, "full_page": "pages/pdftotext-default/p134.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p134.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 2, "text": "3 " } ] }, "full_page": "pages/pdfium-native/p134.txt" }, "pdfgeo-r23": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [ { "text": "3", "box": [ 194.62, 680.12, 199.64, 693.17 ] } ], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p134.txt" } } }, { "id": "p134-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 134, "expected": "4", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 14, "text": "4" } ] }, "full_page": "pages/pdftotext-default/p134.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p134.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 74, "text": "4 " } ] }, "full_page": "pages/pdfium-native/p134.txt" }, "pdfgeo-r23": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [ { "text": "4", "box": [ 406.91, 680.43, 412.15, 693.13 ] } ], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p134.txt" } } }, { "id": "p134-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 134, "expected": "Appx99", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 107, "text": "Appx99" } ] }, "full_page": "pages/pdftotext-default/p134.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 78, "text": " Appx99" } ] }, "full_page": "pages/pdftotext-layout/p134.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 135, "text": "Appx99" } ] }, "full_page": "pages/pdfium-native/p134.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx99", "box": [ 284.64, 19.32, 329.75, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p134.txt" } } }, { "id": "p134-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 134, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "medium", "signals": [ "image_dominant_with_text", "image_region_with_text" ], "body_glyphs": 5753, "image_area_fraction": 0.826, "flagged": true } } }, { "id": "p153-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 153, "expected": "in the average home today would have limited value because there are likely to be many places one or more people could", "original_line_breaks": "in the average home today would have limited value because\nthere are likely to be many places one or more people could", "native_layer_class": "absent_body", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case: 23-1101 Document: 15 Page: 153 Appx118 Filed: 05/09/2023", "start": 0, "end": 62, "normalized_page_characters": 62, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-default/p153.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case: 23-1101 Document: 15 Page: 153 Filed: 05/09/2023 Appx118", "start": 0, "end": 62, "normalized_page_characters": 62, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-layout/p153.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Appx118 Case: 23-1101 Document: 15 Page: 153 Filed: 05/09/2023", "start": 0, "end": 62, "normalized_page_characters": 62, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p153.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "", "start": 0, "end": 0, "normalized_page_characters": 0, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p153.txt" } } }, { "id": "p153-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 153, "expected": "home in which the thermostat is located. The server logs the ambient temperature sensed by each thermostat vs. time and", "original_line_breaks": "home in which the thermostat is located. The server logs the\nambient temperature sensed by each thermostat vs. time and", "native_layer_class": "absent_body", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case: 23-1101 Document: 15 Page: 153 Appx118 Filed: 05/09/2023", "start": 0, "end": 62, "normalized_page_characters": 62, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-default/p153.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case: 23-1101 Document: 15 Page: 153 Filed: 05/09/2023 Appx118", "start": 0, "end": 62, "normalized_page_characters": 62, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-layout/p153.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Appx118 Case: 23-1101 Document: 15 Page: 153 Filed: 05/09/2023", "start": 0, "end": 62, "normalized_page_characters": 62, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p153.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "", "start": 0, "end": 0, "normalized_page_characters": 0, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p153.txt" } } }, { "id": "p153-columns", "kind": "forbidden_interleaving", "scope": "fixed_sample", "physical_page": 153, "expected": { "id": "p153-columns", "kind": "forbidden_interleaving", "before": "limited value because", "after": "there are likely", "forbidden": "FIG. 2 shows a high-level illustration", "reason": "Right-column figure description cannot interrupt left-column prose." }, "arms": { "pdftotext-default": { "verdict": "unassessable", "anchor_pairs": 0, "contaminations": [], "full_page": "pages/pdftotext-default/p153.txt" }, "pdftotext-layout": { "verdict": "unassessable", "anchor_pairs": 0, "contaminations": [], "full_page": "pages/pdftotext-layout/p153.txt" }, "pdfium-native": { "verdict": "unassessable", "anchor_pairs": 0, "contaminations": [], "full_page": "pages/pdfium-native/p153.txt" }, "pdfgeo-r23": { "verdict": "unassessable", "anchor_pairs": 0, "contaminations": [], "full_page": "pages/pdfgeo-r23/p153.txt" } } }, { "id": "p153-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 153, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx118" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx118" ], "full_page": "pages/pdftotext-default/p153.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx118" ], "full_page": "pages/pdftotext-layout/p153.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx118" ], "full_page": "pages/pdfium-native/p153.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p153.txt" } } }, { "id": "p153-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 153, "expected": "3", "arms": { "pdftotext-default": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-default/p153.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p153.txt" }, "pdfium-native": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdfium-native/p153.txt" }, "pdfgeo-r23": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p153.txt" } } }, { "id": "p153-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 153, "expected": "4", "arms": { "pdftotext-default": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-default/p153.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p153.txt" }, "pdfium-native": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdfium-native/p153.txt" }, "pdfgeo-r23": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p153.txt" } } }, { "id": "p153-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 153, "expected": "Appx118", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 7, "text": "Appx118" } ] }, "full_page": "pages/pdftotext-default/p153.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 6, "text": " Appx118" } ] }, "full_page": "pages/pdftotext-layout/p153.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": "Appx118" } ] }, "full_page": "pages/pdfium-native/p153.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx118", "box": [ 279.94, 19.32, 332.05, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p153.txt" } } }, { "id": "p153-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 153, "expected_class": "absent_body", "needs_OCR": true, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "high", "signals": [ "no_body_text", "image_dominant_low_text", "image_region_without_text", "low_alpha_ratio" ], "body_glyphs": 0, "image_area_fraction": 0.83, "flagged": true } } }, { "id": "p172-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 172, "expected": "REPLY to Response to Motion, filed by Google LLC, re 64 Opposed MOTION to Amend/Correct for Leave to Amend Invalidity Contentions", "original_line_breaks": "REPLY to Response to Motion, filed by Google LLC, re 64 Opposed MOTION to\nAmend/Correct for Leave to Amend Invalidity Contentions", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ntralized CM/ECF LIVE - U.S. District Court:txwd 12/1/22, 4:53 PM 05/13/2021 67 REPLY to Response to Motion, filed by Google LLC, re 64 Opposed MOTION to Amend/Correct for Leave to Amend Invalidity Contentions filed by Defendant Google LLC (Jones, Michael) (Entered: 05/13/2021) 06/01/2021", "start": 57, "end": 346, "normalized_page_characters": 2774, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p172.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ntralized CM/ECF LIVE - U.S. District Court:txwd 12/1/22, 4:53 PM 05/13/2021 67 REPLY to Response to Motion, filed by Google LLC, re 64 Opposed MOTION to Amend/Correct for Leave to Amend Invalidity Contentions filed by Defendant Google LLC (Jones, Michael) (Entered: 05/13/2021) 06/01/2021", "start": 57, "end": 346, "normalized_page_characters": 2774, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p172.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "courts.gov/cgi-bin/DktRpt.pl?17286105924045-L_1_1-1 Page 16 of 40 05/13/2021 67 REPLY to Response to Motion, filed by Google LLC, re 64 Opposed MOTION to Amend/Correct for Leave to Amend Invalidity Contentions filed by Defendant Google LLC (Jones, Michael) (Entered: 05/13/2021) 06/01/2021", "start": 87, "end": 376, "normalized_page_characters": 2774, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p172.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "05/13/2021 67 REPLY to Response to Motion, filed by Google LLC, re 64 Opposed MOTION to Amend/Correct for Leave to Amend Invalidity Contentions filed by Defendant Google LLC (Jones, Michael) (Entered: 05/13/2021) 06/01/2021", "start": 0, "end": 223, "normalized_page_characters": 2558, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p172.txt" } } }, { "id": "p172-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 172, "expected": "MOTION to Withdraw as Attorney C. Jay Chung by EcoFactor, Inc.. (Attachments: # 1 Proposed Order)", "original_line_breaks": "MOTION to Withdraw as Attorney C. Jay Chung by EcoFactor, Inc.. (Attachments: #\n1 Proposed Order)", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "EcoFactor, Inc.(pty:pla) (Aichele, Matthew) (Entered: 07/14/2021) 07/27/2021 74 MOTION to Withdraw as Attorney C. Jay Chung by EcoFactor, Inc.. (Attachments: # 1 Proposed Order)(Mirzaie, Reza) (Entered: 07/27/2021) 07/29/2021 75 MOTION to Appear Pro Hac Vic", "start": 1278, "end": 1535, "normalized_page_characters": 2774, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p172.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "EcoFactor, Inc.(pty:pla) (Aichele, Matthew) (Entered: 07/14/2021) 07/27/2021 74 MOTION to Withdraw as Attorney C. Jay Chung by EcoFactor, Inc.. (Attachments: # 1 Proposed Order)(Mirzaie, Reza) (Entered: 07/27/2021) 07/29/2021 75 MOTION to Appear Pro Hac Vic", "start": 1278, "end": 1535, "normalized_page_characters": 2774, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p172.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "EcoFactor, Inc.(pty:pla) (Aichele, Matthew) (Entered: 07/14/2021) 07/27/2021 74 MOTION to Withdraw as Attorney C. Jay Chung by EcoFactor, Inc.. (Attachments: # 1 Proposed Order)(Mirzaie, Reza) (Entered: 07/27/2021) 07/29/2021 75 MOTION to Appear Pro Hac Vic", "start": 1308, "end": 1565, "normalized_page_characters": 2774, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p172.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "EcoFactor, Inc.(pty:pla) (Aichele, Matthew) (Entered: 07/14/2021) 07/27/2021 74 MOTION to Withdraw as Attorney C. Jay Chung by EcoFactor, Inc.. (Attachments: # 1 Proposed Order)(Mirzaie, Reza) (Entered: 07/27/2021) 07/29/2021 75 MOTION to Appear Pro Hac Vic", "start": 1144, "end": 1401, "normalized_page_characters": 2558, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p172.txt" } } }, { "id": "p172-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 172, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx137", "Centralized CM/ECF LIVE - U.S. District Court:txwd" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx137", "Centralized CM/ECF LIVE - U.S. District Court:txwd" ], "full_page": "pages/pdftotext-default/p172.