{"observation":{"id":"184fde87-39d4-4fe1-928e-d94082d4127f","tool":"landing-ai","tool_name":"Landing AI","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":"mixed","score":null,"score_total":null,"note":"Leaves several station-level fields null even though the station is identified, with call_letters \"KMSP\" populated but address, city, state, postal_code, main_phone, and billing_phone all null.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/research-media-landing-ai-invoice-station-af0b8d56c310.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":"landing-ai","tool_url":"https://aidemos.com/tools/landing-ai","permalink":"https://aidemos.com/evidence/184fde87-39d4-4fe1-928e-d94082d4127f","api_url":"https://ai.aidemos.com/v1/observations/184fde87-39d4-4fe1-928e-d94082d4127f"},"peers":[{"id":"76f5a5f0-1389-4341-a623-595405cf206b","tool":"datalab","tool_name":"Datalab","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.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-datalab-invoice-metadat-1c39e0c1c45e.png","evidence_url":"https://aidemos.com/evidence/76f5a5f0-1389-4341-a623-595405cf206b"},{"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":"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":"e21e3065-67a9-44b0-a7d5-4534cc545780","criterion":"schema-adherence","criterion_name":"Schema Adherence","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Reconstructs the requested invoice hierarchy in structured JSON, filling invoice_metadata, advertiser, station, line_items, and summary objects instead of returning a flat extraction.","artifact_count":4,"evidence_url":"https://aidemos.com/evidence/e21e3065-67a9-44b0-a7d5-4534cc545780"},{"id":"16a432ba-f975-4195-9525-e97b93220074","criterion":"semantic-field-enrichment","criterion_name":"Semantic Field Enrichment","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Populates derived line-item fields such as day_of_week \"M\", days_pattern \"MTWT\", time_slot \"430a-5a\", and ad_id \"NRCCW1071005\" on line item 1.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/16a432ba-f975-4195-9525-e97b93220074"},{"id":"4e54005c-915d-492b-8121-ad1d06573a45","criterion":"table-and-record-completeness","criterion_name":"Table & Record Completeness","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Extracts all 8 advertising line items as separate records, preserving the row count and scheduling structure instead of collapsing the table.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/4e54005c-915d-492b-8121-ad1d06573a45"}],"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":"76f5a5f0-1389-4341-a623-595405cf206b","tool":"datalab","tool_name":"Datalab","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."},{"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":"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."}]}