{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GAUZRVIZKWHZFW474YVIJOFXTM","short_pith_number":"pith:GAUZRVIZ","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"},"canonical_sha256":"302998d519558f92db9fe62a84b8b79b0a8648d367344c9cd477ea17cf9073e9","source":{"kind":"arxiv","id":"2306.02142","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02142","created_at":"2026-07-05T06:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02142v1","created_at":"2026-07-05T06:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02142","created_at":"2026-07-05T06:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"GAUZRVIZKWHZ","created_at":"2026-07-05T06:17:13Z"},{"alias_kind":"pith_short_16","alias_value":"GAUZRVIZKWHZFW47","created_at":"2026-07-05T06:17:13Z"},{"alias_kind":"pith_short_8","alias_value":"GAUZRVIZ","created_at":"2026-07-05T06:17:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GAUZRVIZKWHZFW474YVIJOFXTM","target":"record","payload":{"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"},"canonical_sha256":"302998d519558f92db9fe62a84b8b79b0a8648d367344c9cd477ea17cf9073e9","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"},"source_kind":"arxiv","source_id":"2306.02142","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XewGyYLaYYN11WWzSnzSrkTD6MH0rSIItl8uGYvtTCAiLv9T+1GrzZrDfo65Un1W10LzZnwFa3mqTXCTj1KKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:05:27.228040Z"},"content_sha256":"f66a20e784e35f587c3d558c5cf6ab4958483658d02438c625f7f5a324088668","schema_version":"1.0","event_id":"sha256:f66a20e784e35f587c3d558c5cf6ab4958483658d02438c625f7f5a324088668"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GAUZRVIZKWHZFW474YVIJOFXTM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"25AUgTtk4oOYrfOTd8KY81jvK4hafSKrw35+lZb51c3R6PxdMD91iovqAZMNnSUEy5T20p2TJz7kFG2qm5GnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:05:27.228602Z"},"content_sha256":"b8ca9bdcd2f7cdf861a51193774ad01ca983afc8e704693ca121f5fc7681252e","schema_version":"1.0","event_id":"sha256:b8ca9bdcd2f7cdf861a51193774ad01ca983afc8e704693ca121f5fc7681252e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM/bundle.json","state_url":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GAUZRVIZKWHZFW474YVIJOFXTM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T12:05:27Z","links":{"resolver":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM","bundle":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM/bundle.json","state":"https://pith.science/pith/GAUZRVIZKWHZFW474YVIJOFXTM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GAUZRVIZKWHZFW474YVIJOFXTM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GAUZRVIZKWHZFW474YVIJOFXTM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ab20160b610c0042b31a88ebb6db5e8f1c8d627497331e34187886f0b0699754","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-03T15:56:30Z","title_canon_sha256":"0e7882f8f1bcb1c596ba0f3977a4a9938dbd931f56ad592d81de73ea899b76e5"},"schema_version":"1.0","source":{"id":"2306.02142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02142","created_at":"2026-07-05T06:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02142v1","created_at":"2026-07-05T06:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02142","created_at":"2026-07-05T06:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"GAUZRVIZKWHZ","created_at":"2026-07-05T06:17:13Z"},{"alias_kind":"pith_short_16","alias_value":"GAUZRVIZKWHZFW47","created_at":"2026-07-05T06:17:13Z"},{"alias_kind":"pith_short_8","alias_value":"GAUZRVIZ","created_at":"2026-07-05T06:17:13Z"}],"graph_snapshots":[{"event_id":"sha256:b8ca9bdcd2f7cdf861a51193774ad01ca983afc8e704693ca121f5fc7681252e","target":"graph","created_at":"2026-07-05T06:17:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.02142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gaurav Harit, Sagar Chakraborty, Saptarshi Ghosh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-03T15:56:30Z","title":"TransDocAnalyser: A Framework for Offline Semi-structured Handwritten Document Analysis in the Legal Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02142","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f66a20e784e35f587c3d558c5cf6ab4958483658d02438c625f7f5a324088668","target":"record","created_at":"2026-07-05T06:17:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ab20160b610c0042b31a88ebb6db5e8f1c8d627497331e34187886f0b0699754","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-03T15:56:30Z","title_canon_sha256":"0e7882f8f1bcb1c596ba0f3977a4a9938dbd931f56ad592d81de73ea899b76e5"},"schema_version":"1.0","source":{"id":"2306.02142","kind":"arxiv","version":1}},"canonical_sha256":"302998d519558f92db9fe62a84b8b79b0a8648d367344c9cd477ea17cf9073e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"302998d519558f92db9fe62a84b8b79b0a8648d367344c9cd477ea17cf9073e9","first_computed_at":"2026-07-05T06:17:13.410248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:13.410248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/AzysHB7GOb/jwKDj3s/VhJ7dGAu+Pkd1QYU+XjG33oc13G/7Xu9E0y5rlYWOBY+Dy1lNGYV3Xqc8q34Ak7AAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:13.410597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f66a20e784e35f587c3d558c5cf6ab4958483658d02438c625f7f5a324088668","sha256:b8ca9bdcd2f7cdf861a51193774ad01ca983afc8e704693ca121f5fc7681252e"],"state_sha256":"ec104570ed73e1ca52371f1763bf87e662b4078271bc1f61fc473f6c10d05c61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+u9nhgsqS16N/Lzy+mhHvieLE/8/mEyX2O+rZbpP/h2GbPrLyn+QX2ZS1Z/vP7jkLkR81/J55v/qEXn82AnRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:05:27.239485Z","bundle_sha256":"c8402b78aa7b3218cda103ce6bfed414754fffad1e7416f22cd3b5d32679cd99"}}