{"observation":{"id":"b78d37af-33a7-4f25-91f5-6a7c39e2f334","tool":"retab","tool_name":"Retab","criterion":"structural-clean-output","criterion_name":"Structural Clean Output","criterion_definition":"Is the JSON directly consumable by a downstream AI pipeline or system without requiring a structural transformation layer?","criterion_evidence_type":"transformation","criterion_rank_role":"context","criterion_rank_role_reason":"Directly consumable JSON is valuable for workflow convenience, but it is a delivery/integration concern rather than the core measure of extraction quality itself. (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":"Does not preserve the schema-defined property order, so consumers that rely on key order need an extra formatting pass.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/research-media-invoice-schema-order-85baff3c493d.png","role":"input","alt":null},{"url":"https://d3epheqghktydj.cloudfront.net/research-media-retab-invoice-schema-order-4df9e06bef88.png","role":"input","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":"input-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":"retab","tool_url":"https://aidemos.com/tools/retab","permalink":"https://aidemos.com/evidence/b78d37af-33a7-4f25-91f5-6a7c39e2f334","api_url":"https://ai.aidemos.com/v1/observations/b78d37af-33a7-4f25-91f5-6a7c39e2f334"},"peers":[{"id":"df4d4c76-2422-413b-9d07-a3489b53cb50","tool":"datalab","tool_name":"Datalab","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,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-invoice-schema-order-1938d10e3382.png","evidence_url":"https://aidemos.com/evidence/df4d4c76-2422-413b-9d07-a3489b53cb50"},{"id":"be4e0664-3a37-4913-a8df-3cd6f8915087","tool":"extend-ai","tool_name":"Extend AI","verdict":"failed","score":null,"score_total":null,"note":"It reorders several schema sections relative to the supplied schema, so the output is not consistently in the authored field order.","artifact_count":3,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/9e7bb7c55fbf41d8bf08b8139a192ae4.png?v=1","evidence_url":"https://aidemos.com/evidence/be4e0664-3a37-4913-a8df-3cd6f8915087"}],"other_criteria":[{"id":"a764ebf7-c927-4d60-92f5-68838d5361f4","criterion":"extraction-accuracy","criterion_name":"Extraction Accuracy","rank_role":"decisive","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,"evidence_url":"https://aidemos.com/evidence/a764ebf7-c927-4d60-92f5-68838d5361f4"},{"id":"545de688-ed6b-41cf-aa4b-3f3edbf02217","criterion":"extraction-accuracy","criterion_name":"Extraction Accuracy","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Extracts key invoice metadata values as typed fields, including invoice_number 4064621-1, invoice_date 2012-10-28, estimate_number 2968, and order_number 4064621.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/545de688-ed6b-41cf-aa4b-3f3edbf02217"},{"id":"9e5c5bc7-673d-467a-90cc-75c7c06dea40","criterion":"extraction-accuracy","criterion_name":"Extraction Accuracy","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Carries the financial summary through consistently, including agency_commission 4462.5, aired_spots 8, gross_total 29750, and net_amount_due 25287.5.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/9e5c5bc7-673d-467a-90cc-75c7c06dea40"},{"id":"38fc2de5-4406-486b-9a50-fa39c4b5e88a","criterion":"schema-adherence","criterion_name":"Schema Adherence","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Builds the requested invoice hierarchy with separate invoice_metadata, advertiser, station, account_details, billing_address, remit_address, flight_dates, line_items, and summary objects instead of a flat OCR dump.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/38fc2de5-4406-486b-9a50-fa39c4b5e88a"},{"id":"0768d86c-2233-428d-9d43-a4c32b86f2c2","criterion":"semantic-field-enrichment","criterion_name":"Semantic Field Enrichment","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Derives scheduling fields beyond raw OCR, including day_of_week Su and days_pattern ------S for a line item, along with air_time, time_slot, and ad_id.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/0768d86c-2233-428d-9d43-a4c32b86f2c2"},{"id":"351eae64-d136-45cf-bf96-05708a002c49","criterion":"table-and-record-completeness","criterion_name":"Table & Record Completeness","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Reconstructs all 8 advertising line items as separate records without duplication or omission.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/351eae64-d136-45cf-bf96-05708a002c49"}],"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":"df4d4c76-2422-413b-9d07-a3489b53cb50","tool":"datalab","tool_name":"Datalab","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."},{"id":"be4e0664-3a37-4913-a8df-3cd6f8915087","tool":"extend-ai","tool_name":"Extend AI","verdict":"failed","score":null,"score_total":null,"note":"It reorders several schema sections relative to the supplied schema, so the output is not consistently in the authored field order."}]}