{"observation":{"id":"7840c24e-489b-4551-b576-148911ebe640","tool":"reducto","tool_name":"Reducto","criterion":"reading-order-structure","criterion_name":"Reading Order & Structure","criterion_definition":"Maintains headings, sections, column order, document hierarchy, and overall flow.","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"Clean Markdown requires the original reading order, headings, sections, and hierarchy to be maintained correctly. (3 of 3 judges)","scenario":"scanned-research-paper","scenario_name":"Scanned Research Paper","group_tag":"scanned-research-paper","scenario_description":"An image-only scanned research paper used to stress OCR and layout recovery in a multi-column academic document with figures, charts, tables, captions, and references.","modality":"pdf","input_text":null,"input_artifact_refs":[{"alt":null,"url":"https://d3epheqghktydj.cloudfront.net/convert-a-complex-pdf-into-clean-markdow-scanned-research-pdf-7b86de49784d.pdf","role":"input","filename":"Scanned Research PDF.pdf"}],"stresses":["OCR on scanned pages","Multi-column reading order","Figure and chart handling","Table reconstruction from scans","Caption association","Reference extraction","Overall document structure retention"],"verdict":"struggled","score":null,"score_total":null,"note":"Displaces the byline by a full column: the author line that sits above the two-column split in the source is emitted only after the entire left column, and its footnote markers are rendered inconsistently.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://cdn.futuresmart.ai/public/aidemos/2979812e747e44b2b8b333d7b12c3618.png?v=1","role":"input","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/bee1a31be43641ddb0edac66e8fb4645.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://d3epheqghktydj.cloudfront.net/convert-a-complex-pdf-into-clean-markdow-scanned-research-pdf-7b86de49784d.pdf","filename":"Scanned Research PDF.pdf","alt":"Scanned Research Paper","role":"input"}],"modality":"pdf","stresses":["OCR on scanned pages","Multi-column reading order","Figure and chart handling","Table reconstruction from scans","Caption association","Reference extraction","Overall document structure retention"]},"tool_page_slug":"reducto","tool_url":"https://aidemos.com/tools/reducto","permalink":"https://aidemos.com/evidence/7840c24e-489b-4551-b576-148911ebe640","api_url":"https://ai.aidemos.com/v1/observations/7840c24e-489b-4551-b576-148911ebe640"},"peers":[{"id":"24968ab8-597c-4c69-9ec3-a0c216320ebc","tool":"adobe-api","tool_name":"Adobe API","verdict":"failed","score":null,"score_total":null,"note":"Dumps the scanned title page as a dense OCR block without section boundaries or other structural cues, so the document hierarchy is lost.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/28052bbc164e4f51be6903dcaccdb477.png?v=1","evidence_url":"https://aidemos.com/evidence/24968ab8-597c-4c69-9ec3-a0c216320ebc"},{"id":"4556b641-0861-4cec-9988-0748cdfa1664","tool":"extend-ai","tool_name":"Extend AI","verdict":"worked","score":null,"score_total":null,"note":"Reconstructs a multi-column research page so the 'STUDY AREA' heading, its paragraphs, and the following 'STAND PRESCRIPTIONS' section stay in order.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/18b2277b09fa42e3ae7a325fba02b272.png?v=1","evidence_url":"https://aidemos.com/evidence/4556b641-0861-4cec-9988-0748cdfa1664"},{"id":"4d96cef6-8e58-4798-b86c-1b626c8d3ae2","tool":"landing-ai","tool_name":"Landing AI","verdict":"worked","score":null,"score_total":null,"note":"Reconstructs a dense two-column section with its hierarchy intact, keeping the section heading attached to the correct body text across the columns.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/18b2277b09fa42e3ae7a325fba02b272.png?v=1","evidence_url":"https://aidemos.com/evidence/4d96cef6-8e58-4798-b86c-1b626c8d3ae2"},{"id":"fae001a3-d13a-4fa3-8415-862dfb85dca9","tool":"llamaparse","tool_name":"LlamaParse","verdict":"worked","score":null,"score_total":null,"note":"Reflows a two-column scanned page into a single coherent reading order while preserving section-to-body flow.