{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HKK3J4QOKHUW2KELTOJJG7ELH4","short_pith_number":"pith:HKK3J4QO","canonical_record":{"source":{"id":"2505.13535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-18T15:49:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5bf97ea211d8deaaf3d6061e4e7fe2316bbcd6b07dd1a075ab02397a24bdaf7e","abstract_canon_sha256":"22f69d34cdca8156a716d388d901d1fd3cc5cc449fbc73ce8f5859d0a74389c9"},"schema_version":"1.0"},"canonical_sha256":"3a95b4f20e51e96d288b9b92937c8b3f21392473992aacaca838b10df1f1f5a5","source":{"kind":"arxiv","id":"2505.13535","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13535","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13535v1","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13535","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"HKK3J4QOKHUW","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"HKK3J4QOKHUW2KEL","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"HKK3J4QO","created_at":"2026-07-05T11:05:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HKK3J4QOKHUW2KELTOJJG7ELH4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-18T15:49:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5bf97ea211d8deaaf3d6061e4e7fe2316bbcd6b07dd1a075ab02397a24bdaf7e","abstract_canon_sha256":"22f69d34cdca8156a716d388d901d1fd3cc5cc449fbc73ce8f5859d0a74389c9"},"schema_version":"1.0"},"canonical_sha256":"3a95b4f20e51e96d288b9b92937c8b3f21392473992aacaca838b10df1f1f5a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:47.429373Z","signature_b64":"8WxhZfLPVqQIqpX1c0oF4EBs4sjdmfdeV0s7DSh/yO3ouqdC3i3r807kCvctxFusu7I4D3wPUxvz8y88JiKNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a95b4f20e51e96d288b9b92937c8b3f21392473992aacaca838b10df1f1f5a5","last_reissued_at":"2026-07-05T11:05:47.428872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:47.428872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13535","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":"2026-07-05T11:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FGQsXj2RSbxm1wGeIP8yASKEDOVk3vdt2xyV4N88BC1FBaHh/Fk4YbX8iIWuY6ky8KhCJ4vqxgb4TPXluwPpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:46:04.013028Z"},"content_sha256":"c22d67fb35a7d452c3b1e33ee8aed8c034908b5ea110d0427e04054a6ada50f8","schema_version":"1.0","event_id":"sha256:c22d67fb35a7d452c3b1e33ee8aed8c034908b5ea110d0427e04054a6ada50f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HKK3J4QOKHUW2KELTOJJG7ELH4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual Segments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Amit Pathak, Aniket Bhattacharyya, Anurag Tripathi, Archan Karmakar, Maneesh Gupta, Ujjal Das","submitted_at":"2025-05-18T15:49:17Z","abstract_excerpt":"Information extraction (IE) from Visually Rich Documents (VRDs) containing layout features along with text is a critical and well-studied task. Specialized non-LLM NLP-based solutions typically involve training models using both textual and geometric information to label sequences/tokens as named entities or answers to specific questions. However, these approaches lack reasoning, are not able to infer values not explicitly present in documents, and do not generalize well to new formats. Generative LLM-based approaches proposed recently are capable of reasoning, but struggle to comprehend clues"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13535","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/2505.13535/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":"2026-07-05T11:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L5xKqXxRx1lwkibhJKd6hzvyf8OKTfzGj7SF6X+GZTFqifObl59S7Crmgc5T+q/3B0R3yTkDSWNX8WfATaZ8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:46:04.013568Z"},"content_sha256":"1afe857d39ce8366d85199121b5d4367da8379216b6597de7763e4bca222b774","schema_version":"1.0","event_id":"sha256:1afe857d39ce8366d85199121b5d4367da8379216b6597de7763e4bca222b774"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HKK3J4QOKHUW2KELTOJJG7ELH4/bundle.json","state_url":"https://pith.science/pith/HKK3J4QOKHUW2KELTOJJG7ELH4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HKK3J4QOKHUW2KELTOJJG7ELH4/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":"2026-08-18T23:46:04Z","links":{"resolver":"https://pith.science/pith/HKK3J4QOKHUW2KELTOJJG7ELH4","bundle":"https://pith.science/pith/HKK3J4QOKHUW2KELTOJJG7ELH4/bundle.json","state":"https://pith.science/pith/HKK3J4QOKHUW2KELTOJJG7ELH4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HKK3J4QOKHUW2KELTOJJG7ELH4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HKK3J4QOKHUW2KELTOJJG7ELH4","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":"22f69d34cdca8156a716d388d901d1fd3cc5cc449fbc73ce8f5859d0a74389c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-18T15:49:17Z","title_canon_sha256":"5bf97ea211d8deaaf3d6061e4e7fe2316bbcd6b07dd1a075ab02397a24bdaf7e"},"schema_version":"1.0","source":{"id":"2505.13535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13535","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13535v1","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13535","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"HKK3J4QOKHUW","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"HKK3J4QOKHUW2KEL","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"HKK3J4QO","created_at":"2026-07-05T11:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:1afe857d39ce8366d85199121b5d4367da8379216b6597de7763e4bca222b774","target":"graph","created_at":"2026-07-05T11:05:47Z","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/2505.13535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Information extraction (IE) from Visually Rich Documents (VRDs) containing layout features along with text is a critical and well-studied task. Specialized non-LLM NLP-based solutions typically involve training models using both textual and geometric information to label sequences/tokens as named entities or answers to specific questions. However, these approaches lack reasoning, are not able to infer values not explicitly present in documents, and do not generalize well to new formats. Generative LLM-based approaches proposed recently are capable of reasoning, but struggle to comprehend clues","authors_text":"Amit Pathak, Aniket Bhattacharyya, Anurag Tripathi, Archan Karmakar, Maneesh Gupta, Ujjal Das","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-18T15:49:17Z","title":"Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual Segments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13535","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:c22d67fb35a7d452c3b1e33ee8aed8c034908b5ea110d0427e04054a6ada50f8","target":"record","created_at":"2026-07-05T11:05:47Z","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":"22f69d34cdca8156a716d388d901d1fd3cc5cc449fbc73ce8f5859d0a74389c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-18T15:49:17Z","title_canon_sha256":"5bf97ea211d8deaaf3d6061e4e7fe2316bbcd6b07dd1a075ab02397a24bdaf7e"},"schema_version":"1.0","source":{"id":"2505.13535","kind":"arxiv","version":1}},"canonical_sha256":"3a95b4f20e51e96d288b9b92937c8b3f21392473992aacaca838b10df1f1f5a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a95b4f20e51e96d288b9b92937c8b3f21392473992aacaca838b10df1f1f5a5","first_computed_at":"2026-07-05T11:05:47.428872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:47.428872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8WxhZfLPVqQIqpX1c0oF4EBs4sjdmfdeV0s7DSh/yO3ouqdC3i3r807kCvctxFusu7I4D3wPUxvz8y88JiKNCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:47.429373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c22d67fb35a7d452c3b1e33ee8aed8c034908b5ea110d0427e04054a6ada50f8","sha256:1afe857d39ce8366d85199121b5d4367da8379216b6597de7763e4bca222b774"],"state_sha256":"c3e2af36b73f8e23cb443465275a40ab49869b645a19fce5ddacaf192a7e442d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ruFJT0qwfVWYlK0R9xtcCk1W7SPY3MANjoO8e9zme+mCoZ8c8v6b6OPUHwynLp6gg6oVFxun8LN32TMu2+57DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:46:04.018544Z","bundle_sha256":"8a97fcc0361eaceff201af337e89e0d029b67cfe2d10d7d050595fa5b64ffa55"}}