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx137", "Centralized CM/ECF LIVE - U.S. District Court:txwd" ], "full_page": "pages/pdftotext-layout/p172.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx137", "Centralized CM/ECF LIVE - U.S. District Court:txwd" ], "full_page": "pages/pdfium-native/p172.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p172.txt" } } }, { "id": "p172-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 172, "expected": "Page 16 of 40", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 100, "text": "Page 16 of 40" } ] }, "full_page": "pages/pdftotext-default/p172.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 45, "text": "https://ecf.txwd.uscourts.gov/cgi-bin/DktRpt.pl?17286105924045-L_1_1-1 Page 16 of 40" } ] }, "full_page": "pages/pdftotext-layout/p172.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 2, "text": "https://ecf.txwd.uscourts.gov/cgi-bin/DktRpt.pl?17286105924045-L_1_1-1 Page 16 of 40" } ] }, "full_page": "pages/pdfium-native/p172.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Page 16 of 40", "box": [ 540.83, 37.49, 588.29, 45.51 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p172.txt" } } }, { "id": "p172-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 172, "expected": "Appx137", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 98, "text": "Appx137" } ] }, "full_page": "pages/pdftotext-default/p172.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 47, "text": " Appx137" } ] }, "full_page": "pages/pdftotext-layout/p172.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 41, "text": "Appx137" } ] }, "full_page": "pages/pdfium-native/p172.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx137", "box": [ 279.94, 19.32, 332.05, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p172.txt" } } }, { "id": "p172-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 172, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "none", "signals": [], "body_glyphs": 2169, "image_area_fraction": 0.0, "flagged": false } } }, { "id": "p191-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 191, "expected": "purchased from the court reporter or viewed at the clerk's office public terminal. If redaction is necessary, a Notice of Redaction Request must be filed within 21 days.", "original_line_breaks": "purchased from the court reporter or viewed at the clerk's office public terminal. If\nredaction is necessary, a Notice of Redaction Request must be filed within 21 days.", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "lized CM/ECF LIVE - U.S. District Court:txwd Filed: 05/09/2023 12/1/22, 4:53 PM purchased from the court reporter or viewed at the clerk's office public terminal. If redaction is necessary, a Notice of Redaction Request must be filed within 21 days. If no such Notice is filed, the transcript will be made available via PACER wit", "start": 43, "end": 372, "normalized_page_characters": 3398, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p191.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " 05/09/2023 Centralized CM/ECF LIVE - U.S. District Court:txwd 12/1/22, 4:53 PM purchased from the court reporter or viewed at the clerk's office public terminal. If redaction is necessary, a Notice of Redaction Request must be filed within 21 days. If no such Notice is filed, the transcript will be made available via PACER wit", "start": 43, "end": 372, "normalized_page_characters": 3400, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p191.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "://ecf.txwd.uscourts.gov/cgi-bin/DktRpt.pl?17286105924045-L_1_1-1 Page 35 of 40 purchased from the court reporter or viewed at the clerk's office public terminal. If redaction is necessary, a Notice of Redaction Request must be filed within 21 days. If no such Notice is filed, the transcript will be made available via PACER wit", "start": 73, "end": 402, "normalized_page_characters": 3400, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p191.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "purchased from the court reporter or viewed at the clerk's office public terminal. If redaction is necessary, a Notice of Redaction Request must be filed within 21 days. If no such Notice is filed, the transcript will be made available via PACER wit", "start": 0, "end": 249, "normalized_page_characters": 3184, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p191.txt" } } }, { "id": "p191-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 191, "expected": "NOTICE of Attorney Appearance by Shaun William Hassett on behalf of Google LLC", "original_line_breaks": "NOTICE of Attorney Appearance by Shaun William Hassett on behalf of Google LLC", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "lkotte - 04.08.2022 FINAL)(Jones, Michael) (Entered: 04/08/2022) 04/11/2022 241 NOTICE of Attorney Appearance by Shaun William Hassett on behalf of Google LLC (Hassett, Shaun) (Entered: 04/11/2022) 04/14/2022 242 Standing Order Regarding ", "start": 1919, "end": 2157, "normalized_page_characters": 3398, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p191.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "otte - 04.08.2022 - FINAL)(Jones, Michael) (Entered: 04/08/2022) 04/11/2022 241 NOTICE of Attorney Appearance by Shaun William Hassett on behalf of Google LLC (Hassett, Shaun) (Entered: 04/11/2022) 04/14/2022 242 Standing Order Regarding ", "start": 1921, "end": 2159, "normalized_page_characters": 3400, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p191.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "otte - 04.08.2022 - FINAL)(Jones, Michael) (Entered: 04/08/2022) 04/11/2022 241 NOTICE of Attorney Appearance by Shaun William Hassett on behalf of Google LLC (Hassett, Shaun) (Entered: 04/11/2022) 04/14/2022 242 Standing Order Regarding ", "start": 1951, "end": 2189, "normalized_page_characters": 3400, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p191.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "otte - 04.08.2022 - FINAL)(Jones, Michael) (Entered: 04/08/2022) 04/11/2022 241 NOTICE of Attorney Appearance by Shaun William Hassett on behalf of Google LLC (Hassett, Shaun) (Entered: 04/11/2022) 04/14/2022 242 Standing Order Regarding ", "start": 1798, "end": 2036, "normalized_page_characters": 3184, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p191.txt" } } }, { "id": "p191-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 191, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx156", "Centralized CM/ECF LIVE - U.S. District Court:txwd" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx156", "Centralized CM/ECF LIVE - U.S. District Court:txwd" ], "full_page": "pages/pdftotext-default/p191.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx156", "Centralized CM/ECF LIVE - U.S. District Court:txwd" ], "full_page": "pages/pdftotext-layout/p191.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx156", "Centralized CM/ECF LIVE - U.S. District Court:txwd" ], "full_page": "pages/pdfium-native/p191.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p191.txt" } } }, { "id": "p191-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 191, "expected": "Page 35 of 40", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 81, "text": "Page 35 of 40" } ] }, "full_page": "pages/pdftotext-default/p191.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 49, "text": "https://ecf.txwd.uscourts.gov/cgi-bin/DktRpt.pl?17286105924045-L_1_1-1 Page 35 of 40" } ] }, "full_page": "pages/pdftotext-layout/p191.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 2, "text": "https://ecf.txwd.uscourts.gov/cgi-bin/DktRpt.pl?17286105924045-L_1_1-1 Page 35 of 40" } ] }, "full_page": "pages/pdfium-native/p191.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Page 35 of 40", "box": [ 539.83, 37.49, 588.3, 45.51 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p191.txt" } } }, { "id": "p191-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 191, "expected": "Appx156", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 79, "text": "Appx156" } ] }, "full_page": "pages/pdftotext-default/p191.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 51, "text": " Appx156" } ] }, "full_page": "pages/pdftotext-layout/p191.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 45, "text": "Appx156" } ] }, "full_page": "pages/pdfium-native/p191.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx156", "box": [ 279.94, 19.32, 332.05, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p191.txt" } } }, { "id": "p191-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 191, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "none", "signals": [], "body_glyphs": 2689, "image_area_fraction": 0.0, "flagged": false } } }, { "id": "p210-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 210, "expected": "place. There was no operational software, but in my head, I was able to do that on a one-house-by-one-house basis.", "original_line_breaks": "place. There was no operational software, but in my\nhead, I was able to do that on a\none-house-by-one-house basis.", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": " a 14:21:55 3 one-house-by-one-house basis. 14:21:57 4 BY MS. WANG: 14:22:09 5 Q There was no operational software, but in my You mentioned you made modifications to the 14:21:52 14:22:10 6 off-the-shelf hardware to collect data; is that 14:22:14 7 correct? 14:22:20 8 A Yes", "start": 162, "end": 436, "normalized_page_characters": 1387, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p210.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": " 05/09/2023 Case 6:20-cv-00075-ADA Document 111-5 Filed 11/19/21 Page 7 of 16 1 place. There was no operational software, but in my 14:21:52 2 head, I was able to do that on a 14:21:55 3 one-house-by-one-house basis. 14:21:57 4 BY MS. WANG: 14:22:09 5 Q You mentioned you ma", "start": 43, "end": 317, "normalized_page_characters": 1387, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p210.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "1 place. There was no operational software, but in my 14:21:52 2 head, I was able to do that on a 14:21:55 3 one-house-by-one-house basis. 14:21:57 4 BY MS. WANG: 14:22:09 5 Q You mentioned you ma", "start": 0, "end": 196, "normalized_page_characters": 1387, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p210.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "place. There was no operational software, but in my head, I was able to do that on a one-house-by-one-house basis. BY MS. WANG: Q You mentioned you made modifications to the off-the-shelf hardwa", "start": 0, "end": 194, "normalized_page_characters": 919, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p210.txt" } } }, { "id": "p210-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 210, "expected": "the hardware. It was a modification to the software that was actually running on the hardware.", "original_line_breaks": "the hardware. It was a modification to the software\nthat was actually running on the hardware.", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "22:22 10 11 the hardware? Yeah. I mean, it wasn't a modification to 14:22:26 12 the hardware. It was a modification to the software 14:22:29 13 that was actually running on the hardware. 14 15 A 14:22:24 Q So there was no modification to the hardware its", "start": 496, "end": 750, "normalized_page_characters": 1387, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p210.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "e hardware? 14:22:24 11 A Yeah. I mean, it wasn't a modification to 14:22:26 12 the hardware. It was a modification to the software 14:22:29 13 that was actually running on the hardware. 14:22:31 14 Q So there was no modification to the 14:22:33 15 hardw", "start": 507, "end": 761, "normalized_page_characters": 1387, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p210.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "e hardware? 14:22:24 11 A Yeah. I mean, it wasn't a modification to 14:22:26 12 the hardware. It was a modification to the software 14:22:29 13 that was actually running on the hardware. 14:22:31 14 Q So there was no modification to the 14:22:33 15 hardw", "start": 386, "end": 640, "normalized_page_characters": 1387, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p210.