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/bb646d6406274eb280aa628c32bfa474.png?v=1","evidence_url":"https://aidemos.com/evidence/fae001a3-d13a-4fa3-8415-862dfb85dca9"},{"id":"cc8096bb-19af-4b8f-901f-657634e78a25","tool":"mistral-ai","tool_name":"Mistral AI","verdict":"failed","score":null,"score_total":null,"note":"The opening page loses the distinction between the document title and the abstract, flattening the semantic organization of the first page.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/dd8e2c3021024a24be3970549c24ccc7.png?v=1","evidence_url":"https://aidemos.com/evidence/cc8096bb-19af-4b8f-901f-657634e78a25"},{"id":"269c8673-40ed-4da2-a18e-2a17a92616e3","tool":"nutrient-io","tool_name":"Nutrient.io","verdict":"failed","score":null,"score_total":null,"note":"Misorders the first page so the abstract is placed before the title, showing a layout-reading-order inversion on the scanned article.","artifact_count":3,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/94e13a264c0c464fba32bd78b5bb4b27.png?v=1","evidence_url":"https://aidemos.com/evidence/269c8673-40ed-4da2-a18e-2a17a92616e3"},{"id":"fc3553de-a932-4313-bb83-66645ce7441c","tool":"tensorlake","tool_name":"Tensorlake","verdict":"worked","score":null,"score_total":null,"note":"Retains section-level reading order in a scanned multi-column paper, with headings continuing to guide the flow across columns and into the next section.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/18b2277b09fa42e3ae7a325fba02b272.png?v=1","evidence_url":"https://aidemos.com/evidence/fc3553de-a932-4313-bb83-66645ce7441c"},{"id":"86f4991b-db92-402b-bd03-7a1f3777691e","tool":"upstage-ai","tool_name":"Upstage AI","verdict":"failed","score":null,"score_total":null,"note":"Breaks paragraph-level segmentation in the scanned two-column page, so the extracted text no longer follows the source column order cleanly.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/18b2277b09fa42e3ae7a325fba02b272.png?v=1","evidence_url":"https://aidemos.com/evidence/86f4991b-db92-402b-bd03-7a1f3777691e"}],"other_criteria":[{"id":"73354714-3c90-4a35-a5c6-c27f03292e80","criterion":"advanced-features","criterion_name":"Advanced Features","rank_role":"context","verdict":"worked","score":null,"score_total":null,"note":"Schema-driven extract.run fully recovers the corrupted Table 4 rows, returning all 12 checked rows exactly, including the 10-inch-cut 1979 MPB row whose parse.run output was badly garbled.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/73354714-3c90-4a35-a5c6-c27f03292e80"},{"id":"6e5c93ad-2b5d-4c86-89f8-0503d11424d6","criterion":"advanced-features","criterion_name":"Advanced Features","rank_role":"context","verdict":"mixed","score":null,"score_total":null,"note":"The confidence signal flags the faint handwritten margin note and the garbled Table 4 as low confidence, but it misses the hallucinated 'USA' word in the title, which is still rated 0.9354 confident.","artifact_count":4,"evidence_url":"https://aidemos.com/evidence/6e5c93ad-2b5d-4c86-89f8-0503d11424d6"},{"id":"3bec7ed4-9b8e-44f3-b548-b76f0215b34c","criterion":"complex-document-handling","criterion_name":"Complex Document Handling","rank_role":"decisive","verdict":"struggled","score":null,"score_total":null,"note":"Handles the 12-page scan in 10.6 seconds with no truncation, but the densest 17-column table has unreadable stretches with injected glyphs and run-on numbers.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/3bec7ed4-9b8e-44f3-b548-b76f0215b34c"},{"id":"39ecbd6f-1599-4ba1-ae17-16b29b9c07cb","criterion":"markdown-quality","criterion_name":"Markdown Quality","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Uses no invented tags or malformed markdown; the only HTML seen is legitimate <br /> inside table cells, so the syntax stays clean even though the document does not surface real heading markup.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/39ecbd6f-1599-4ba1-ae17-16b29b9c07cb"},{"id":"671f1c02-54bd-415d-8592-f65b9923c375","criterion":"table-preservation","criterion_name":"Table Preservation","rank_role":"decisive","verdict":"failed","score":null,"score_total":null,"note":"Catastrophically corrupts the dense 17-column Table 4, injecting non-Latin glyphs into numeric cells and producing run-on strings such as 238-563NT, 2231, and 8998 6 in the 10-inch and 12-inch blocks.