{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V3HO4VUB2KBAHM5HNWXSWAENQI","short_pith_number":"pith:V3HO4VUB","schema_version":"1.0","canonical_sha256":"aeceee5681d28203b3a76daf2b008d822a14d2f1922fb70e9666ead0ee20b739","source":{"kind":"arxiv","id":"2607.24745","version":1},"attestation_state":"computed","paper":{"title":"DocAnnot -- Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Goutham Vignesh, Harikrishnan P M, Siddartha Reddy, Varun V, Vishal Vaddina","submitted_at":"2026-05-08T07:43:02Z","abstract_excerpt":"Key Information Extraction (KIE) is vital for many document applications, but creating training datasets is traditionally a time-consuming manual process. We introduce DocAnnot, a framework that significantly accelerates KIE dataset generation. DocAnnot leverages a Large Vision Language Model (LVLM) for label value extraction, OCR for text/bounding box detection, and a novel Spatially Informed Contextual Matching (SICM) algorithm. SICM improves label-value association by combining spatial relationships and proximity analysis with textual matching. We evaluate our framework on the CORD and SROI"},"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":"2607.24745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-08T07:43:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"ae18a88a6447c9c33f82f16850497e9a7a97ff2cd0b57e4090fb521b533b6a60","abstract_canon_sha256":"648c24cf7cc53847c1a6a0a010b50986b6c4599a517b52243ae5674a8e7019ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:41.796300Z","signature_b64":"iieu4TSILPFGPsET/Hojy4E3ILIx2oWbxo3/Ap2K8AWZU/a8uiaBAOLSPPpvNIljm2Mt+nKKo//mpzEIKCLGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aeceee5681d28203b3a76daf2b008d822a14d2f1922fb70e9666ead0ee20b739","last_reissued_at":"2026-07-29T00:24:41.795358Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:41.795358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocAnnot -- Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Goutham Vignesh, Harikrishnan P M, Siddartha Reddy, Varun V, Vishal Vaddina","submitted_at":"2026-05-08T07:43:02Z","abstract_excerpt":"Key Information Extraction (KIE) is vital for many document applications, but creating training datasets is traditionally a time-consuming manual process. We introduce DocAnnot, a framework that significantly accelerates KIE dataset generation. DocAnnot leverages a Large Vision Language Model (LVLM) for label value extraction, OCR for text/bounding box detection, and a novel Spatially Informed Contextual Matching (SICM) algorithm. SICM improves label-value association by combining spatial relationships and proximity analysis with textual matching. We evaluate our framework on the CORD and SROI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24745","kind":"arxiv","version":1},"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/2607.24745/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":"2607.24745","created_at":"2026-07-29T00:24:41.795812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24745v1","created_at":"2026-07-29T00:24:41.795812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24745","created_at":"2026-07-29T00:24:41.795812+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3HO4VUB2KBA","created_at":"2026-07-29T00:24:41.795812+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3HO4VUB2KBAHM5H","created_at":"2026-07-29T00:24:41.795812+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3HO4VUB","created_at":"2026-07-29T00:24:41.795812+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/V3HO4VUB2KBAHM5HNWXSWAENQI","json":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI.json","graph_json":"https://pith.science/api/pith-number/V3HO4VUB2KBAHM5HNWXSWAENQI/graph.json","events_json":"https://pith.science/api/pith-number/V3HO4VUB2KBAHM5HNWXSWAENQI/events.json","paper":"https://pith.science/paper/V3HO4VUB"},"agent_actions":{"view_html":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI","download_json":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI.json","view_paper":"https://pith.science/paper/V3HO4VUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24745&json=true","fetch_graph":"https://pith.science/api/pith-number/V3HO4VUB2KBAHM5HNWXSWAENQI/graph.json","fetch_events":"https://pith.science/api/pith-number/V3HO4VUB2KBAHM5HNWXSWAENQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/action/storage_attestation","attest_author":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/action/author_attestation","sign_citation":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/action/citation_signature","submit_replication":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/action/replication_record"}},"created_at":"2026-07-29T00:24:41.795812+00:00","updated_at":"2026-07-29T00:24:41.795812+00:00"}