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ification you made to the hardware? A Yeah. I mean, it wasn't a modification to the hardware. It was a modification to the software that was actually running on the hardware. Q So there was no modification to the hardware itself? A No. No modification to", "start": 260, "end": 514, "normalized_page_characters": 919, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p210.txt" } } }, { "id": "p210-gutter", "kind": "forbidden_interleaving", "scope": "fixed_sample", "physical_page": 210, "expected": { "id": "p210-gutter", "kind": "forbidden_interleaving", "before": "but in my", "after": "head, I was able", "forbidden": "2", "reason": "Line number 2 is not part of the witness's sentence." }, "arms": { "pdftotext-default": { "verdict": "unassessable", "anchor_pairs": 0, "contaminations": [], "full_page": "pages/pdftotext-default/p210.txt" }, "pdftotext-layout": { "verdict": "fail", "anchor_pairs": 1, "contaminations": [ { "before_start": 165, "after_start": 186, "intervening_text": " 14:21:52 2 " } ], "full_page": "pages/pdftotext-layout/p210.txt" }, "pdfium-native": { "verdict": "fail", "anchor_pairs": 1, "contaminations": [ { "before_start": 44, "after_start": 65, "intervening_text": " 14:21:52 2 " } ], "full_page": "pages/pdfium-native/p210.txt" }, "pdfgeo-r23": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdfgeo-r23/p210.txt" } } }, { "id": "p210-timestamp", "kind": "forbidden_interleaving", "scope": "fixed_sample", "physical_page": 210, "expected": { "id": "p210-timestamp", "kind": "forbidden_interleaving", "before": "but in my", "after": "head, I was able", "forbidden": "14:21:52", "reason": "Timestamp is outside the spoken text." }, "arms": { "pdftotext-default": { "verdict": "unassessable", "anchor_pairs": 0, "contaminations": [], "full_page": "pages/pdftotext-default/p210.txt" }, "pdftotext-layout": { "verdict": "fail", "anchor_pairs": 1, "contaminations": [ { "before_start": 165, "after_start": 186, "intervening_text": " 14:21:52 2 " } ], "full_page": "pages/pdftotext-layout/p210.txt" }, "pdfium-native": { "verdict": "fail", "anchor_pairs": 1, "contaminations": [ { "before_start": 44, "after_start": 65, "intervening_text": " 14:21:52 2 " } ], "full_page": "pages/pdfium-native/p210.txt" }, "pdfgeo-r23": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdfgeo-r23/p210.txt" } } }, { "id": "p210-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 210, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx1167", "Veritext Legal Solutions", "866 299-5127" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx1167", "Veritext Legal Solutions", "866 299-5127" ], "full_page": "pages/pdftotext-default/p210.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx1167", "Veritext Legal Solutions", "866 299-5127" ], "full_page": "pages/pdftotext-layout/p210.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx1167", "Veritext Legal Solutions", "866 299-5127" ], "full_page": "pages/pdfium-native/p210.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p210.txt" } } }, { "id": "p210-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 210, "expected": "Page 131", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 178, "text": "Page 131" } ] }, "full_page": "pages/pdftotext-default/p210.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 56, "text": " Page 131" } ] }, "full_page": "pages/pdftotext-layout/p210.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 26, "text": "Page 131" } ] }, "full_page": "pages/pdfium-native/p210.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Page 131", "box": [ 464.18, 80.1, 510.4, 91.0 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p210.txt" } } }, { "id": "p210-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 210, "expected": "Appx1167", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 183, "text": "Appx1167" } ] }, "full_page": "pages/pdftotext-default/p210.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 60, "text": " Appx1167" } ] }, "full_page": "pages/pdftotext-layout/p210.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 30, "text": "Appx1167" } ] }, "full_page": "pages/pdfium-native/p210.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx1167", "box": [ 276.44, 19.32, 335.55, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p210.txt" } } }, { "id": "p210-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 210, "expected": "Page 7 of 16", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Case 6:20-cv-00075-ADA Document 111-5 Filed 11/19/21 Page 7 of 16" } ] }, "full_page": "pages/pdftotext-default/p210.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 3, "text": " Case 6:20-cv-00075-ADA Document 111-5 Filed 11/19/21 Page 7 of 16" } ] }, "full_page": "pages/pdftotext-layout/p210.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 29, "text": "Case 6:20-cv-00075-ADA Document 111-5 Filed 11/19/21 Page 7 of 16" } ] }, "full_page": "pages/pdfium-native/p210.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Case 6:20-cv-00075-ADA Document 111-5 Filed 11/19/21 Page 7 of 16", "box": [ 110.15, 740.95, 494.63, 751.79 ], "kind": "running_header" } ] }, "full_page": "pages/pdfgeo-r23/p210.txt" } } }, { "id": "p210-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 210, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "none", "signals": [], "body_glyphs": 758, "image_area_fraction": 0.0, "flagged": false } } }, { "id": "p229-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 229, "expected": "Now here is where we need to be careful. We want to drop the absolute value signs to", "original_line_breaks": "Now here is where we need to be careful. We want to drop the absolute value signs to", "native_layer_class": "partial_body", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": " 111-8 Filed 11/19/21 Page 4 of 5 RESTRICTED – CONFIDENTIAL SOURCE CODE 37. When the proportionality constants of this equation are solved (using, for example, historical data), temperature can be predicted as a function of time or time can be ", "start": 86, "end": 330, "normalized_page_characters": 621, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p229.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": " 111-8 Filed 11/19/21 Page 4 of 5 RESTRICTED – CONFIDENTIAL SOURCE CODE 37. When the proportionality constants of this equation are solved (using, for example, historical data), temperature can be predicted as a function of time or time can be ", "start": 86, "end": 330, "normalized_page_characters": 621, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p229.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "RESTRICTED – CONFIDENTIAL SOURCE CODE 15 37. When the proportionality constants of this equation are solved (using, for example, historical data), temperature can be predicted as a function of time or time can be ", "start": 0, "end": 213, "normalized_page_characters": 621, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p229.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "RESTRICTED – CONFIDENTIAL SOURCE CODE 37. When the proportionality constants of this equation are solved (using, for example, historical data), temperature can be predicted as a function of time or time can be ", "start": 0, "end": 210, "normalized_page_characters": 489, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p229.txt" } } }, { "id": "p229-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 229, "expected": "Since the object is cooling down to the surrounding temperature, T will always be greater than M so A will be a positive value.", "original_line_breaks": "Since the object is cooling down to the surrounding temperature, T will always be greater\nthan M so A will be a positive value.", "native_layer_class": "partial_body", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ity constants of this equation are solved (using, for example, historical data), temperature can be predicted as a function of time or time can be predicted as a function of temperature. Note that Newton’s law does not in its simplest form comprise a heating or cooling device such as an", "start": 183, "end": 470, "normalized_page_characters": 621, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p229.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ity constants of this equation are solved (using, for example, historical data), temperature can be predicted as a function of time or time can be predicted as a function of temperature. Note that Newton’s law does not in its simplest form comprise a heating or cooling device such as an", "start": 183, "end": 470, "normalized_page_characters": 621, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p229.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ity constants of this equation are solved (using, for example, historical data), temperature can be predicted as a function of time or time can be predicted as a function of temperature. Note that Newton’s law does not in its simplest form comprise a heating or cooling device such as an", "start": 66, "end": 353, "normalized_page_characters": 621, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p229.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ity constants of this equation are solved (using, for example, historical data), temperature can be predicted as a function of time or time can be predicted as a function of temperature. Note that Newton’s law does not in its simplest form comprise a heating or cooling device such as an", "start": 63, "end": 350, "normalized_page_characters": 489, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p229.txt" } } }, { "id": "p229-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 229, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx1192", "RESTRICTED – CONFIDENTIAL SOURCE CODE", "NEWTON'S LAW OF COOLING OR HEATING" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx1192", "RESTRICTED – CONFIDENTIAL SOURCE CODE" ], "full_page": "pages/pdftotext-default/p229.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx1192", "RESTRICTED – CONFIDENTIAL SOURCE CODE" ], "full_page": "pages/pdftotext-layout/p229.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx1192", "RESTRICTED – CONFIDENTIAL SOURCE CODE" ], "full_page": "pages/pdfium-native/p229.txt" }, "pdfgeo-r23": { "verdict": "fail", "residual_strings": [ "RESTRICTED – CONFIDENTIAL SOURCE CODE" ], "full_page": "pages/pdfgeo-r23/p229.txt" } } }, { "id": "p229-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 229, "expected": "1", "arms": { "pdftotext-default": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-default/p229.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p229.txt" }, "pdfium-native": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdfium-native/p229.txt" }, "pdfgeo-r23": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p229.txt" } } }, { "id": "p229-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 229, "expected": "2", "arms": { "pdftotext-default": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-default/p229.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p229.txt" }, "pdfium-native": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdfium-native/p229.txt" }, "pdfgeo-r23": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p229.txt" } } }, { "id": "p229-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 229, "expected": "15", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 19, "text": "15" } ] }, "full_page": "pages/pdftotext-default/p229.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 18, "text": " 15" } ] }, "full_page": "pages/pdftotext-layout/p229.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 2, "text": "15" } ] }, "full_page": "pages/pdfium-native/p229.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "15", "box": [ 291.73, 39.37, 303.25, 52.12 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p229.txt" } } }, { "id": "p229-label-4", "kind": "page_label", "scope": "fixed_sample", "physical_page": 229, "expected": "Appx1192", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 21, "text": "Appx1192" } ] }, "full_page": "pages/pdftotext-default/p229.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 19, "text": " Appx1192" } ] }, "full_page": "pages/pdftotext-layout/p229.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Appx1192" } ] }, "full_page": "pages/pdfium-native/p229.