{"observation":{"id":"e2f47c60-3f78-4b14-aa96-2e76d8e2483a","tool":"reducto","tool_name":"Reducto","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":"bank-statement-pdf","scenario_name":"Bank Statement PDF","group_tag":"financial-document-extraction","scenario_description":"A 4-page bank statement PDF with 51 transactions, balances, rewards, and disclaimer text, used to test schema-driven extraction of dense financial tables and multi-page continuity.","modality":"pdf","input_text":null,"input_artifact_refs":[{"alt":null,"url":"https://d3epheqghktydj.cloudfront.net/extract-and-query-structured-data-from-d-bank-statement-pdf-25ec532be6e1.pdf","role":"input","filename":"Bank Statement PDF.pdf"}],"stresses":["Table extraction across 50+ transaction rows","Multi-page continuity with BALANCE FORWARD bridges","Structured metadata vs. free-text transaction descriptions","Numerical accuracy for balances, deposits, withdrawals, and summaries","Nested schema population for account, branch, balances, rewards, and disclaimers"],"verdict":"failed","score":null,"score_total":null,"note":"Leaves derived transaction metadata incomplete, with transaction_type and transaction_id missing across transaction rows.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/research-media-bank-statement-schema-transactions-00d0c871c403.png","role":"input","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/b8fa1b7a29974c7192fab2f6023708c6.png?v=1","role":"output","alt":null},{"url":"https://d3epheqghktydj.cloudfront.net/research-media-reducto-extracted-transactions-6831b5a2572e.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":"input-and-output","input":{"state":"files","text":null,"files":[{"url":"https://d3epheqghktydj.cloudfront.net/extract-and-query-structured-data-from-d-bank-statement-pdf-25ec532be6e1.pdf","filename":"Bank Statement PDF.pdf","alt":"Bank Statement PDF","role":"input"}],"modality":"pdf","stresses":["Table extraction across 50+ transaction rows","Multi-page continuity with BALANCE FORWARD bridges","Structured metadata vs. free-text transaction descriptions","Numerical accuracy for balances, deposits, withdrawals, and summaries","Nested schema population for account, branch, balances, rewards, and disclaimers"]},"tool_page_slug":"reducto","tool_url":"https://aidemos.com/tools/reducto","permalink":"https://aidemos.com/evidence/e2f47c60-3f78-4b14-aa96-2e76d8e2483a","api_url":"https://ai.aidemos.com/v1/observations/e2f47c60-3f78-4b14-aa96-2e76d8e2483a"},"peers":[{"id":"6028e5fa-9c96-4f9c-ad9d-5cc900225ace","tool":"datalab","tool_name":"Datalab","verdict":"failed","score":null,"score_total":null,"note":"Does not populate schema-derived transaction identifiers at all: the 18 Jun withdrawal keeps transaction_id = null even though the identifier is visible in the source row.","artifact_count":4,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/80135a758c5a4d2aa2187e8af3f050e8.png?v=1","evidence_url":"https://aidemos.com/evidence/6028e5fa-9c96-4f9c-ad9d-5cc900225ace"},{"id":"2c4cdb0a-b344-4604-b614-c97af6d74ea2","tool":"extend-ai","tool_name":"Extend AI","verdict":"worked","score":null,"score_total":null,"note":"It classifies bank transactions into derived `transaction_type` values such as Withdrawal or Deposit from the description text.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-extend-ai-transaction-type-5ef541ac7fec.png","evidence_url":"https://aidemos.com/evidence/2c4cdb0a-b344-4604-b614-c97af6d74ea2"},{"id":"a2a1f6f5-e278-415c-afcd-a43a2ec3e91b","tool":"landing-ai","tool_name":"Landing AI","verdict":"worked","score":null,"score_total":null,"note":"Adds meaningful transaction_type labels to extracted rows, classifying the sample 18 Jun records as Withdrawal, Withdrawal, and Deposit instead of leaving the field as raw OCR text.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-landing-ai-bank-statement-18-jun-extract-321aa2936cc6.png","evidence_url":"https://aidemos.com/evidence/a2a1f6f5-e278-415c-afcd-a43a2ec3e91b"},{"id":"e10bbd24-0b50-44a1-8902-eb59e2fbaf4f","tool":"llamaparse","tool_name":"LlamaParse","verdict":"failed","score":null,"score_total":null,"note":"Fails to derive transaction-level fields, leaving transaction_id and transaction_type empty even for descriptions that encode ATM, UPI, and CRADJ cues.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-llamaparse-bank-statement-transaction-id-c01a0d30b3be.png","evidence_url":"https://aidemos.com/evidence/e10bbd24-0b50-44a1-8902-eb59e2fbaf4f"},{"id":"db96ee62-b038-4189-9112-9ff53de816f8","tool":"nanonets","tool_name":"Nanonets","verdict":"failed","score":null,"score_total":null,"note":"It does not populate the derived transaction_type field, leaving it null across the statement instead of classifying deposits and withdrawals.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-bank-statement-2-jul-a511cf7bd0d6.png","evidence_url":"https://aidemos.com/evidence/db96ee62-b038-4189-9112-9ff53de816f8"},{"id":"0067b41d-0138-4fc0-80b1-151bb93e2539","tool":"retab","tool_name":"Retab","verdict":"worked","score":null,"score_total":null,"note":"Derives transaction_type and transaction_id on transaction rows, classifying one record as UPI with transaction_id 917615251879 and cheque_number left empty.