{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NOEH3LWEAAWB7YVJ2HLKJIYCOA","short_pith_number":"pith:NOEH3LWE","canonical_record":{"source":{"id":"2412.20072","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-28T07:54:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"83f2e21bd3c81a6e5246cb72eefb3e7a9340a87abf601550baa6657d1dffb261","abstract_canon_sha256":"6c7f8daa2bd544d07a78b2af291d968e8b103621b27c55805bed9a238ddf2d8c"},"schema_version":"1.0"},"canonical_sha256":"6b887daec4002c1fe2a9d1d6a4a302700ed4e7859d0857292af8fe39ba9ac016","source":{"kind":"arxiv","id":"2412.20072","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20072","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20072v2","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20072","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"NOEH3LWEAAWB","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_16","alias_value":"NOEH3LWEAAWB7YVJ","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_8","alias_value":"NOEH3LWE","created_at":"2026-07-05T09:55:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NOEH3LWEAAWB7YVJ2HLKJIYCOA","target":"record","payload":{"canonical_record":{"source":{"id":"2412.20072","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-28T07:54:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"83f2e21bd3c81a6e5246cb72eefb3e7a9340a87abf601550baa6657d1dffb261","abstract_canon_sha256":"6c7f8daa2bd544d07a78b2af291d968e8b103621b27c55805bed9a238ddf2d8c"},"schema_version":"1.0"},"canonical_sha256":"6b887daec4002c1fe2a9d1d6a4a302700ed4e7859d0857292af8fe39ba9ac016","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:37.091927Z","signature_b64":"cYoDoQ70cwixddf36lSHrNdDk3Py1xiG3WlLneN0qqjGWlICQZQayrhpjWeS2MFxBiV0jAPWeAh6rZORcykNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b887daec4002c1fe2a9d1d6a4a302700ed4e7859d0857292af8fe39ba9ac016","last_reissued_at":"2026-07-05T09:55:37.091340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:37.091340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.20072","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":"2026-07-05T09:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iE4UO8DI2kzHCTPmVbly8QqOwFZxVU6oWCNmX3B2huhP+6TuII88dzCAU4ylwzjIPLuOl+5Xg9PLf3Evw0TQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:47:34.953711Z"},"content_sha256":"fee3a3fdf136a5aa8a416da867dd51dec33805c63e8329978aa58c91a724a2e2","schema_version":"1.0","event_id":"sha256:fee3a3fdf136a5aa8a416da867dd51dec33805c63e8329978aa58c91a724a2e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NOEH3LWEAAWB7YVJ2HLKJIYCOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chongjian Yue, Dongmei Zhang, Lun Du, Qi Zhang, Shi Han, Xiaojun Ma, Xinrun Xu, Zhiming Ding","submitted_at":"2024-12-28T07:54:14Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains unexplored. The hybrid text often appears in the form of hybrid long documents (HLDs), which far exceed the token limit of LLMs. Consequently, we apply an Automated Information Extraction framework (AIE) to enable LLMs to process the HLDs and carry out experiments to analyse four important aspects of information extraction from HLDs. Given the findings: 1) The effective w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20072","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/2412.20072/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":"2026-07-05T09:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3+tvRvG/C5+kLEmMxz2oNi5oct1IMn8+abKMDbegAd7LObPstFrteIgz/rWO4z6CoN1k7oFMr4llOVabFbFxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:47:34.954210Z"},"content_sha256":"0a2e0dc435857ca44d3159392cee2c7db5c56d32270b8406faaaf377eeb10865","schema_version":"1.0","event_id":"sha256:0a2e0dc435857ca44d3159392cee2c7db5c56d32270b8406faaaf377eeb10865"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NOEH3LWEAAWB7YVJ2HLKJIYCOA/bundle.json","state_url":"https://pith.science/pith/NOEH3LWEAAWB7YVJ2HLKJIYCOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NOEH3LWEAAWB7YVJ2HLKJIYCOA/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":"2026-08-15T03:47:34Z","links":{"resolver":"https://pith.science/pith/NOEH3LWEAAWB7YVJ2HLKJIYCOA","bundle":"https://pith.science/pith/NOEH3LWEAAWB7YVJ2HLKJIYCOA/bundle.json","state":"https://pith.science/pith/NOEH3LWEAAWB7YVJ2HLKJIYCOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NOEH3LWEAAWB7YVJ2HLKJIYCOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NOEH3LWEAAWB7YVJ2HLKJIYCOA","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":"6c7f8daa2bd544d07a78b2af291d968e8b103621b27c55805bed9a238ddf2d8c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-28T07:54:14Z","title_canon_sha256":"83f2e21bd3c81a6e5246cb72eefb3e7a9340a87abf601550baa6657d1dffb261"},"schema_version":"1.0","source":{"id":"2412.20072","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20072","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20072v2","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20072","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"NOEH3LWEAAWB","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_16","alias_value":"NOEH3LWEAAWB7YVJ","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_8","alias_value":"NOEH3LWE","created_at":"2026-07-05T09:55:37Z"}],"graph_snapshots":[{"event_id":"sha256:0a2e0dc435857ca44d3159392cee2c7db5c56d32270b8406faaaf377eeb10865","target":"graph","created_at":"2026-07-05T09:55:37Z","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/2412.20072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains unexplored. The hybrid text often appears in the form of hybrid long documents (HLDs), which far exceed the token limit of LLMs. Consequently, we apply an Automated Information Extraction framework (AIE) to enable LLMs to process the HLDs and carry out experiments to analyse four important aspects of information extraction from HLDs. Given the findings: 1) The effective w","authors_text":"Chongjian Yue, Dongmei Zhang, Lun Du, Qi Zhang, Shi Han, Xiaojun Ma, Xinrun Xu, Zhiming Ding","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-28T07:54:14Z","title":"Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20072","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:fee3a3fdf136a5aa8a416da867dd51dec33805c63e8329978aa58c91a724a2e2","target":"record","created_at":"2026-07-05T09:55:37Z","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":"6c7f8daa2bd544d07a78b2af291d968e8b103621b27c55805bed9a238ddf2d8c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-28T07:54:14Z","title_canon_sha256":"83f2e21bd3c81a6e5246cb72eefb3e7a9340a87abf601550baa6657d1dffb261"},"schema_version":"1.0","source":{"id":"2412.20072","kind":"arxiv","version":2}},"canonical_sha256":"6b887daec4002c1fe2a9d1d6a4a302700ed4e7859d0857292af8fe39ba9ac016","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b887daec4002c1fe2a9d1d6a4a302700ed4e7859d0857292af8fe39ba9ac016","first_computed_at":"2026-07-05T09:55:37.091340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:37.091340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cYoDoQ70cwixddf36lSHrNdDk3Py1xiG3WlLneN0qqjGWlICQZQayrhpjWeS2MFxBiV0jAPWeAh6rZORcykNDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:37.091927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20072","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fee3a3fdf136a5aa8a416da867dd51dec33805c63e8329978aa58c91a724a2e2","sha256:0a2e0dc435857ca44d3159392cee2c7db5c56d32270b8406faaaf377eeb10865"],"state_sha256":"11bd40e3ad38cf14f9b6d0f964a00fd0c40d5b68e8abb3cc80e8c00ecbd40c99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QhntO2Fe5OuXMeVTW4qubauURq9LalPn/C+Vq5MzEQru7mSHBI41iAfp3dQ4g/wZzL/nuwoqul+TdGTTlBhyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T03:47:34.957551Z","bundle_sha256":"595788204f740181d8e6657b7de2b2b060ff1c68b44a428b9ab42fe38a1239a7"}}