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx1192", "box": [ 276.44, 19.32, 335.55, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p229.txt" } } }, { "id": "p229-label-5", "kind": "page_label", "scope": "fixed_sample", "physical_page": 229, "expected": "Page 4 of 5", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Case 6:20-cv-00075-ADA Document 111-8 Filed 11/19/21 Page 4 of 5" } ] }, "full_page": "pages/pdftotext-default/p229.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 3, "text": " Case 6:20-cv-00075-ADA Document 111-8 Filed 11/19/21 Page 4 of 5" } ] }, "full_page": "pages/pdftotext-layout/p229.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 8, "text": "Case 6:20-cv-00075-ADA Document 111-8 Filed 11/19/21 Page 4 of 5" } ] }, "full_page": "pages/pdfium-native/p229.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Case 6:20-cv-00075-ADA Document 111-8 Filed 11/19/21 Page 4 of 5", "box": [ 109.08, 741.0, 485.91, 751.81 ], "kind": "running_header" } ] }, "full_page": "pages/pdfgeo-r23/p229.txt" } } }, { "id": "p229-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 229, "expected_class": "partial_body", "needs_OCR": true, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "medium", "signals": [ "image_region_without_text" ], "body_glyphs": 408, "image_area_fraction": 0.47, "flagged": true } } }, { "id": "p248-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 248, "expected": "These claims are expressly directed to technical improvements to then-existing technology, namely those associated with electronically programmable thermostats and other", "original_line_breaks": "These claims are expressly directed to technical improvements to then-existing\ntechnology, namely those associated with electronically programmable thermostats and other", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Case: 23-1101 Document: 15 Page: 248 Filed: 05/09/2023 PUBLIC VERSION These claims are expressly directed to technical improvements to then-existing technology, namely those associated with electronically programmable thermostats and other HVAC controls. See Alice, 573 U.S. at 217 (claims patent-eligible as a matter o", "start": 0, "end": 319, "normalized_page_characters": 1982, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p248.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Case: 23-1101 Document: 15 Page: 248 Filed: 05/09/2023 PUBLIC VERSION These claims are expressly directed to technical improvements to then-existing technology, namely those associated with electronically programmable thermostats and other HVAC controls. See Alice, 573 U.S. at 217 (claims patent-eligible as a matter o", "start": 0, "end": 319, "normalized_page_characters": 1982, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p248.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "423 These claims are expressly directed to technical improvements to then-existing technology, namely those associated with electronically programmable thermostats and other HVAC controls. See Alice, 573 U.S. at 217 (claims patent-eligible as a matter o", "start": 0, "end": 253, "normalized_page_characters": 1982, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p248.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "PUBLIC VERSION These claims are expressly directed to technical improvements to then-existing technology, namely those associated with electronically programmable thermostats and other HVAC controls. See Alice, 573 U.S. at 217 (claims patent-eligible as a matter o", "start": 0, "end": 264, "normalized_page_characters": 1914, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p248.txt" } } }, { "id": "p248-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 248, "expected": "thermostat HVAC control system at the time. For instance, the inventions use a networked thermostat HVAC control system", "original_line_breaks": "thermostat HVAC control system at the time. For instance, the inventions use a networked\nthermostat HVAC control system", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "’497 patents purport to overcome the limitations in the conventional electronic thermostat HVAC control system at the time. For instance, the inventions use a networked thermostat HVAC control system to “measure[] temperature” in a building and “reporting said temperature measur", "start": 1057, "end": 1336, "normalized_page_characters": 1982, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p248.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "’497 patents purport to overcome the limitations in the conventional electronic thermostat HVAC control system at the time. For instance, the inventions use a networked thermostat HVAC control system to “measure[] temperature” in a building and “reporting said temperature measur", "start": 1057, "end": 1336, "normalized_page_characters": 1982, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p248.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "’497 patents purport to overcome the limitations in the conventional electronic thermostat HVAC control system at the time. For instance, the inventions use a networked thermostat HVAC control system to “measure[] temperature” in a building and “reporting said temperature measur", "start": 991, "end": 1270, "normalized_page_characters": 1982, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p248.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "’497 patents purport to overcome the limitations in the conventional electronic thermostat HVAC control system at the time. For instance, the inventions use a networked thermostat HVAC control system to “measure[] temperature” in a building and “reporting said temperature measur", "start": 1002, "end": 1281, "normalized_page_characters": 1914, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p248.txt" } } }, { "id": "p248-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 248, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx1919", "PUBLIC VERSION" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx1919", "PUBLIC VERSION" ], "full_page": "pages/pdftotext-default/p248.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx1919", "PUBLIC VERSION" ], "full_page": "pages/pdftotext-layout/p248.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx1919", "PUBLIC VERSION" ], "full_page": "pages/pdfium-native/p248.txt" }, "pdfgeo-r23": { "verdict": "fail", "residual_strings": [ "PUBLIC VERSION" ], "full_page": "pages/pdfgeo-r23/p248.txt" } } }, { "id": "p248-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 248, "expected": "423", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 38, "text": "423" } ] }, "full_page": "pages/pdftotext-default/p248.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 53, "text": " 423" } ] }, "full_page": "pages/pdftotext-layout/p248.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": "423 " } ] }, "full_page": "pages/pdfium-native/p248.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "423", "box": [ 289.47, 51.81, 307.01, 67.56 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p248.txt" } } }, { "id": "p248-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 248, "expected": "Appx1919", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 40, "text": "Appx1919" } ] }, "full_page": "pages/pdftotext-default/p248.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 55, "text": " Appx1919" } ] }, "full_page": "pages/pdftotext-layout/p248.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 26, "text": "PUBLIC VERSION Appx1919" } ] }, "full_page": "pages/pdfium-native/p248.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx1919", "box": [ 276.44, 19.32, 335.55, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p248.txt" } } }, { "id": "p248-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 248, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "none", "signals": [], "body_glyphs": 1613, "image_area_fraction": 0.0, "flagged": false } } }, { "id": "p267-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 267, "expected": "The undersigned hereby certifies that on January 26, 2022, the foregoing was served on", "original_line_breaks": "The undersigned hereby certifies that on January 26, 2022, the foregoing was served on", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": ":20-cv-00075-ADA Document 186 Filed 01/26/22 Page 4 of 4 CERTIFICATE OF SERVICE The undersigned hereby certifies that on January 26, 2022, the foregoing was served on all counsel of record by e-mail. /s/ Reza Mirzaie Appx2253", "start": 61, "end": 286, "normalized_page_characters": 286, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p267.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": ":20-cv-00075-ADA Document 186 Filed 01/26/22 Page 4 of 4 CERTIFICATE OF SERVICE The undersigned hereby certifies that on January 26, 2022, the foregoing was served on all counsel of record by e-mail. /s/ Reza Mirzaie Appx2253", "start": 61, "end": 286, "normalized_page_characters": 286, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p267.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "CERTIFICATE OF SERVICE The undersigned hereby certifies that on January 26, 2022, the foregoing was served on all counsel of record by e-mail. /s/ Reza Mirzaie Case 6:20-cv-00075-ADA Docume", "start": 0, "end": 189, "normalized_page_characters": 286, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p267.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "CERTIFICATE OF SERVICE The undersigned hereby certifies that on January 26, 2022, the foregoing was served on all counsel of record by e-mail. /s/ Reza Mirzaie", "start": 0, "end": 159, "normalized_page_characters": 159, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p267.txt" } } }, { "id": "p267-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 267, "expected": "all counsel of record by e-mail.", "original_line_breaks": "all counsel of record by e-mail.", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ersigned hereby certifies that on January 26, 2022, the foregoing was served on all counsel of record by e-mail. /s/ Reza Mirzaie Appx2253", "start": 148, "end": 286, "normalized_page_characters": 286, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p267.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ersigned hereby certifies that on January 26, 2022, the foregoing was served on all counsel of record by e-mail. /s/ Reza Mirzaie Appx2253", "start": 148, "end": 286, "normalized_page_characters": 286, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p267.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ersigned hereby certifies that on January 26, 2022, the foregoing was served on all counsel of record by e-mail. /s/ Reza Mirzaie Case 6:20-cv-00075-ADA Document 186 Filed 01/26/22 Page 4 of 4", "start": 30, "end": 222, "normalized_page_characters": 286, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p267.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ersigned hereby certifies that on January 26, 2022, the foregoing was served on all counsel of record by e-mail. /s/ Reza Mirzaie", "start": 30, "end": 159, "normalized_page_characters": 159, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p267.txt" } } }, { "id": "p267-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 267, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx2253", "Case 6:20-cv-00075-ADA", "Document 186" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx2253", "Case 6:20-cv-00075-ADA", "Document 186" ], "full_page": "pages/pdftotext-default/p267.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx2253", "Case 6:20-cv-00075-ADA", "Document 186" ], "full_page": "pages/pdftotext-layout/p267.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx2253", "Case 6:20-cv-00075-ADA", "Document 186" ], "full_page": "pages/pdfium-native/p267.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p267.txt" } } }, { "id": "p267-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 267, "expected": "Page 4 of 4", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Case 6:20-cv-00075-ADA Document 186 Filed 01/26/22 Page 4 of 4" } ] }, "full_page": "pages/pdftotext-default/p267.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 6, "text": " Case 6:20-cv-00075-ADA Document 186 Filed 01/26/22 Page 4 of 4" } ] }, "full_page": "pages/pdftotext-layout/p267.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 5, "text": "Case 6:20-cv-00075-ADA Document 186 Filed 01/26/22 Page 4 of 4" } ] }, "full_page": "pages/pdfium-native/p267.