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/671f1c02-54bd-415d-8592-f65b9923c375"},{"id":"fcad1a88-bccf-4eea-8bf5-0d8e5dbc22ee","criterion":"table-preservation","criterion_name":"Table Preservation","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"Partially reconstructs Table 1: most of the roughly 90 numeric values are exact, but literal 0 values in the 12-inch column become blanks, one mean cell picks up stray digits (33.0 830000), and a row-label-only section header is broadcast across all six columns in one instance.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/fcad1a88-bccf-4eea-8bf5-0d8e5dbc22ee"},{"id":"b0876a41-66cd-455c-b38c-421968bf4e16","criterion":"text-ocr-completeness","criterion_name":"Text & OCR Completeness","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Converts all 12 scanned pages with no gaps; the page-11-to-page-12 handoff is preserved verbatim, and a separate page-marker output shows pages 1 through 12 present with no missing markers.","artifact_count":4,"evidence_url":"https://aidemos.com/evidence/b0876a41-66cd-455c-b38c-421968bf4e16"},{"id":"ab812bbc-7ab3-4b0c-82e1-e142cb5375fe","criterion":"visual-content-retention","criterion_name":"Visual Content Retention","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Segments a shield logo out of a single full-page raster scan and also retains Figure 1 as an image with an accurate synthesized caption; the returned logo crop is a tight 77x81px cut with legible shield text.","artifact_count":5,"evidence_url":"https://aidemos.com/evidence/ab812bbc-7ab3-4b0c-82e1-e142cb5375fe"}],"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":"24968ab8-597c-4c69-9ec3-a0c216320ebc","tool":"adobe-api","tool_name":"Adobe API","verdict":"failed","score":null,"score_total":null,"note":"Dumps the scanned title page as a dense OCR block without section boundaries or other structural cues, so the document hierarchy is lost."},{"id":"4556b641-0861-4cec-9988-0748cdfa1664","tool":"extend-ai","tool_name":"Extend AI","verdict":"worked","score":null,"score_total":null,"note":"Reconstructs a multi-column research page so the 'STUDY AREA' heading, its paragraphs, and the following 'STAND PRESCRIPTIONS' section stay in order."},{"id":"4d96cef6-8e58-4798-b86c-1b626c8d3ae2","tool":"landing-ai","tool_name":"Landing AI","verdict":"worked","score":null,"score_total":null,"note":"Reconstructs a dense two-column section with its hierarchy intact, keeping the section heading attached to the correct body text across the columns."},{"id":"fae001a3-d13a-4fa3-8415-862dfb85dca9","tool":"llamaparse","tool_name":"LlamaParse","verdict":"worked","score":null,"score_total":null,"note":"Reflows a two-column scanned page into a single coherent reading order while preserving section-to-body flow."},{"id":"cc8096bb-19af-4b8f-901f-657634e78a25","tool":"mistral-ai","tool_name":"Mistral AI","verdict":"failed","score":null,"score_total":null,"note":"The opening page loses the distinction between the document title and the abstract, flattening the semantic organization of the first page."},{"id":"269c8673-40ed-4da2-a18e-2a17a92616e3","tool":"nutrient-io","tool_name":"Nutrient.io","verdict":"failed","score":null,"score_total":null,"note":"Misorders the first page so the abstract is placed before the title, showing a layout-reading-order inversion on the scanned article."},{"id":"fc3553de-a932-4313-bb83-66645ce7441c","tool":"tensorlake","tool_name":"Tensorlake","verdict":"worked","score":null,"score_total":null,"note":"Retains section-level reading order in a scanned multi-column paper, with headings continuing to guide the flow across columns and into the next section."},{"id":"86f4991b-db92-402b-bd03-7a1f3777691e","tool":"upstage-ai","tool_name":"Upstage AI","verdict":"failed","score":null,"score_total":null,"note":"Breaks paragraph-level segmentation in the scanned two-column page, so the extracted text no longer follows the source column order cleanly."}]}