{"observation":{"id":"76f5a5f0-1389-4341-a623-595405cf206b","tool":"datalab","tool_name":"Datalab","criterion":"extraction-accuracy","criterion_name":"Extraction Accuracy","criterion_definition":"Are field values correct, complete, and free of OCR or parsing errors? Includes numerical precision on financial fields.","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"The whole point is to pull the right values from documents; wrong or incomplete field values mean the tool failed at the job. (3 of 3 judges)","scenario":"invoice-pdf","scenario_name":"Invoice PDF","group_tag":"financial-document-extraction","scenario_description":"A 2-page broadcast advertising invoice PDF with 8 line items, complex time/day fields, large dollar amounts, and compliance text, used to test hierarchical line-item extraction and financial validation.","modality":"pdf","input_text":null,"input_artifact_refs":[{"alt":null,"url":null,"role":null,"filename":"Invoice PDF.pdf"}],"stresses":["Nested line-item hierarchy extraction","Multi-page line-item continuity across a page break","Large dollar amount precision and total validation","Parsing time slots, day patterns, and air dates","Extraction of alphanumeric ad IDs and reference codes","Structured metadata mapping for advertiser, station, billing, and remit sections","Political advertising and FCC compliance text recognition"],"verdict":"worked","score":null,"score_total":null,"note":"Extracts the invoice metadata and monetary values accurately, including invoice 4064621-1, invoice date 10/28/12, gross_total 29750, agency_commission 4462.5, net_amount_due 25287.5, and payment_terms 30 Days.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/research-media-datalab-invoice-metadat-1c39e0c1c45e.png","role":"output","alt":null},{"url":"https://d3epheqghktydj.cloudfront.net/research-media-datalab-invoice-summary-485f182a6662.png","role":"output","alt":null}],"run_id":"ec4d736d-95f9-4c88-884c-e280435f7b7b","study_title":"Extract and query structured data from documents using natural language","study_kind":"generation","research_task":"86b9y25e5","tested_at":null,"completeness":"output-only","input":{"state":"not-captured","text":null,"files":[],"modality":"pdf","stresses":["Nested line-item hierarchy extraction","Multi-page line-item continuity across a page break","Large dollar amount precision and total validation","Parsing time slots, day patterns, and air dates","Extraction of alphanumeric ad IDs and reference codes","Structured metadata mapping for advertiser, station, billing, and remit sections","Political advertising and FCC compliance text recognition"]},"tool_page_slug":"datalab","tool_url":"https://aidemos.com/tools/datalab","permalink":"https://aidemos.com/evidence/76f5a5f0-1389-4341-a623-595405cf206b","api_url":"https://ai.aidemos.com/v1/observations/76f5a5f0-1389-4341-a623-595405cf206b"},"peers":[{"id":"21668a8b-96b6-4a98-ab20-6b71dc0db783","tool":"extend-ai","tool_name":"Extend AI","verdict":"worked","score":null,"score_total":null,"note":"Its invoice totals match the source document, including 8 aired spots, gross_total 29750, agency_commission 4462.5, and net_amount_due 25287.5.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-extend-ai-invoice-summary-2e03dc36fa48.png","evidence_url":"https://aidemos.com/evidence/21668a8b-96b6-4a98-ab20-6b71dc0db783"},{"id":"19860e8d-14dd-466c-b257-a1945282f00a","tool":"landing-ai","tool_name":"Landing AI","verdict":"worked","score":null,"score_total":null,"note":"Gets the invoice totals and metadata numerically right, including aired_spots 8, gross_total 29750, agency_commission 4462.5, net_amount_due 25287.5, and payment_terms \"30 Days\".","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-landing-ai-invoice-summary-eb031f81c889.png","evidence_url":"https://aidemos.com/evidence/19860e8d-14dd-466c-b257-a1945282f00a"},{"id":"60b3eaf0-635a-4363-9547-53cae8bcb695","tool":"llamaparse","tool_name":"LlamaParse","verdict":"worked","score":null,"score_total":null,"note":"Matches the source invoice totals and payment terms: aired_spots 8, gross_total 29750, agency_commission 4462.5, net_amount_due 25287.5, and payment_terms \"30 Days\".","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-llamaparse-invoice-summary-9c05de684d8a.png","evidence_url":"https://aidemos.com/evidence/60b3eaf0-635a-4363-9547-53cae8bcb695"},{"id":"47a6fef2-07cd-4dea-97ff-47ef7be54f95","tool":"nanonets","tool_name":"Nanonets","verdict":"mixed","score":null,"score_total":null,"note":"It concatenates program-description text without a separator, so labels such as \"Political Issue Rates\" are appended directly onto the show title in fields like \"Fox 9 AM News at 4:30amPolitical Issue Rates\".","artifact_count":3,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-invoice-program-description-47fa10018717.png","evidence_url":"https://aidemos.com/evidence/47a6fef2-07cd-4dea-97ff-47ef7be54f95"},{"id":"d0f6a303-e33e-4c5f-a8e1-94a8bfbe403a","tool":"reducto","tool_name":"Reducto","verdict":"worked","score":null,"score_total":null,"note":"Extracts the invoice summary amounts accurately; the report says the financial totals and aired_spots match the source document.