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Case 6:20-cv-00075-ADA Document 186 Filed 01/26/22 Page 4 of 4", "box": [ 112.07, 456.02, 493.99, 467.28 ], "kind": "stamp_outside_margin" } ] }, "full_page": "pages/pdfgeo-r23/p267.txt" } } }, { "id": "p267-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 267, "expected": "Appx2253", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 16, "text": "Appx2253" } ] }, "full_page": "pages/pdftotext-default/p267.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 21, "text": " Appx2253" } ] }, "full_page": "pages/pdftotext-layout/p267.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 6, "text": "Appx2253" } ] }, "full_page": "pages/pdfium-native/p267.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx2253", "box": [ 276.44, 19.32, 335.55, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p267.txt" } } }, { "id": "p267-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 267, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "none", "signals": [], "body_glyphs": 134, "image_area_fraction": 0.0, "flagged": false } } }, { "id": "p286-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 286, "expected": "rate of change in inside temperature", "original_line_breaks": "rate of change in inside\ntemperature", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "v-00075-ADA Document 40 Filed 11/17/20 Page 3 of 7 Disputed Constructions Term “rate of change in inside temperature” (’488 patent claims 1, 9; ’327 patent claims 1, 11); “rate of change in temper", "start": 66, "end": 262, "normalized_page_characters": 2267, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p286.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "e 3 of 7 Disputed Constructions Term Plaintiff’s Proposal Defendants’ Proposal “rate of change in inside “the difference between two “the difference between temperature” (’488 patent inside temper", "start": 108, "end": 304, "normalized_page_characters": 2267, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p286.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "2 Disputed Constructions Term Plaintiff’s Proposal Defendants’ Proposal “rate of change in inside temperature” (’488 patent claims 1, 9; ’327 patent claims 1, 11); “rate of change in temper", "start": 0, "end": 189, "normalized_page_characters": 2267, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p286.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Disputed Constructions Term “rate of change in inside temperature” (’488 patent claims 1, 9; ’327 patent Plaintiff’s Proposal “the difference bet", "start": 0, "end": 145, "normalized_page_characters": 2139, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p286.txt" } } }, { "id": "p286-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 286, "expected": "Indefinite due to lack of essential structural connections, under In re", "original_line_breaks": "Indefinite due to lack of\nessential structural\nconnections, under In re", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ent claims 1, 2, 11, 12) Plain and ordinary meaning; no construction necessary. Indefinite due to lack of essential structural connections, under In re Collier, 397 F.2d 1003 (C.C.P.A. 1968), and its progeny. “a user intentionally ", "start": 1614, "end": 1845, "normalized_page_characters": 2267, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p286.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ary meaning; Indefinite due to lack of Indefiniteness no construction necessary. essential structural connections, under In re Collier, 397 F.2d 1003 (C.C.P.A. 1968), and its progeny. “user interface actions Plain and ordinary mean", "start": 1149, "end": 1380, "normalized_page_characters": 2267, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p286.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "1 and 9 – Indefiniteness Plain and ordinary meaning; no construction necessary. Indefinite due to lack of essential structural connections, under In re Collier, 397 F.2d 1003 (C.C.P.A. 1968), and its progeny. “user interface action", "start": 1009, "end": 1240, "normalized_page_characters": 2267, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p286.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ination [of the claimed property] by an instrument by using standardized units” Indefinite due to lack of essential structural connections, under In re Collier, 397 F.2d 1003 (C.C.P.A. 1968), and its progeny. “a user intentionally ", "start": 965, "end": 1196, "normalized_page_characters": 2139, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p286.txt" } } }, { "id": "p286-cells", "kind": "forbidden_interleaving", "scope": "fixed_sample", "physical_page": 286, "expected": { "id": "p286-cells", "kind": "forbidden_interleaving", "before": "rate of change in inside", "after": "temperature", "forbidden": "the difference between", "reason": "Proposed-construction text in another cell must not interrupt the term phrase." }, "arms": { "pdftotext-default": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdftotext-default/p286.txt" }, "pdftotext-layout": { "verdict": "fail", "anchor_pairs": 1, "contaminations": [ { "before_start": 188, "after_start": 265, "intervening_text": " “the difference between two “the difference between " } ], "full_page": "pages/pdftotext-layout/p286.txt" }, "pdfium-native": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdfium-native/p286.txt" }, "pdfgeo-r23": { "verdict": "pass", "anchor_pairs": 1, "contaminations": [], "full_page": "pages/pdfgeo-r23/p286.txt" } } }, { "id": "p286-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 286, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx6752" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx6752" ], "full_page": "pages/pdftotext-default/p286.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx6752" ], "full_page": "pages/pdftotext-layout/p286.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx6752" ], "full_page": "pages/pdfium-native/p286.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p286.txt" } } }, { "id": "p286-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 286, "expected": "2", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 108, "text": "2" } ] }, "full_page": "pages/pdftotext-default/p286.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 57, "text": " 2" } ] }, "full_page": "pages/pdftotext-layout/p286.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": "2 " } ] }, "full_page": "pages/pdfium-native/p286.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "2", "box": [ 295.45, 38.27, 301.21, 53.78 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p286.txt" } } }, { "id": "p286-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 286, "expected": "Appx6752", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 110, "text": "Appx6752" } ] }, "full_page": "pages/pdftotext-default/p286.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 58, "text": " Appx6752" } ] }, "full_page": "pages/pdftotext-layout/p286.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 87, "text": "Appx6752" } ] }, "full_page": "pages/pdfium-native/p286.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx6752", "box": [ 276.44, 19.32, 335.55, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p286.txt" } } }, { "id": "p286-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 286, "expected": "Page 3 of 7", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Case 6:20-cv-00075-ADA Document 40 Filed 11/17/20 Page 3 of 7" } ] }, "full_page": "pages/pdftotext-default/p286.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 3, "text": " Case 6:20-cv-00075-ADA Document 40 Filed 11/17/20 Page 3 of 7" } ] }, "full_page": "pages/pdftotext-layout/p286.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 86, "text": "Case 6:20-cv-00075-ADA Document 40 Filed 11/17/20 Page 3 of 7" } ] }, "full_page": "pages/pdfium-native/p286.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Case 6:20-cv-00075-ADA Document 40 Filed 11/17/20 Page 3 of 7", "box": [ 118.23, 741.0, 478.42, 751.8 ], "kind": "running_header" } ] }, "full_page": "pages/pdfgeo-r23/p286.txt" } } }, { "id": "p286-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 286, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "none", "signals": [], "body_glyphs": 1824, "image_area_fraction": 0.0, "flagged": false } } }, { "id": "p305-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 305, "expected": "Program Definitions", "original_line_breaks": "Program Definitions", "native_layer_class": "noisy_existing_layer", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " Patent Application Publication Jun. 17, 2004 Sheet 18 of 18 US 2004/0117330 A1 Program Definitions gr 5,58 5.60 Supply Type O on Demand Oscheduled 1 N-5.62 Available Time: From: ", "start": 54, "end": 233, "normalized_page_characters": 825, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p305.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " Patent Application Publication Jun. 17, 2004 Sheet 18 of 18 US 2004/0117330 A1 Program Definitions gr 5,58 5.60 Supply Type O on Demand Oscheduled 1 N-5.62 Available Time: From: ", "start": 54, "end": 233, "normalized_page_characters": 825, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p305.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Patent Application Publication Jun. 17, 2004 Sheet 18 of 18 US 2004/0117330 A1 Program Definitions gr 5,58 5.60 Supply Type O on Demand Oscheduled 1 N-5.62 Available Time: From: ", "start": 0, "end": 178, "normalized_page_characters": 827, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p305.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Program Definitions gr Supply Type O on Demand Oscheduled 1 N-5.62 Available Time: From: HH Availab", "start": 0, "end": 99, "normalized_page_characters": 639, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p305.txt" } } }, { "id": "p305-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 305, "expected": "Energy Consumption for Tuesday , March 18 ,2003", "original_line_breaks": "Energy Consumption for Tuesday , March 18 ,2003", "native_layer_class": "noisy_existing_layer", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "orhood Power Company Daily Report for Electric Meter M Total Usage: 647.32 kWh. Energy Consumption for Tuesday, March 18,2003 O Hourly kWH 20.00 18.00 16.00 400 200 s 0.00 8.00 6.00 4.00 200 0.00 00 01 02 03", "start": 424, "end": 631, "normalized_page_characters": 825, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p305.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "orhood Power Company M Daily Report for Electric Meter Total Usage: 647.32 kWh. Energy Consumption for Tuesday, March 18,2003 O Hourly kWH 20.00 18.00 16.00 400 200 s 0.00 8.00 6.00 4.00 200 0.00 00 01 02 03", "start": 424, "end": 631, "normalized_page_characters": 825, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p305.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "orhood Power Company M Daily Report for Electric Meter Total Usage: 647.32 kWh. Energy Consumption for Tuesday, March 18,2003 O Hourly kWH 20.00 18.00 16.00 400 200 s 0.00 8.00 6.00 4.00 200 0.00 00 01 02 03", "start": 369, "end": 576, "normalized_page_characters": 827, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p305.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "hborhood Power Company Daily Report for Electric Meter Total Usage: 647.32 kWh. Energy Consumption for Tuesday, March 18,2003 M O Hourly kWH 20.00 18.00 16.00 400 200 s 0.00 8.00 6.00 4.00 200 0.00 00 01 02 ", "start": 288, "end": 495, "normalized_page_characters": 639, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p305.txt" } } }, { "id": "p305-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 305, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx10124", "DTX0219, Page 19 of 50", "DC_PRIOR_ART_0000421" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx10124", "DTX0219, Page 19 of 50", "DC_PRIOR_ART_0000421" ], "full_page": "pages/pdftotext-default/p305.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx10124", "DTX0219, Page 19 of 50", "DC_PRIOR_ART_0000421" ], "full_page": "pages/pdftotext-layout/p305.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx10124", "DTX0219, Page 19 of 50", "DC_PRIOR_ART_0000421" ], "full_page": "pages/pdfium-native/p305.