{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GXS7GZTP4G26CD6BM2FAW7NFXC","short_pith_number":"pith:GXS7GZTP","canonical_record":{"source":{"id":"2307.07929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T02:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"c9304e4627cb1a7b7785d7d2c1a8aaf8105efdb2fe744636b84c80c24c6f9a48","abstract_canon_sha256":"615924671035ed1422010989bc1789a81d943484624ab72eb894149846c0fa4c"},"schema_version":"1.0"},"canonical_sha256":"35e5f3666fe1b5e10fc1668a0b7da5b89cfef701c42a226569827fb96a663be5","source":{"kind":"arxiv","id":"2307.07929","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07929","created_at":"2026-07-05T06:31:17Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07929v1","created_at":"2026-07-05T06:31:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07929","created_at":"2026-07-05T06:31:17Z"},{"alias_kind":"pith_short_12","alias_value":"GXS7GZTP4G26","created_at":"2026-07-05T06:31:17Z"},{"alias_kind":"pith_short_16","alias_value":"GXS7GZTP4G26CD6B","created_at":"2026-07-05T06:31:17Z"},{"alias_kind":"pith_short_8","alias_value":"GXS7GZTP","created_at":"2026-07-05T06:31:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GXS7GZTP4G26CD6BM2FAW7NFXC","target":"record","payload":{"canonical_record":{"source":{"id":"2307.07929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T02:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"c9304e4627cb1a7b7785d7d2c1a8aaf8105efdb2fe744636b84c80c24c6f9a48","abstract_canon_sha256":"615924671035ed1422010989bc1789a81d943484624ab72eb894149846c0fa4c"},"schema_version":"1.0"},"canonical_sha256":"35e5f3666fe1b5e10fc1668a0b7da5b89cfef701c42a226569827fb96a663be5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:17.733147Z","signature_b64":"fCHljMvQWvWe7M3YU0yGJ3kxFubYblxGubQ7nY4vP9jEaOxYyiKlOityi2m9o6u9GFiCJtZkGp9jfV6nfSZPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35e5f3666fe1b5e10fc1668a0b7da5b89cfef701c42a226569827fb96a663be5","last_reissued_at":"2026-07-05T06:31:17.732651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:17.732651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.07929","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":"2026-07-05T06:31:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GAZNJEhnnf2Fn2hDjQ7NrCdRmEBAjPSPr+9aq7H0mOxQWWWKDfPfDY5TIB+64Lg/L31/ffkQs5M1ata2wPjMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:03:37.894348Z"},"content_sha256":"6191e7bf2a0e1acd6749dbe338bfe1403cfdd8c779161b1dcd8eda680f7cf67a","schema_version":"1.0","event_id":"sha256:6191e7bf2a0e1acd6749dbe338bfe1403cfdd8c779161b1dcd8eda680f7cf67a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GXS7GZTP4G26CD6BM2FAW7NFXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocTr: Document Transformer for Structured Information Extraction in Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ankan Bansal, Aruni RoyChowdhury, Haofu Liao, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Weijian Li, Yuting Zhang, Zhuowen Tu","submitted_at":"2023-07-16T02:59:30Z","abstract_excerpt":"We present a new formulation for structured information extraction (SIE) from visually rich documents. It aims to address the limitations of existing IOB tagging or graph-based formulations, which are either overly reliant on the correct ordering of input text or struggle with decoding a complex graph. Instead, motivated by anchor-based object detectors in vision, we represent an entity as an anchor word and a bounding box, and represent entity linking as the association between anchor words. This is more robust to text ordering, and maintains a compact graph for entity linking. The formulatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07929","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/2307.07929/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":"2026-07-05T06:31:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g5ndlIQ1Z58pHHKTJNfyOltaUK4Fjfs8Tp7uSFwk3ndgUV5gzZ47YForMXL7KnBxbCE2azFhmIedLwdkyCSLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:03:37.895048Z"},"content_sha256":"6581e47baa86d4ae2d48100db7ad78798dfe2bb85a4968dc96ff12cd38a25ef5","schema_version":"1.0","event_id":"sha256:6581e47baa86d4ae2d48100db7ad78798dfe2bb85a4968dc96ff12cd38a25ef5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/bundle.json","state_url":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/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":"2026-08-12T18:03:37Z","links":{"resolver":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC","bundle":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/bundle.json","state":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GXS7GZTP4G26CD6BM2FAW7NFXC","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":"615924671035ed1422010989bc1789a81d943484624ab72eb894149846c0fa4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T02:59:30Z","title_canon_sha256":"c9304e4627cb1a7b7785d7d2c1a8aaf8105efdb2fe744636b84c80c24c6f9a48"},"schema_version":"1.0","source":{"id":"2307.07929","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07929","created_at":"2026-07-05T06:31:17Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07929v1","created_at":"2026-07-05T06:31:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07929","created_at":"2026-07-05T06:31:17Z"},{"alias_kind":"pith_short_12","alias_value":"GXS7GZTP4G26","created_at":"2026-07-05T06:31:17Z"},{"alias_kind":"pith_short_16","alias_value":"GXS7GZTP4G26CD6B","created_at":"2026-07-05T06:31:17Z"},{"alias_kind":"pith_short_8","alias_value":"GXS7GZTP","created_at":"2026-07-05T06:31:17Z"}],"graph_snapshots":[{"event_id":"sha256:6581e47baa86d4ae2d48100db7ad78798dfe2bb85a4968dc96ff12cd38a25ef5","target":"graph","created_at":"2026-07-05T06:31:17Z","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/2307.07929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new formulation for structured information extraction (SIE) from visually rich documents. It aims to address the limitations of existing IOB tagging or graph-based formulations, which are either overly reliant on the correct ordering of input text or struggle with decoding a complex graph. Instead, motivated by anchor-based object detectors in vision, we represent an entity as an anchor word and a bounding box, and represent entity linking as the association between anchor words. This is more robust to text ordering, and maintains a compact graph for entity linking. The formulatio","authors_text":"Ankan Bansal, Aruni RoyChowdhury, Haofu Liao, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Weijian Li, Yuting Zhang, Zhuowen Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T02:59:30Z","title":"DocTr: Document Transformer for Structured Information Extraction in Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07929","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":"sha256:6191e7bf2a0e1acd6749dbe338bfe1403cfdd8c779161b1dcd8eda680f7cf67a","target":"record","created_at":"2026-07-05T06:31:17Z","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":"615924671035ed1422010989bc1789a81d943484624ab72eb894149846c0fa4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T02:59:30Z","title_canon_sha256":"c9304e4627cb1a7b7785d7d2c1a8aaf8105efdb2fe744636b84c80c24c6f9a48"},"schema_version":"1.0","source":{"id":"2307.07929","kind":"arxiv","version":1}},"canonical_sha256":"35e5f3666fe1b5e10fc1668a0b7da5b89cfef701c42a226569827fb96a663be5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35e5f3666fe1b5e10fc1668a0b7da5b89cfef701c42a226569827fb96a663be5","first_computed_at":"2026-07-05T06:31:17.732651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:31:17.732651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fCHljMvQWvWe7M3YU0yGJ3kxFubYblxGubQ7nY4vP9jEaOxYyiKlOityi2m9o6u9GFiCJtZkGp9jfV6nfSZPCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:31:17.733147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.07929","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6191e7bf2a0e1acd6749dbe338bfe1403cfdd8c779161b1dcd8eda680f7cf67a","sha256:6581e47baa86d4ae2d48100db7ad78798dfe2bb85a4968dc96ff12cd38a25ef5"],"state_sha256":"85034321bf1747e5ae8ba56451e14ab2940a71bb819d5af88d93e2e6a6bac309"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9iDadvVvdH9UE//V+kLAh92bmDmjGPi+T4bv6lwAnyxVVLdA4KK29lkfMGdkdPjGPW/MrNuQyEbQJuAdSFFbAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:03:37.900405Z","bundle_sha256":"9262f2ec9c5a89f79f1545e95276f347e8326df71e4785b1a283370f8e5647dd"}}