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-reducto-invoice-summary-915cda528c4b.png","evidence_url":"https://aidemos.com/evidence/d0f6a303-e33e-4c5f-a8e1-94a8bfbe403a"},{"id":"a764ebf7-c927-4d60-92f5-68838d5361f4","tool":"retab","tool_name":"Retab","verdict":"mixed","score":null,"score_total":null,"note":"Retains the source label in payment_terms, returning Payment Terms 30 Days instead of only the requested value, so a cleanup step is needed.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/03e9858033fe4660abc1ffeb342a2d78.png?v=1","evidence_url":"https://aidemos.com/evidence/a764ebf7-c927-4d60-92f5-68838d5361f4"},{"id":"668dd494-5404-4e0d-b091-134c04dde238","tool":"unstract","tool_name":"Unstract","verdict":"struggled","score":null,"score_total":null,"note":"Introduces a stray OCR-style space into every Ad-ID, so the identifier text is not preserved exactly as printed.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/unstract-unstract-invoice-output-e53f3477db06.json","evidence_url":"https://aidemos.com/evidence/668dd494-5404-4e0d-b091-134c04dde238"}],"other_criteria":[{"id":"c01474f8-d601-4535-b19c-9ab5759d7f35","criterion":"schema-adherence","criterion_name":"Schema Adherence","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Reconstructs the invoice into nested JSON objects and arrays that follow the supplied schema, including invoice_metadata and line_items rather than returning generic OCR text.","artifact_count":5,"evidence_url":"https://aidemos.com/evidence/c01474f8-d601-4535-b19c-9ab5759d7f35"},{"id":"f376333b-6c46-4298-91ee-eddd286afd5d","criterion":"semantic-field-enrichment","criterion_name":"Semantic Field Enrichment","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Correctly extracts derived scheduling fields on line 2, including day_of_week Su, time_slot 9a-10a, air_time 9:38 AM, and ad_id NRCCWI071005.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/f376333b-6c46-4298-91ee-eddd286afd5d"},{"id":"df4d4c76-2422-413b-9d07-a3489b53cb50","criterion":"structural-clean-output","criterion_name":"Structural Clean Output","rank_role":"context","verdict":"mixed","score":null,"score_total":null,"note":"The generated JSON is structurally valid but not order-stable: line_items appears before other top-level sections that were defined earlier in the supplied schema.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/df4d4c76-2422-413b-9d07-a3489b53cb50"},{"id":"a2dfbd36-ebfc-4d14-ab59-0d615bee1ed4","criterion":"table-and-record-completeness","criterion_name":"Table & Record Completeness","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Keeps all 8 advertising spots as separate line-item records, with the JSON tree showing indices 0 through 7 and no adjacent-row merging.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/a2dfbd36-ebfc-4d14-ab59-0d615bee1ed4"}],"appears_in":[{"page_type":"ranking","slug":"document-extraction","title":"Best AI Tools for Extracting Structured Data from PDFs and Business Documents","url":"https://aidemos.com/best/document-extraction","binding":"run"},{"page_type":"tool","slug":"unstract","title":null,"url":"https://aidemos.com/tools/unstract","binding":"run"}],"same_scenario":[{"id":"21668a8b-96b6-4a98-ab20-6b71dc0db783","tool":"extend-ai","tool_name":"Extend AI","verdict":"worked","score":null,"score_total":null,"note":"Its invoice totals match the source document, including 8 aired spots, gross_total 29750, agency_commission 4462.5, and net_amount_due 25287.5."},{"id":"19860e8d-14dd-466c-b257-a1945282f00a","tool":"landing-ai","tool_name":"Landing AI","verdict":"worked","score":null,"score_total":null,"note":"Gets the invoice totals and metadata numerically right, including aired_spots 8, gross_total 29750, agency_commission 4462.5, net_amount_due 25287.5, and payment_terms \"30 Days\"."},{"id":"60b3eaf0-635a-4363-9547-53cae8bcb695","tool":"llamaparse","tool_name":"LlamaParse","verdict":"worked","score":null,"score_total":null,"note":"Matches the source invoice totals and payment terms: aired_spots 8, gross_total 29750, agency_commission 4462.5, net_amount_due 25287.5, and payment_terms \"30 Days\"."},{"id":"47a6fef2-07cd-4dea-97ff-47ef7be54f95","tool":"nanonets","tool_name":"Nanonets","verdict":"mixed","score":null,"score_total":null,"note":"It concatenates program-description text without a separator, so labels such as \"Political Issue Rates\" are appended directly onto the show title in fields like \"Fox 9 AM News at 4:30amPolitical Issue Rates\"."},{"id":"d0f6a303-e33e-4c5f-a8e1-94a8bfbe403a","tool":"reducto","tool_name":"Reducto","verdict":"worked","score":null,"score_total":null,"note":"Extracts the invoice summary amounts accurately; the report says the financial totals and aired_spots match the source document."},{"id":"a764ebf7-c927-4d60-92f5-68838d5361f4","tool":"retab","tool_name":"Retab","verdict":"mixed","score":null,"score_total":null,"note":"Retains the source label in payment_terms, returning Payment Terms 30 Days instead of only the requested value, so a cleanup step is needed."},{"id":"668dd494-5404-4e0d-b091-134c04dde238","tool":"unstract","tool_name":"Unstract","verdict":"struggled","score":null,"score_total":null,"note":"Introduces a stray OCR-style space into every Ad-ID, so the identifier text is not preserved exactly as printed."}]}