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p305.txt" } } }, { "id": "p305-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 305, "expected": "Sheet 18 of 18", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Patent Application Publication Jun. 17, 2004 Sheet 18 of 18 US 2004/0117330 A1" } ] }, "full_page": "pages/pdftotext-default/p305.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 6, "text": "Patent Application Publication Jun. 17, 2004 Sheet 18 of 18 US 2004/0117330 A1" } ] }, "full_page": "pages/pdftotext-layout/p305.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": "Patent Application Publication Jun. 17, 2004 Sheet 18 of 18 US 2004/0117330 A1 " } ] }, "full_page": "pages/pdfium-native/p305.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Patent Application Publication Jun. 17, 2004 Sheet 18 of 18 US 2004/0117330 A1", "box": [ 84.33, 716.4, 482.91, 736.01 ], "kind": "running_header" } ] }, "full_page": "pages/pdfgeo-r23/p305.txt" } } }, { "id": "p305-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 305, "expected": "DTX0219, Page 19 of 50", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 84, "text": "DTX0219, Page 19 of 50" } ] }, "full_page": "pages/pdftotext-default/p305.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 53, "text": " DTX0219, Page 19 of 50" } ] }, "full_page": "pages/pdftotext-layout/p305.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 45, "text": "DTX0219, Page 19 of 50" } ] }, "full_page": "pages/pdfium-native/p305.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "DTX0219, Page 19 of 50", "box": [ 203.2, 39.71, 353.14, 54.32 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p305.txt" } } }, { "id": "p305-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 305, "expected": "Appx10124", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 86, "text": "Appx10124" } ] }, "full_page": "pages/pdftotext-default/p305.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 54, "text": " Appx10124" } ] }, "full_page": "pages/pdftotext-layout/p305.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 46, "text": "Appx10124" } ] }, "full_page": "pages/pdfium-native/p305.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx10124", "box": [ 245.34, 19.32, 311.45, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p305.txt" } } }, { "id": "p305-label-4", "kind": "page_label", "scope": "fixed_sample", "physical_page": 305, "expected": "DC_PRIOR_ART_0000421", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 82, "text": "DC_PRIOR_ART_0000421" } ] }, "full_page": "pages/pdftotext-default/p305.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 52, "text": " DC_PRIOR_ART_0000421" } ] }, "full_page": "pages/pdftotext-layout/p305.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 44, "text": "DC_PRIOR_ART_0000421" } ] }, "full_page": "pages/pdfium-native/p305.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "DC_PRIOR_ART_0000421", "box": [ 332.01, 54.97, 461.79, 69.53 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p305.txt" } } }, { "id": "p305-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 305, "expected_class": "noisy_existing_layer", "needs_OCR": true, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "medium", "signals": [ "image_dominant_with_text", "image_region_without_text", "overprint_present" ], "body_glyphs": 515, "image_area_fraction": 1.0, "flagged": true } } }, { "id": "p324-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 324, "expected": "should be noted here that the set point of the system 3.08 was set at a fixed point for the entire day and the use of humidity", "original_line_breaks": "should be noted here that the set point of the system 3.08 was\nset at a fixed point for the entire day and the use of humidity", "native_layer_class": "noisy_existing_layer", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "-1101 Document: 15 Page: 324 US 2004/0117330 A1 Filed: 05/09/2023 Jun. 17, 2004 should be noted here that the set point of the system 3.08 was Set at a fixed point for the entire day and the use of humidity Sensing and control of humidity levels were not introduced into the illustratio", "start": 8, "end": 294, "normalized_page_characters": 7579, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p324.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "-1101 Document: 15 Page: 324 Filed: 05/09/2023 US 2004/0117330 A1 Jun. 17, 2004 should be noted here that the set point of the system 3.08 was 1.04. For the maximum savings setting, the dead band in this Set at a fixed point for the entire day and the use of humidity example would be r", "start": 8, "end": 294, "normalized_page_characters": 7579, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p324.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "US 2004/0117330 A1 should be noted here that the set point of the system 3.08 was Set at a fixed point for the entire day and the use of humidity Sensing and control of humidity levels were not introduced into the illustratio", "start": 0, "end": 225, "normalized_page_characters": 7579, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p324.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "should be noted here that the set point of the system 3.08 was Set at a fixed point for the entire day and the use of humidity Sensing and control of humidity levels were not introduced into the illustratio", "start": 0, "end": 206, "normalized_page_characters": 7437, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p324.txt" } } }, { "id": "p324-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 324, "expected": "While this example would in its simplest from provide a selection of 10 options", "original_line_breaks": "While this example would in its simplest from provide a\nselection of 10 options", "native_layer_class": "noisy_existing_layer", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ct from, where 1 is pure comfort management and 10 is pure economic management. While this example would in its simplest from provide a Selection of 10 options, the underlying control options used by the system 3.08 could be modified and e", "start": 1701, "end": 1940, "normalized_page_characters": 7579, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p324.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "e economic management. should not be construed to limit the capabilities of the While this example would in its simplest from provide a System 3.08 to perform these functions using different Selection of 10 options, the underlying control ", "start": 3365, "end": 3604, "normalized_page_characters": 7579, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p324.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ct from, where 1 is pure comfort management and 10 is pure economic management. While this example would in its simplest from provide a Selection of 10 options, the underlying control options used by the system 3.08 could be modified and e", "start": 1632, "end": 1871, "normalized_page_characters": 7579, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p324.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ct from, where 1 is pure comfort management and 10 is pure economic management. While this example would in its simplest from provide a Selection of 10 options, the underlying control options used by the system 3.08 could be modified and e", "start": 1613, "end": 1852, "normalized_page_characters": 7437, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p324.txt" } } }, { "id": "p324-columns", "kind": "forbidden_interleaving", "scope": "fixed_sample", "physical_page": 324, "expected": { "id": "p324-columns", "kind": "forbidden_interleaving", "before": "system 3.08 was", "after": "set at a fixed point", "forbidden": "For the maximum savings setting", "reason": "Right-column continuation must not interrupt the left-column sentence." }, "arms": { "pdftotext-default": { "verdict": "unassessable", "anchor_pairs": 0, "contaminations": [], "full_page": "pages/pdftotext-default/p324.txt" }, "pdftotext-layout": { "verdict": "unassessable", "anchor_pairs": 0, "contaminations": [], "full_page": "pages/pdftotext-layout/p324.txt" }, "pdfium-native": { "verdict": "unassessable", "anchor_pairs": 0, "contaminations": [], "full_page": "pages/pdfium-native/p324.txt" }, "pdfgeo-r23": { "verdict": "unassessable", "anchor_pairs": 0, "contaminations": [], "full_page": "pages/pdfgeo-r23/p324.txt" } } }, { "id": "p324-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 324, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx10143", "DTX0219, Page 38 of 50", "DC_PRIOR_ART_0000440" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx10143", "DTX0219, Page 38 of 50", "DC_PRIOR_ART_0000440" ], "full_page": "pages/pdftotext-default/p324.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx10143", "DTX0219, Page 38 of 50", "DC_PRIOR_ART_0000440" ], "full_page": "pages/pdftotext-layout/p324.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx10143", "DTX0219, Page 38 of 50", "DC_PRIOR_ART_0000440" ], "full_page": "pages/pdfium-native/p324.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p324.txt" } } }, { "id": "p324-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 324, "expected": "19", "arms": { "pdftotext-default": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-default/p324.txt" }, "pdftotext-layout": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdftotext-layout/p324.txt" }, "pdfium-native": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [] }, "full_page": "pages/pdfium-native/p324.txt" }, "pdfgeo-r23": { "verdict": "missing", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p324.txt" } } }, { "id": "p324-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 324, "expected": "Appx10143", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 153, "text": "Appx10143" } ] }, "full_page": "pages/pdftotext-default/p324.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 80, "text": " Appx10143" } ] }, "full_page": "pages/pdftotext-layout/p324.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 124, "text": "Appx10143" } ] }, "full_page": "pages/pdfium-native/p324.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx10143", "box": [ 245.34, 19.32, 311.45, 37.72 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p324.txt" } } }, { "id": "p324-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 324, "expected": "DTX0219, Page 38 of 50", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 151, "text": "DTX0219, Page 38 of 50" } ] }, "full_page": "pages/pdftotext-default/p324.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 79, "text": " DTX0219, Page 38 of 50" } ] }, "full_page": "pages/pdftotext-layout/p324.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 123, "text": "DTX0219, Page 38 of 50" } ] }, "full_page": "pages/pdfium-native/p324.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "DTX0219, Page 38 of 50", "box": [ 203.2, 39.71, 353.14, 54.32 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p324.txt" } } }, { "id": "p324-label-4", "kind": "page_label", "scope": "fixed_sample", "physical_page": 324, "expected": "DC_PRIOR_ART_0000440", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 149, "text": "DC_PRIOR_ART_0000440" } ] }, "full_page": "pages/pdftotext-default/p324.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 78, "text": " DC_PRIOR_ART_0000440" } ] }, "full_page": "pages/pdftotext-layout/p324.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 122, "text": "DC_PRIOR_ART_0000440" } ] }, "full_page": "pages/pdfium-native/p324.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "DC_PRIOR_ART_0000440", "box": [ 332.01, 54.97, 461.79, 69.53 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p324.txt" } } }, { "id": "p324-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 324, "expected_class": "noisy_existing_layer", "needs_OCR": true, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "medium", "signals": [ "image_dominant_with_text", "image_region_with_text" ], "body_glyphs": 6138, "image_area_fraction": 1.0, "flagged": true } } }, { "id": "p343-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 343, "expected": "Pages APPX10364; APPX10367", "original_line_breaks": "Pages APPX10364;\nAPPX10367", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Case: 23-1101 Document: 15 Page: 343 Filed: 05/09/2023 Pages APPX10364; APPX10367 Removed Due to Confidential Material", "start": 0, "end": 118, "normalized_page_characters": 118, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-default/p343.