{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:F443JFVMEKN5GWA4PSCM23WPEB","short_pith_number":"pith:F443JFVM","canonical_record":{"source":{"id":"2309.10952","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T22:32:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f8c18a2ff6fb5f9d8f8e3a085a6ac8d70a6fb54d29b9c033a5520381477642ac","abstract_canon_sha256":"2ae50ef5304a93bc6cd4997f91a8df1b92aa5511757d32f8f7c90cfaff3848f1"},"schema_version":"1.0"},"canonical_sha256":"2f39b496ac229bd3581c7c84cd6ecf204a0d675d64ea18b32616540310a2d73c","source":{"kind":"arxiv","id":"2309.10952","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10952","created_at":"2026-07-05T08:35:18Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10952v2","created_at":"2026-07-05T08:35:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10952","created_at":"2026-07-05T08:35:18Z"},{"alias_kind":"pith_short_12","alias_value":"F443JFVMEKN5","created_at":"2026-07-05T08:35:18Z"},{"alias_kind":"pith_short_16","alias_value":"F443JFVMEKN5GWA4","created_at":"2026-07-05T08:35:18Z"},{"alias_kind":"pith_short_8","alias_value":"F443JFVM","created_at":"2026-07-05T08:35:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:F443JFVMEKN5GWA4PSCM23WPEB","target":"record","payload":{"canonical_record":{"source":{"id":"2309.10952","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T22:32:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f8c18a2ff6fb5f9d8f8e3a085a6ac8d70a6fb54d29b9c033a5520381477642ac","abstract_canon_sha256":"2ae50ef5304a93bc6cd4997f91a8df1b92aa5511757d32f8f7c90cfaff3848f1"},"schema_version":"1.0"},"canonical_sha256":"2f39b496ac229bd3581c7c84cd6ecf204a0d675d64ea18b32616540310a2d73c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:18.001866Z","signature_b64":"IVhdlMzDUuTx/uHzIIA2IqGEbMbA9IhaixaiVAiUxNQSUg2dy4AC22gmNr1qu4oJ533XI4uygG3VJo2rZoJFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f39b496ac229bd3581c7c84cd6ecf204a0d675d64ea18b32616540310a2d73c","last_reissued_at":"2026-07-05T08:35:18.001378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:18.001378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.10952","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:35:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQSX5d46GtkfOm0oWb91bhad5WnVo+bpG7vV7K9I7BBy9l61GIlMg62p/AqS/H2XcHHBDJkqxAqK/CAO2xNoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T10:44:33.192192Z"},"content_sha256":"eefc6ad44ee9c16090bc9b8c99e83cd2d25a857a495faa3f12e632ef84fc104b","schema_version":"1.0","event_id":"sha256:eefc6ad44ee9c16090bc9b8c99e83cd2d25a857a495faa3f12e632ef84fc104b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:F443JFVMEKN5GWA4PSCM23WPEB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LMDX: Language Model-based Document Information Extraction and Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen-Yu Lee, Florian Luisier, Guolong Su, Hao Zhang, Jiaqi Mu, Kai Kang, Nan Hua, Ramya Sree Boppana, Vincent Perot, Xiaoyu Sun, Zifeng Wang, Zilong Wang","submitted_at":"2023-09-19T22:32:56Z","abstract_excerpt":"Large Language Models (LLM) have revolutionized Natural Language Processing (NLP), improving state-of-the-art and exhibiting emergent capabilities across various tasks. However, their application in extracting information from visually rich documents, which is at the core of many document processing workflows and involving the extraction of key entities from semi-structured documents, has not yet been successful. The main obstacles to adopting LLMs for this task include the absence of layout encoding within LLMs, which is critical for high quality extraction, and the lack of a grounding mechan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10952","kind":"arxiv","version":2},"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/2309.10952/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":"2026-07-05T08:35:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pXHs+oU8NuGXaYIJhBSlMq5wulD7pXdBncD6Ih0LXuzeU6NkpaM8Rzb1goYCW/TJJVF9n0tY4o/nUVmtuYujBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T10:44:33.192587Z"},"content_sha256":"ae5958701630355070339d819bb68b24dfc469ffd9a6994d39efdcfda5cca18f","schema_version":"1.0","event_id":"sha256:ae5958701630355070339d819bb68b24dfc469ffd9a6994d39efdcfda5cca18f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F443JFVMEKN5GWA4PSCM23WPEB/bundle.json","state_url