{"observation":{"id":"dd1db974-fbae-43d1-8a89-bbbd8cf1255d","tool":"extend-ai","tool_name":"Extend AI","criterion":"text-ocr-completeness","criterion_name":"Text & OCR Completeness","criterion_definition":"Extracts all readable content, including scanned pages, with accurate OCR and minimal omissions.","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"If the tool misses readable text or fails on scanned pages, it has not actually converted the PDF faithfully into Markdown. (3 of 3 judges)","scenario":"hybrid-earnings-report","scenario_name":"Hybrid Earnings Report","group_tag":"hybrid-earnings-report","scenario_description":"A long, real-world hybrid annual report used to benchmark end-to-end PDF-to-markdown conversion. It combines native text, financial tables, charts/graphics, and scanned signature/stamp regions, stressing preservation of document structure, reading order, and embedded visual content across a multi-section report.","modality":"pdf","input_text":null,"input_artifact_refs":[{"alt":null,"url":"https://cdn.futuresmart.ai/public/aidemos/f63a44b441704753b65d1b89dc9b4bbb.pdf?v=1","role":"input","filename":"Target-2015-Annual-Report.pdf"}],"stresses":["Native digital text extraction","Complex financial table preservation","Chart and graphic retention","Image-based signatures and stamps","Reading order across a long multi-section report","Markdown quality and consistency"],"verdict":"mixed","score":null,"score_total":null,"note":"Reads low-clarity signer and auditor markings, but the stamp OCR is not perfect: 'LLP' is misread as '1LP'.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://cdn.futuresmart.ai/public/aidemos/ce874b3599394bcdb0e813ae4006d734.png?v=1","role":"input","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/618070b15e1b47fe92cd7f937f0e24ae.png?v=1","role":"output","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/de8fdecc934b4671b1787129f5467b61.png?v=1","role":"input","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/a79f3336f3414649a84367b22a3fd312.png?v=1","role":"output","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/28682e5fe1544bc8be1957cb10de6cbe.png?v=1","role":"output","alt":null}],"run_id":"6e3160de-fe46-4b45-b071-72560b5c5d0e","study_title":"Convert a Complex PDF into Clean Markdown with an API","study_kind":"generation","research_task":"86b9h7t37","tested_at":null,"completeness":"input-and-output","input":{"state":"files","text":null,"files":[{"url":"https://cdn.futuresmart.ai/public/aidemos/f63a44b441704753b65d1b89dc9b4bbb.pdf?v=1","filename":"Target-2015-Annual-Report.pdf","alt":"Hybrid Earnings Report","role":"input"}],"modality":"pdf","stresses":["Native digital text extraction","Complex financial table preservation","Chart and graphic retention","Image-based signatures and stamps","Reading order across a long multi-section report","Markdown quality and consistency"]},"tool_page_slug":"extend-ai","tool_url":"https://aidemos.com/tools/extend-ai","permalink":"https://aidemos.com/evidence/dd1db974-fbae-43d1-8a89-bbbd8cf1255d","api_url":"https://ai.aidemos.com/v1/observations/dd1db974-fbae-43d1-8a89-bbbd8cf1255d"},"peers":[{"id":"f77e8735-7e24-462a-bd4c-6e29808f7156","tool":"llamaparse","tool_name":"LlamaParse","verdict":"worked","score":null,"score_total":null,"note":"Recovers a blurred signature stamp as readable text, showing OCR can salvage low-quality scanned text rather than dropping it entirely.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/6cbf1e9cd25a47e483a0144f1dcc4b61.png?v=1","evidence_url":"https://aidemos.com/evidence/f77e8735-7e24-462a-bd4c-6e29808f7156"},{"id":"4171c2f8-81c8-472e-abf5-a809333282b6","tool":"reducto","tool_name":"Reducto","verdict":"worked","score":null,"score_total":null,"note":"Converts the full 84-page native-digital annual report with no skipped pages; the output contains all 84 page-marker pairs, and checked high-risk numbers survive exactly, including the $51,550,988,273 market-value figure and 599,982,121 shares outstanding.","artifact_count":7,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-reducto-input1-hybridearnings-output-2e5bed5d1e5a.md","evidence_url":"https://aidemos.com/evidence/4171c2f8-81c8-472e-abf5-a809333282b6"},{"id":"b3b06de4-1c1f-451a-a26e-d1bb11daed26","tool":"tensorlake","tool_name":"Tensorlake","verdict":"mixed","score":null,"score_total":null,"note":"On a blurry Ernst & Young signoff, the OCR preserves the firm reference but makes a symbol-level mistake by rendering the ampersand as '+', so the text is close but not exact.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/6cbf1e9cd25a47e483a0144f1dcc4b61.png?v=1","evidence_url":"https://aidemos.com/evidence/b3b06de4-1c1f-451a-a26e-d1bb11daed26"}],"other_criteria":[{"id":"6cfee092-61f2-4247-aaff-49291fa4a600","criterion":"complex-document-handling","criterion_name":"Complex Document Handling","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Processes an 84-page hybrid annual report end-to-end across native text, tables, charts, and scan-only signature regions without manual cleanup.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/6cfee092-61f2-4247-aaff-49291fa4a600"},{"id":"b69aa8f8-8162-47d0-9487-6b903f8ffe84","criterion":"reading-order-structure","criterion_name":"Reading Order & Structure","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Maintains report hierarchy and reading flow in an 84-page annual report, keeping section text, bullets, and business narrative aligned instead of flattening them.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/b69aa8f8-8162-47d0-9487-6b903f8ffe84"},{"id":"f09929e3-569b-4cc1-8a0e-f0dff9b4279c","criterion":"table-preservation","criterion_name":"Table Preservation","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Preserves a 5-year financial summary table with row labels and year columns aligned, keeping the annual financial grid intact in markdown.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/f09929e3-569b-4cc1-8a0e-f0dff9b4279c"},{"id":"3c7b525c-4c85-4bab-9ff6-9033a037e77c","criterion":"visual-content-retention","criterion_name":"Visual Content Retention","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"Retains charts and logos as standalone figure blocks with captions, but they are extracted out of page position rather than embedded inline.","artifact_count":5,"evidence_url":"https://aidemos.com/evidence/3c7b525c-4c85-4bab-9ff6-9033a037e77c"}],"appears_in":[{"page_type":"ranking","slug":"pdf-to-markdown-apis","title":"Best AI Tools to Convert Complex PDFs into Clean Markdown with an API","url":"https://aidemos.com/best/pdf-to-markdown-apis","binding":"run"}],"same_scenario":[{"id":"f77e8735-7e24-462a-bd4c-6e29808f7156","tool":"llamaparse","tool_name":"LlamaParse","verdict":"worked","score":null,"score_total":null,"note":"Recovers a blurred signature stamp as readable text, showing OCR can salvage low-quality scanned text rather than dropping it entirely."},{"id":"4171c2f8-81c8-472e-abf5-a809333282b6","tool":"reducto","tool_name":"Reducto","verdict":"worked","score":null,"score_total":null,"note":"Converts the full 84-page native-digital annual report with no skipped pages; the output contains all 84 page-marker pairs, and checked high-risk numbers survive exactly, including the $51,550,988,273 market-value figure and 599,982,121 shares outstanding."},{"id":"b3b06de4-1c1f-451a-a26e-d1bb11daed26","tool":"tensorlake","tool_name":"Tensorlake","verdict":"mixed","score":null,"score_total":null,"note":"On a blurry Ernst & Young signoff, the OCR preserves the firm reference but makes a symbol-level mistake by rendering the ampersand as '+', so the text is close but not exact."}]}