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Case: 23-1101 Document: 15 Page: 343 Filed: 05/09/2023 Pages APPX10364; APPX10367 Removed Due to Confidential Material", "start": 0, "end": 118, "normalized_page_characters": 118, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-layout/p343.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Pages APPX10364; APPX10367 Removed Due to Confidential Material Case: 23-1101 Document: 15 Page: 343 Filed", "start": 0, "end": 106, "normalized_page_characters": 118, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p343.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Pages APPX10364; APPX10367 Removed Due to Confidential Material", "start": 0, "end": 63, "normalized_page_characters": 63, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p343.txt" } } }, { "id": "p343-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 343, "expected": "Removed Due to Confidential Material", "original_line_breaks": "Removed Due to Confidential Material", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "se: 23-1101 Document: 15 Page: 343 Filed: 05/09/2023 Pages APPX10364; APPX10367 Removed Due to Confidential Material", "start": 2, "end": 118, "normalized_page_characters": 118, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p343.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "se: 23-1101 Document: 15 Page: 343 Filed: 05/09/2023 Pages APPX10364; APPX10367 Removed Due to Confidential Material", "start": 2, "end": 118, "normalized_page_characters": 118, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p343.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Pages APPX10364; APPX10367 Removed Due to Confidential Material Case: 23-1101 Document: 15 Page: 343 Filed: 05/09/2023", "start": 0, "end": 118, "normalized_page_characters": 118, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p343.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Pages APPX10364; APPX10367 Removed Due to Confidential Material", "start": 0, "end": 63, "normalized_page_characters": 63, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p343.txt" } } }, { "id": "p343-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 343, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "full_page": "pages/pdftotext-default/p343.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "full_page": "pages/pdftotext-layout/p343.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "full_page": "pages/pdfium-native/p343.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p343.txt" } } }, { "id": "p343-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 343, "expected": "APPX10364", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Pages APPX10364;" } ] }, "full_page": "pages/pdftotext-default/p343.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 6, "text": " Pages APPX10364;" } ] }, "full_page": "pages/pdftotext-layout/p343.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": "Pages APPX10364;" } ] }, "full_page": "pages/pdfium-native/p343.txt" }, "pdfgeo-r23": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [ { "text": "Pages APPX10364;", "box": [ 231.9, 395.51, 452.89, 432.09 ] } ], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p343.txt" } } }, { "id": "p343-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 343, "expected": "APPX10367", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 10, "text": "APPX10367" } ] }, "full_page": "pages/pdftotext-default/p343.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 7, "text": " APPX10367" } ] }, "full_page": "pages/pdftotext-layout/p343.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 2, "text": "APPX10367" } ] }, "full_page": "pages/pdfium-native/p343.txt" }, "pdfgeo-r23": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [ { "text": "APPX10367", "box": [ 272.0, 359.11, 412.76, 395.69 ] } ], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p343.txt" } } }, { "id": "p343-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 343, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "none", "signals": [], "body_glyphs": 56, "image_area_fraction": 0.0, "flagged": false } } }, { "id": "p362-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 362, "expected": "Pages APPX10439; APPX10467", "original_line_breaks": "Pages APPX10439;\nAPPX10467", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Case: 23-1101 Document: 15 Page: 362 Filed: 05/09/2023 Pages APPX10439; APPX10467 Removed Due to Confidential Material", "start": 0, "end": 118, "normalized_page_characters": 118, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-default/p362.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Case: 23-1101 Document: 15 Page: 362 Filed: 05/09/2023 Pages APPX10439; APPX10467 Removed Due to Confidential Material", "start": 0, "end": 118, "normalized_page_characters": 118, "excerpt_is_complete_page": true }, "full_page": "pages/pdftotext-layout/p362.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Pages APPX10439; APPX10467 Removed Due to Confidential Material Case: 23-1101 Document: 15 Page: 362 Filed", "start": 0, "end": 106, "normalized_page_characters": 118, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p362.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Pages APPX10439; APPX10467 Removed Due to Confidential Material", "start": 0, "end": 63, "normalized_page_characters": 63, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p362.txt" } } }, { "id": "p362-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 362, "expected": "Removed Due to Confidential Material", "original_line_breaks": "Removed Due to Confidential Material", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "se: 23-1101 Document: 15 Page: 362 Filed: 05/09/2023 Pages APPX10439; APPX10467 Removed Due to Confidential Material", "start": 2, "end": 118, "normalized_page_characters": 118, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p362.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "se: 23-1101 Document: 15 Page: 362 Filed: 05/09/2023 Pages APPX10439; APPX10467 Removed Due to Confidential Material", "start": 2, "end": 118, "normalized_page_characters": 118, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p362.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Pages APPX10439; APPX10467 Removed Due to Confidential Material Case: 23-1101 Document: 15 Page: 362 Filed: 05/09/2023", "start": 0, "end": 118, "normalized_page_characters": 118, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p362.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "Pages APPX10439; APPX10467 Removed Due to Confidential Material", "start": 0, "end": 63, "normalized_page_characters": 63, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p362.txt" } } }, { "id": "p362-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 362, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "full_page": "pages/pdftotext-default/p362.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "full_page": "pages/pdftotext-layout/p362.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Filed: 05/09/2023" ], "full_page": "pages/pdfium-native/p362.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p362.txt" } } }, { "id": "p362-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 362, "expected": "APPX10439", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 9, "text": "Pages APPX10439;" } ] }, "full_page": "pages/pdftotext-default/p362.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 6, "text": " Pages APPX10439;" } ] }, "full_page": "pages/pdftotext-layout/p362.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 1, "text": "Pages APPX10439;" } ] }, "full_page": "pages/pdfium-native/p362.txt" }, "pdfgeo-r23": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [ { "text": "Pages APPX10439;", "box": [ 234.66, 395.51, 455.65, 432.09 ] } ], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p362.txt" } } }, { "id": "p362-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 362, "expected": "APPX10467", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 10, "text": "APPX10467" } ] }, "full_page": "pages/pdftotext-default/p362.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 7, "text": " APPX10467" } ] }, "full_page": "pages/pdftotext-layout/p362.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 2, "text": "APPX10467" } ] }, "full_page": "pages/pdfium-native/p362.txt" }, "pdfgeo-r23": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [ { "text": "APPX10467", "box": [ 274.77, 359.11, 415.54, 395.69 ] } ], "removed_candidates": [] }, "full_page": "pages/pdfgeo-r23/p362.txt" } } }, { "id": "p362-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 362, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "none", "signals": [], "body_glyphs": 56, "image_area_fraction": 0.0, "flagged": false } } }, { "id": "p373-a", "kind": "phrase", "scope": "fixed_sample", "physical_page": 373, "expected": "we’re taking steps to make that possible for most systems in Canada and the U.S. with HVAC monitoring, which is rolling out today to all Nest thermostats in those regions.", "original_line_breaks": "we’re taking steps to make that possible for most systems in Canada and the U.S.\nwith HVAC monitoring, which is rolling out today to all Nest thermostats in those regions.", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "y to figure out when something might be going wrong with your HVAC system. Now, we’re taking steps to make that possible for most systems in Canada and the U.S. with HVAC monitoring, which is rolling out today to all Nest thermostats in those regions. Where did the idea for the HVAC monitoring feature come from? Marco: It started", "start": 71, "end": 402, "normalized_page_characters": 2058, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p373.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "y to figure out when something might be going wrong with your HVAC system. Now, we’re taking steps to make that possible for most systems in Canada and the U.S. with HVAC monitoring, which is rolling out today to all Nest thermostats in those regions. Where did the idea for the HVAC monitoring feature come from? Marco: It started", "start": 71, "end": 402, "normalized_page_characters": 2058, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p373.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "y to figure out when something might be going wrong with your HVAC system. Now, we’re taking steps to make that possible for most systems in Canada and the U.S. with HVAC monitoring, which is rolling out today to all Nest thermostats in those regions. Where did the idea for the HVAC monitoring feature come from? Marco: It started", "start": 6, "end": 337, "normalized_page_characters": 2076, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p373.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "y to figure out when something might be going wrong with your HVAC system. Now, we’re taking steps to make that possible for most systems in Canada and the U.S. with HVAC monitoring, which is rolling out today to all Nest thermostats in those regions. Where did the idea for the HVAC monitoring feature come from? Marco: It started", "start": 6, "end": 337, "normalized_page_characters": 1958, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p373.txt" } } }, { "id": "p373-b", "kind": "phrase", "scope": "fixed_sample", "physical_page": 373, "expected": "Ramya: Cloud computing advancements, definitely. We used to run a lot of algorithms on the device, that’s what got Nest started.", "original_line_breaks": "Ramya: Cloud computing advancements, definitely. We used to run a lot of algorithms on\nthe device, that’s what got Nest started.", "native_layer_class": "sampled_text_present", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ncouraged to provide more proactive help to customers. What made this possible? Ramya: Cloud computing advancements, definitely. We used to run a lot of algorithms on the device, that’s what got Nest started. Now, with cloud computing, we can aggregate data anonymously from Nest thermost", "start": 1038, "end": 1326, "normalized_page_characters": 2058, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p373.