":"https://pith.science/pith/F443JFVMEKN5GWA4PSCM23WPEB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F443JFVMEKN5GWA4PSCM23WPEB/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":"2026-07-19T10:44:33Z","links":{"resolver":"https://pith.science/pith/F443JFVMEKN5GWA4PSCM23WPEB","bundle":"https://pith.science/pith/F443JFVMEKN5GWA4PSCM23WPEB/bundle.json","state":"https://pith.science/pith/F443JFVMEKN5GWA4PSCM23WPEB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F443JFVMEKN5GWA4PSCM23WPEB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F443JFVMEKN5GWA4PSCM23WPEB","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":"2ae50ef5304a93bc6cd4997f91a8df1b92aa5511757d32f8f7c90cfaff3848f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T22:32:56Z","title_canon_sha256":"f8c18a2ff6fb5f9d8f8e3a085a6ac8d70a6fb54d29b9c033a5520381477642ac"},"schema_version":"1.0","source":{"id":"2309.10952","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10952","created_at":"2026-07-05T08:35:18Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10952v2","created_at":"2026-07-05T08:35:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10952","created_at":"2026-07-05T08:35:18Z"},{"alias_kind":"pith_short_12","alias_value":"F443JFVMEKN5","created_at":"2026-07-05T08:35:18Z"},{"alias_kind":"pith_short_16","alias_value":"F443JFVMEKN5GWA4","created_at":"2026-07-05T08:35:18Z"},{"alias_kind":"pith_short_8","alias_value":"F443JFVM","created_at":"2026-07-05T08:35:18Z"}],"graph_snapshots":[{"event_id":"sha256:ae5958701630355070339d819bb68b24dfc469ffd9a6994d39efdcfda5cca18f","target":"graph","created_at":"2026-07-05T08:35:18Z","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/2309.10952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLM) have revolutionized Natural Language Processing (NLP), improving state-of-the-art and exhibiting emergent capabilities across various tasks. However, their application in extracting information from visually rich documents, which is at the core of many document processing workflows and involving the extraction of key entities from semi-structured documents, has not yet been successful. The main obstacles to adopting LLMs for this task include the absence of layout encoding within LLMs, which is critical for high quality extraction, and the lack of a grounding mechan","authors_text":"Chen-Yu Lee, Florian Luisier, Guolong Su, Hao Zhang, Jiaqi Mu, Kai Kang, Nan Hua, Ramya Sree Boppana, Vincent Perot, Xiaoyu Sun, Zifeng Wang, Zilong Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T22:32:56Z","title":"LMDX: Language Model-based Document Information Extraction and Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10952","kind":"arxiv","version":2},"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:eefc6ad44ee9c16090bc9b8c99e83cd2d25a857a495faa3f12e632ef84fc104b","target":"record","created_at":"2026-07-05T08:35:18Z","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":"2ae50ef5304a93bc6cd4997f91a8df1b92aa5511757d32f8f7c90cfaff3848f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T22:32:56Z","title_canon_sha256":"f8c18a2ff6fb5f9d8f8e3a085a6ac8d70a6fb54d29b9c033a5520381477642ac"},"schema_version":"1.0","source":{"id":"2309.10952","kind":"arxiv","version":2}},"canonical_sha256":"2f39b496ac229bd3581c7c84cd6ecf204a0d675d64ea18b32616540310a2d73c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f39b496ac229bd3581c7c84cd6ecf204a0d675d64ea18b32616540310a2d73c","first_computed_at":"2026-07-05T08:35:18.001378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:18.001378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IVhdlMzDUuTx/uHzIIA2IqGEbMbA9IhaixaiVAiUxNQSUg2dy4AC22gmNr1qu4oJ533XI4uygG3VJo2rZoJFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:18.001866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10952","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eefc6ad44ee9c16090bc9b8c99e83cd2d25a857a495faa3f12e632ef84fc104b","sha256:ae5958701630355070339d819bb68b24dfc469ffd9a6994d39efdcfda5cca18f"],"state_sha256":"982066ca4dd87b3cc4a999e0cdf7981d534f17eaa33def41bf9f6255345e694c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rh4Ru3ydHyQbDywGvm1OHewkBqF36sVqv59GxRuydzrhPvxD3RKHsY88GVhAnbMWFlJlG4kCs07/62ockEGSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T10:44:33.194702Z","bundle_sha256":"b0021d227de29135616107abbe1b9c71d123ad9829b20b38b29d00cd4788ef0a"}}