{"observation":{"id":"e8595df9-eff1-4a6e-8be3-bd38b9254082","tool":"llamaparse","tool_name":"LlamaParse","criterion":"semantic-field-enrichment","criterion_name":"Semantic Field Enrichment","criterion_definition":"Are derived fields — transaction_type, transaction_id, cheque_number, day patterns, ad codes — correctly classified or extracted beyond raw OCR?","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"This ranking is not just about copying OCR text; it also depends on whether the tool can correctly infer or classify document-specific fields needed for useful structured output. (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":"Correctly derives scheduling metadata in line items, including day_of_week, time_slot, flight_period_start/end, frequency, and days_pattern such as \"---T---\".","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/research-media-llamaparse-invoice-extracted-line-item-2-f4ecd3c8fd80.png","role":"output","alt":null},{"url":"https://d3epheqghktydj.cloudfront.net/research-media-llamaparse-invoice-extracted-line-item-8-ddd5553310ea.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":"llamaparse","tool_url":"https://aidemos.com/tools/llamaparse","permalink":"https://aidemos.com/evidence/e8595df9-eff1-4a6e-8be3-bd38b9254082","api_url":"https://ai.aidemos.com/v1/observations/e8595df9-eff1-4a6e-8be3-bd38b9254082"},"peers":[{"id":"f376333b-6c46-4298-91ee-eddd286afd5d","tool":"datalab","tool_name":"Datalab","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,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-datalab-invoice-line-item-2-ab8a8332ed35.png","evidence_url":"https://aidemos.com/evidence/f376333b-6c46-4298-91ee-eddd286afd5d"},{"id":"b387cbf1-3dca-4b92-9a44-768b8a7f0926","tool":"extend-ai","tool_name":"Extend AI","verdict":"worked","score":null,"score_total":null,"note":"It derives non-OCR line-item fields such as `day_of_week`, `days_pattern`, `time_slot`, and `air_time`.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-extend-ai-invoice-line-item-6-6c1cfecca1da.png","evidence_url":"https://aidemos.com/evidence/b387cbf1-3dca-4b92-9a44-768b8a7f0926"},{"id":"16a432ba-f975-4195-9525-e97b93220074","tool":"landing-ai","tool_name":"Landing AI","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,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-landing-ai-extracted-line-item-1-6f5a3b324a8b.png","evidence_url":"https://aidemos.com/evidence/16a432ba-f975-4195-9525-e97b93220074"},{"id":"c3d6a0fb-4f54-4ee8-9e7a-c8382539a82e","tool":"nanonets","tool_name":"Nanonets","verdict":"mixed","score":null,"score_total":null,"note":"It leaves line 8 without derived scheduling fields such as flight_period_start, flight_period_end, frequency, and days_pattern, even though comparable rows populate them.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-invoice-line-item-8-ae95b671f1c5.png","evidence_url":"https://aidemos.com/evidence/c3d6a0fb-4f54-4ee8-9e7a-c8382539a82e"},{"id":"9499ff43-0583-4050-bfe1-951e5a7fb8af","tool":"reducto","tool_name":"Reducto","verdict":"worked","score":null,"score_total":null,"note":"Surfaces derived line-item metadata as structured fields, including frequency = 1x with citation support.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/095fac7ce60b4f339aefe2ccaed96912.png?v=1","evidence_url":"https://aidemos.com/evidence/9499ff43-0583-4050-bfe1-951e5a7fb8af"},{"id":"0768d86c-2233-428d-9d43-a4c32b86f2c2","tool":"retab","tool_name":"Retab","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,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-retab-invoice-extracted-line-item-ff712d23f334.png","evidence_url":"https://aidemos.com/evidence/0768d86c-2233-428d-9d43-a4c32b86f2c2"},{"id":"4aecc9a8-5ccf-4aa9-af98-482f367c634d","tool":"unstract","tool_name":"Unstract","verdict":"worked","score":null,"score_total":null,"note":"Extracts the compact days_pattern field correctly as the actual single broadcast-day letter.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/f76d402f677748dfa30611569dbbc5f2.pdf?v=1","evidence_url":"https://aidemos.com/evidence/4aecc9a8-5ccf-4aa9-af98-482f367c634d"}],"other_criteria":[{"id":"60b3eaf0-635a-4363-9547-53cae8bcb695","criterion":"extraction-accuracy","criterion_name":"Extraction Accuracy","rank_role":"decisive","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,"evidence_url":"https://aidemos.com/evidence/60b3eaf0-635a-4363-9547-53cae8bcb695"},{"id":"0b3ba3e3-dd88-4377-97f7-2da41c08c915","criterion":"schema-adherence","criterion_name":"Schema Adherence","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Keeps the invoice hierarchy intact, emitting invoice_metadata, advertiser, station, line_items, and summary objects rather than flat OCR text.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/0b3ba3e3-dd88-4377-97f7-2da41c08c915"},{"id":"b9247b59-eb1e-4af9-be1b-8c3a5de68f1c","criterion":"table-and-record-completeness","criterion_name":"Table & Record Completeness","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Extracts the invoice line_items table as 8 separate records (indices 0 through 7) without merging adjacent rows.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/b9247b59-eb1e-4af9-be1b-8c3a5de68f1c"}],"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":"f376333b-6c46-4298-91ee-eddd286afd5d","tool":"datalab","tool_name":"Datalab","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."},{"id":"b387cbf1-3dca-4b92-9a44-768b8a7f0926","tool":"extend-ai","tool_name":"Extend AI","verdict":"worked","score":null,"score_total":null,"note":"It derives non-OCR line-item fields such as `day_of_week`, `days_pattern`, `time_slot`, and `air_time`."},{"id":"16a432ba-f975-4195-9525-e97b93220074","tool":"landing-ai","tool_name":"Landing AI","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."},{"id":"c3d6a0fb-4f54-4ee8-9e7a-c8382539a82e","tool":"nanonets","tool_name":"Nanonets","verdict":"mixed","score":null,"score_total":null,"note":"It leaves line 8 without derived scheduling fields such as flight_period_start, flight_period_end, frequency, and days_pattern, even though comparable rows populate them."},{"id":"9499ff43-0583-4050-bfe1-951e5a7fb8af","tool":"reducto","tool_name":"Reducto","verdict":"worked","score":null,"score_total":null,"note":"Surfaces derived line-item metadata as structured fields, including frequency = 1x with citation support."},{"id":"0768d86c-2233-428d-9d43-a4c32b86f2c2","tool":"retab","tool_name":"Retab","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."},{"id":"4aecc9a8-5ccf-4aa9-af98-482f367c634d","tool":"unstract","tool_name":"Unstract","verdict":"worked","score":null,"score_total":null,"note":"Extracts the compact days_pattern field correctly as the actual single broadcast-day letter."}]}