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ncouraged to provide more proactive help to customers. What made this possible? Ramya: Cloud computing advancements, definitely. We used to run a lot of algorithms on the device, that’s what got Nest started. Now, with cloud computing, we can aggregate data anonymously from Nest thermost", "start": 1038, "end": 1326, "normalized_page_characters": 2058, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p373.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ncouraged to provide more proactive help to customers. What made this possible? Ramya: Cloud computing advancements, definitely. We used to run a lot of algorithms on the device, that’s what got Nest started. Now, with cloud computing, we can aggregate data anonymously from Nest thermost", "start": 973, "end": 1261, "normalized_page_characters": 2076, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p373.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ncouraged to provide more proactive help to customers. What made this possible? Ramya: Cloud computing advancements, definitely. We used to run a lot of algorithms on the device, that’s what got Nest started. Now, with cloud computing, we can aggregate data anonymously from Nest thermost", "start": 973, "end": 1261, "normalized_page_characters": 1958, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p373.txt" } } }, { "id": "p373-furniture", "kind": "furniture", "scope": "fixed_sample", "physical_page": 373, "expected_absent_from_body": [ "Case: 23-1101", "Document: 15", "Appx10894", "PTX-0263-0003", "EF_0895725" ], "arms": { "pdftotext-default": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx10894", "PTX-0263-0003", "EF_0895725" ], "full_page": "pages/pdftotext-default/p373.txt" }, "pdftotext-layout": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx10894", "PTX-0263-0003", "EF_0895725" ], "full_page": "pages/pdftotext-layout/p373.txt" }, "pdfium-native": { "verdict": "fail", "residual_strings": [ "Case: 23-1101", "Document: 15", "Appx10894", "PTX-0263-0003", "EF_0895725" ], "full_page": "pages/pdfium-native/p373.txt" }, "pdfgeo-r23": { "verdict": "pass", "residual_strings": [], "full_page": "pages/pdfgeo-r23/p373.txt" } } }, { "id": "p373-label-1", "kind": "page_label", "scope": "fixed_sample", "physical_page": 373, "expected": "PTX-0263-0003", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 44, "text": "PTX-0263-0003" } ] }, "full_page": "pages/pdftotext-default/p373.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 49, "text": " PTX-0263-0003" } ] }, "full_page": "pages/pdftotext-layout/p373.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 32, "text": "PTX-0263-0003" } ] }, "full_page": "pages/pdfium-native/p373.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "PTX-0263-0003", "box": [ 271.23, 48.3, 342.59, 60.34 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p373.txt" } } }, { "id": "p373-label-2", "kind": "page_label", "scope": "fixed_sample", "physical_page": 373, "expected": "Appx10894", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 46, "text": "Appx10894" } ] }, "full_page": "pages/pdftotext-default/p373.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 50, "text": " Appx10894" } ] }, "full_page": "pages/pdftotext-layout/p373.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 33, "text": "Appx10894" } ] }, "full_page": "pages/pdfium-native/p373.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "Appx10894", "box": [ 272.94, 26.52, 339.05, 44.92 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p373.txt" } } }, { "id": "p373-label-3", "kind": "page_label", "scope": "fixed_sample", "physical_page": 373, "expected": "EF_0895725", "arms": { "pdftotext-default": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 42, "text": "EF_0895725" } ] }, "full_page": "pages/pdftotext-default/p373.txt" }, "pdftotext-layout": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 48, "text": " EF_0895725" } ] }, "full_page": "pages/pdftotext-layout/p373.txt" }, "pdfium-native": { "verdict": "body_only", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "line_candidates": [ { "line": 31, "text": "EF_0895725" } ] }, "full_page": "pages/pdfium-native/p373.txt" }, "pdfgeo-r23": { "verdict": "removed_metadata", "role_verification": "candidate locations retained; numeric labels require visual-role adjudication", "evidence": { "body_candidates": [], "removed_candidates": [ { "text": "EF_0895725", "box": [ 507.48, 65.37, 557.69, 75.16 ], "kind": "running_footer" } ] }, "full_page": "pages/pdfgeo-r23/p373.txt" } } }, { "id": "p373-ocr", "kind": "ocr_flag", "scope": "fixed_sample", "physical_page": 373, "expected_class": "sampled_text_present", "needs_OCR": false, "arms": { "pdftotext-default": { "reported_risk": "no structured warning channel", "flagged": false }, "pdftotext-layout": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfium-native": { "reported_risk": "no structured warning channel", "flagged": false }, "pdfgeo-r23": { "reported_risk": "medium", "signals": [ "image_region_without_text", "offpage_text" ], "body_glyphs": 1622, "image_area_fraction": 0.137, "flagged": true } } }, { "id": "demo202-a", "kind": "phrase", "scope": "purposive_extra", "physical_page": 202, "expected": "By only reciting generic components performing conventional functions, the claims fail to specify how any of claimed elements", "original_line_breaks": "By only reciting generic components performing conventional functions, the claims fail\nto specify how any of claimed elements", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " thereby confirming their conventional nature. Ex. 4 at 126:13-22; 136:1-138:1. By only reciting generic components performing conventional functions, the claims fail to specify how any of claimed elements, such as the processor, programmable thermostat, or HVAC system, actually achie", "start": 359, "end": 644, "normalized_page_characters": 2361, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p202.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " thereby confirming their conventional nature. Ex. 4 at 126:13-22; 136:1-138:1. By only reciting generic components performing conventional functions, the claims fail to specify how any of claimed elements, such as the processor, programmable thermostat, or HVAC system, actually achie", "start": 359, "end": 644, "normalized_page_characters": 2361, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p202.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " thereby confirming their conventional nature. Ex. 4 at 126:13-22; 136:1-138:1. By only reciting generic components performing conventional functions, the claims fail to specify how any of claimed elements, such as the processor, programmable thermostat, or HVAC system, actually achie", "start": 242, "end": 527, "normalized_page_characters": 2360, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p202.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": " thereby confirming their conventional nature. Ex. 4 at 126:13-22; 136:1-138:1. By only reciting generic components performing conventional functions, the claims fail to specify how any of claimed elements, such as the processor, programmable thermostat, or HVAC system, actually achie", "start": 239, "end": 524, "normalized_page_characters": 2228, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p202.txt" } } }, { "id": "demo202-footnote", "kind": "phrase", "scope": "purposive_extra", "physical_page": 202, "expected": "As discussed above, the ’488 and ’327 patents share a specification and have many overlapping claim elements.", "original_line_breaks": "As discussed above, the ’488 and ’327 patents share a specification and have many overlapping\nclaim elements.", "arms": { "pdftotext-default": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ce energy usage. After removing extraneous verbiage, 6 independent claim 1 of 5 As discussed above, the ’488 and ’327 patents share a specification and have many overlapping claim elements. To the extent that the claim elements are overlapping, the arguments above with", "start": 1696, "end": 1965, "normalized_page_characters": 2361, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p202.txt" }, "pdftotext-layout": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "ce energy usage. After removing extraneous verbiage, 6 independent claim 1 of 5 As discussed above, the ’488 and ’327 patents share a specification and have many overlapping claim elements. To the extent that the claim elements are overlapping, the arguments above with", "start": 1696, "end": 1965, "normalized_page_characters": 2361, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p202.txt" }, "pdfium-native": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "uce energy usage. After removing extraneous verbiage,6 independent claim 1 of 5 As discussed above, the ’488 and ’327 patents share a specification and have many overlapping claim elements. To the extent that the claim elements are overlapping, the arguments above with", "start": 1578, "end": 1847, "normalized_page_characters": 2360, "excerpt_is_complete_page": false }, "full_page": "pages/pdfium-native/p202.txt" }, "pdfgeo-r23": { "verdict": "pass", "secondary_case_punctuation_tolerant": true, "actual": { "text": "uce energy usage. After removing extraneous verbiage,6 independent claim 1 of 5 As discussed above, the ’488 and ’327 patents share a specification and have many overlapping claim elements. To the extent that the claim elements are overlapping, the arguments above with", "start": 1575, "end": 1844, "normalized_page_characters": 2228, "excerpt_is_complete_page": false }, "full_page": "pages/pdfgeo-r23/p202.txt" } } }, { "id": "demo075-a", "kind": "phrase", "scope": "purposive_extra", "physical_page": 75, "expected": "Any amount you find as of damages must be based on the value attributable to the patented invention, as distinct from unpatented features", "original_line_breaks": "Any amount you find as of damages must be based on the value attributable to the patented\ninvention, as distinct from unpatented features", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": " 75 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 38 of 41 Appx40", "start": 32, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p075.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": " 75 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 38 of 41 Appx40", "start": 32, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p075.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 38 of 41 Appx40 Case: 23-1101 Document: 15 Page: 75 Filed: 05/09/2023", "start": 0, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p075.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "", "start": 0, "end": 0, "normalized_page_characters": 0, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p075.txt" } } }, { "id": "demo075-b", "kind": "phrase", "scope": "purposive_extra", "physical_page": 75, "expected": "Apportionment can be addressed in a variety of ways, including by careful selection of the royalty base", "original_line_breaks": "Apportionment can be addressed in a variety of ways, including by careful selection of the\nroyalty base", "arms": { "pdftotext-default": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ase: 23-1101 Document: 15 Page: 75 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 38 of 41 Appx40", "start": 1, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-default/p075.txt" }, "pdftotext-layout": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "ase: 23-1101 Document: 15 Page: 75 Filed: 05/09/2023 Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 38 of 41 Appx40", "start": 1, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": false }, "full_page": "pages/pdftotext-layout/p075.txt" }, "pdfium-native": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "Case 6:20-cv-00075-ADA Document 209 Filed 02/10/22 Page 38 of 41 Appx40 Case: 23-1101 Document: 15 Page: 75 Filed: 05/09/2023", "start": 0, "end": 125, "normalized_page_characters": 125, "excerpt_is_complete_page": true }, "full_page": "pages/pdfium-native/p075.txt" }, "pdfgeo-r23": { "verdict": "fail", "secondary_case_punctuation_tolerant": false, "actual": { "text": "", "start": 0, "end": 0, "normalized_page_characters": 0, "excerpt_is_complete_page": true }, "full_page": "pages/pdfgeo-r23/p075.txt" } } } ] }