{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GAUZRVIZKWHZFW474YVIJOFXTM","short_pith_number":"pith:GAUZRVIZ","schema_version":"1.0","canonical_sha256":"302998d519558f92db9fe62a84b8b79b0a8648d367344c9cd477ea17cf9073e9","source":{"kind":"arxiv","id":"2306.02142","version":1},"attestation_state":"computed","paper":{"title":"TransDocAnalyser: A Framework for Offline Semi-structured Handwritten Document Analysis in the Legal Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gaurav Harit, Sagar Chakraborty, Saptarshi Ghosh","submitted_at":"2023-06-03T15:56:30Z","abstract_excerpt":"State-of-the-art offline Optical Character Recognition (OCR) frameworks perform poorly on semi-structured handwritten domain-specific documents due to their inability to localize and label form fields with domain-specific semantics. Existing techniques for semi-structured document analysis have primarily used datasets comprising invoices, purchase orders, receipts, and identity-card documents for benchmarking. In this work, we build the first semi-structured document analysis dataset in the legal domain by collecting a large number of First Information Report (FIR) documents from several polic"},"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":"2306.02142","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-03T15:56:30Z","cross_cats_sorted":[],"title_canon_sha256":"0e7882f8f1bcb1c596ba0f3977a4a9938dbd931f56ad592d81de73ea899b76e5","abstract_canon_sha256":"ab20160b610c0042b31a88ebb6db5e8f1c8d627497331e34187886f0b0699754"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:13.410597Z","signature_b64":"/AzysHB7GOb/jwKDj3s/VhJ7dGAu+Pkd1QYU+XjG33oc13G/7Xu9E0y5rlYWOBY+Dy1lNGYV3Xqc8q34Ak7AAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"302998d519558f92db9fe62a84b8b79b0a8648d367344c9cd477ea17cf9073e9","last_reissued_at":"2026-07-05T06:17:13.410248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:13.410248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransDocAnalyser: A Framework for Offline Semi-structured Handwritten Document Analysis in the Legal Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gaurav Harit, Sagar Chakraborty, Saptarshi Ghosh","submitted_at":"2023-06-03T15:56:30Z","abstract_excerpt":"State-of-the-art offline Optical Character Recognition (OCR) frameworks perform poorly on semi-structured handwritten domain-specific documents due to their inability to localize and label form fields with domain-specific semantics. Existing techniques for semi-structured document analysis have primarily used datasets comprising invoices, purchase orders, receipts, and identity-card documents for benchmarking. In this work, we build the first semi-structured document analysis dataset in the legal domain by collecting a large number of First Information Report (FIR) documents from several polic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02142","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/2306.02142/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":"2306.02142","created_at":"2026-07-05T06:17:13.410302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02142v1","created_at":"2026-07-05T06:17:13.410302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02142","created_at":"2026-07-05T06:17:13.410302+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAUZRVIZKWHZ","created_at":"2026-07-05T06:17:13.410302+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAUZRVIZKWHZFW47","created_at":"2026-07-05T06:17:13.410302+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAUZRVIZ","created_at":"2026-07-05T06:17:13.410302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11156","citing_title":"Digitization of Document and Information Extraction using OCR","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM","json":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM.json","graph_json":"https://pith.science/api/pith-number/GAUZRVIZKWHZFW474YVIJOFXTM/graph.json","events_json":"https://pith.science/api/pith-number/GAUZRVIZKWHZFW474YVIJOFXTM/events.json","paper":"https://pith.science/paper/GAUZRVIZ"},"agent_actions":{"view_html":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM","download_json":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM.json","view_paper":"https://pith.science/paper/GAUZRVIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02142&json=true","fetch_graph":"https://pith.science/api/pith-number/GAUZRVIZKWHZFW474YVIJOFXTM/graph.json","fetch_events":"https://pith.science/api/pith-number/GAUZRVIZKWHZFW474YVIJOFXTM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM/action/storage_attestation","attest_author":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM/action/author_attestation","sign_citation":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM/action/citation_signature","submit_replication":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM/action/replication_record"}},"created_at":"2026-07-05T06:17:13.410302+00:00","updated_at":"2026-07-05T06:17:13.410302+00:00"}