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-bank-statement-2-jul-a511cf7bd0d6.png","evidence_url":"https://aidemos.com/evidence/0067b41d-0138-4fc0-80b1-151bb93e2539"},{"id":"9c65076c-303b-4d4c-a3f7-619f2667c82e","tool":"unstract","tool_name":"Unstract","verdict":"worked","score":null,"score_total":null,"note":"Classifies transaction_type correctly across the transaction array, using Deposit and Withdrawal labels rather than raw OCR text.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/6d9450b3c58b477ea0066e52ceb2f6ca.png?v=1","evidence_url":"https://aidemos.com/evidence/9c65076c-303b-4d4c-a3f7-619f2667c82e"}],"other_criteria":[{"id":"5ac2276f-3c09-465c-88d0-3a8315e997f4","criterion":"extraction-accuracy","criterion_name":"Extraction Accuracy","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"Gets some bank values right but misstates a core aggregate: summary.total_transactions is reported as 70 even though the report says the correct count is 40.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/5ac2276f-3c09-465c-88d0-3a8315e997f4"},{"id":"956bec9e-b310-4628-a049-b04b3e645b5e","criterion":"extraction-accuracy","criterion_name":"Extraction Accuracy","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"The tool correctly extracts the bank statement currency as INR and includes citation metadata for that field.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/956bec9e-b310-4628-a049-b04b3e645b5e"},{"id":"95071c07-2f7a-463b-b7c7-3738ddbd3651","criterion":"schema-adherence","criterion_name":"Schema Adherence","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Reconstructs the bank statement into a nested JSON structure aligned to the requested schema, with document metadata, account, branch, statement period, transactions, summary, and rewards-style sections instead of flat OCR text.","artifact_count":6,"evidence_url":"https://aidemos.com/evidence/95071c07-2f7a-463b-b7c7-3738ddbd3651"},{"id":"2d9d828a-e002-45f9-9dfe-93aef402a5de","criterion":"structural-clean-output","criterion_name":"Structural Clean Output","rank_role":"context","verdict":"mixed","score":null,"score_total":null,"note":"Exports JSON directly, but the bank workflow is not cleanly consumable end-to-end because the report says the result still needs reconciliation and correction before use.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/2d9d828a-e002-45f9-9dfe-93aef402a5de"},{"id":"d7084667-c138-440e-ae8a-85055f890e01","criterion":"table-and-record-completeness","criterion_name":"Table & Record Completeness","rank_role":"decisive","verdict":"failed","score":null,"score_total":null,"note":"Does not preserve the repeating transaction table faithfully, returning 53 transaction records for a statement that contains 51 transactions.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/d7084667-c138-440e-ae8a-85055f890e01"}],"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":"6028e5fa-9c96-4f9c-ad9d-5cc900225ace","tool":"datalab","tool_name":"Datalab","verdict":"failed","score":null,"score_total":null,"note":"Does not populate schema-derived transaction identifiers at all: the 18 Jun withdrawal keeps transaction_id = null even though the identifier is visible in the source row."},{"id":"2c4cdb0a-b344-4604-b614-c97af6d74ea2","tool":"extend-ai","tool_name":"Extend AI","verdict":"worked","score":null,"score_total":null,"note":"It classifies bank transactions into derived `transaction_type` values such as Withdrawal or Deposit from the description text."},{"id":"a2a1f6f5-e278-415c-afcd-a43a2ec3e91b","tool":"landing-ai","tool_name":"Landing AI","verdict":"worked","score":null,"score_total":null,"note":"Adds meaningful transaction_type labels to extracted rows, classifying the sample 18 Jun records as Withdrawal, Withdrawal, and Deposit instead of leaving the field as raw OCR text."},{"id":"e10bbd24-0b50-44a1-8902-eb59e2fbaf4f","tool":"llamaparse","tool_name":"LlamaParse","verdict":"failed","score":null,"score_total":null,"note":"Fails to derive transaction-level fields, leaving transaction_id and transaction_type empty even for descriptions that encode ATM, UPI, and CRADJ cues."},{"id":"db96ee62-b038-4189-9112-9ff53de816f8","tool":"nanonets","tool_name":"Nanonets","verdict":"failed","score":null,"score_total":null,"note":"It does not populate the derived transaction_type field, leaving it null across the statement instead of classifying deposits and withdrawals."},{"id":"0067b41d-0138-4fc0-80b1-151bb93e2539","tool":"retab","tool_name":"Retab","verdict":"worked","score":null,"score_total":null,"note":"Derives transaction_type and transaction_id on transaction rows, classifying one record as UPI with transaction_id 917615251879 and cheque_number left empty."},{"id":"9c65076c-303b-4d4c-a3f7-619f2667c82e","tool":"unstract","tool_name":"Unstract","verdict":"worked","score":null,"score_total":null,"note":"Classifies transaction_type correctly across the transaction array, using Deposit and Withdrawal labels rather than raw OCR text."}]}