{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LDAI7WG6VNYAIQJIKQDS3GV7JE","short_pith_number":"pith:LDAI7WG6","schema_version":"1.0","canonical_sha256":"58c08fd8deab7004412854072d9abf4928ecddf7e0c931b74d749a1e50972a1c","source":{"kind":"arxiv","id":"2412.02886","version":3},"attestation_state":"computed","paper":{"title":"Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel O'Malley, Hari Viswanathan, Javier E. Santos, Manish Bhattarai, Martin Ma, Minh Vu, Roman Colman","submitted_at":"2024-12-03T22:46:09Z","abstract_excerpt":"For decades, corporations and governments have relied on scanned documents to record vast amounts of information. However, extracting this information is a slow and tedious process due to the sheer volume and complexity of these records. The rise of Vision Language Models (VLMs) presents a way to efficiently and accurately extract the information out of these documents. The current automated workflow often requires a two-step approach involving the extraction of information using optical character recognition software and subsequent usage of large language models for processing this informatio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.02886","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T22:46:09Z","cross_cats_sorted":[],"title_canon_sha256":"874762887bce3cf7b90ac8e0cb78e2ca997e8bb3b19115b7075da7a80bde5128","abstract_canon_sha256":"d80460d8a1895a57df202960dbdcbf8733cf5c59bb5471a62b963c911c19b923"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:13.232461Z","signature_b64":"KSe0rsK9sSjU6XUaRJ5JmstEon1JBjAcL6Y4FnonUTkPgoslhO6yeW3e6eKlVQ7GRflOwBX8Icpo3FBxLwNEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58c08fd8deab7004412854072d9abf4928ecddf7e0c931b74d749a1e50972a1c","last_reissued_at":"2026-07-05T09:49:13.232045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:13.232045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel O'Malley, Hari Viswanathan, Javier E. Santos, Manish Bhattarai, Martin Ma, Minh Vu, Roman Colman","submitted_at":"2024-12-03T22:46:09Z","abstract_excerpt":"For decades, corporations and governments have relied on scanned documents to record vast amounts of information. However, extracting this information is a slow and tedious process due to the sheer volume and complexity of these records. The rise of Vision Language Models (VLMs) presents a way to efficiently and accurately extract the information out of these documents. The current automated workflow often requires a two-step approach involving the extraction of information using optical character recognition software and subsequent usage of large language models for processing this informatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02886","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.02886/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.02886","created_at":"2026-07-05T09:49:13.232104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02886v3","created_at":"2026-07-05T09:49:13.232104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02886","created_at":"2026-07-05T09:49:13.232104+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDAI7WG6VNYA","created_at":"2026-07-05T09:49:13.232104+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDAI7WG6VNYAIQJI","created_at":"2026-07-05T09:49:13.232104+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDAI7WG6","created_at":"2026-07-05T09:49:13.232104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDAI7WG6VNYAIQJIKQDS3GV7JE","json":"https://pith.science/pith/LDAI7WG6VNYAIQJIKQDS3GV7JE.json","graph_json":"https://pith.science/api/pith-number/LDAI7WG6VNYAIQJIKQDS3GV7JE/graph.json","events_json":"https://pith.science/api/pith-number/LDAI7WG6VNYAIQJIKQDS3GV7JE/events.json","paper":"https://pith.science/paper/LDAI7WG6"},"agent_actions":{"view_html":"https://pith.science/pith/LDAI7WG6VNYAIQJIKQDS3GV7JE","download_json":"https://pith.science/pith/LDAI7WG6VNYAIQJIKQDS3GV7JE.json","view_paper":"https://pith.science/paper/LDAI7WG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02886&json=true","fetch_graph":"https://pith.science/api/pith-number/LDAI7WG6VNYAIQJIKQDS3GV7JE/graph.json","fetch_events":"https://pith.science/api/pith-number/LDAI7WG6VNYAIQJIKQDS3GV7JE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDAI7WG6VNYAIQJIKQDS3GV7JE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDAI7WG6VNYAIQJIKQDS3GV7JE/action/storage_attestation","attest_author":"https://pith.science/pith/LDAI7WG6VNYAIQJIKQDS3GV7JE/action/author_attestation","sign_citation":"https://pith.science/pith/LDAI7WG6VNYAIQJIKQDS3GV7JE/action/citation_signature","submit_replication":"https://pith.science/pith/LDAI7WG6VNYAIQJIKQDS3GV7JE/action/replication_record"}},"created_at":"2026-07-05T09:49:13.232104+00:00","updated_at":"2026-07-05T09:49:13.232104+00:00"}