{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IQTKWHFNAG2BZUNLISURKCGSRS","short_pith_number":"pith:IQTKWHFN","canonical_record":{"source":{"id":"2305.16344","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T10:35:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eecc08677240198672e74ce4b1fd559beab18311c431d8ad73b6b6948acd9abf","abstract_canon_sha256":"00fc3c38d32c9a64ecd0910e2c8d8066bad466c7d6afb08b69ab3c6a76772c40"},"schema_version":"1.0"},"canonical_sha256":"4426ab1cad01b41cd1ab44a91508d28c8501da64011175535162888ffd2a9ac6","source":{"kind":"arxiv","id":"2305.16344","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16344","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16344v2","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16344","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"IQTKWHFNAG2B","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_16","alias_value":"IQTKWHFNAG2BZUNL","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_8","alias_value":"IQTKWHFN","created_at":"2026-07-05T07:53:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IQTKWHFNAG2BZUNLISURKCGSRS","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16344","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T10:35:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eecc08677240198672e74ce4b1fd559beab18311c431d8ad73b6b6948acd9abf","abstract_canon_sha256":"00fc3c38d32c9a64ecd0910e2c8d8066bad466c7d6afb08b69ab3c6a76772c40"},"schema_version":"1.0"},"canonical_sha256":"4426ab1cad01b41cd1ab44a91508d28c8501da64011175535162888ffd2a9ac6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:08.429997Z","signature_b64":"GB048DadqocT3W+q3ApE1lkLqxN22LvuopK6reXS9MKf0FnhiwLrR/2FZxkQAtjUOPh358i1aYRE8Vy/mAMABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4426ab1cad01b41cd1ab44a91508d28c8501da64011175535162888ffd2a9ac6","last_reissued_at":"2026-07-05T07:53:08.429540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:08.429540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16344","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":"2026-07-05T07:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Parb2LGVU8tHC/gEaagj8WxGuHrggGxZVdBp4eQQG0djSFynxpKMan4Ja7pQ/+0mKiVDUi77Ddw089fBip4dBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:13:02.493936Z"},"content_sha256":"e242c6521550a3c567746849d983f53dd089d278dc4f131a67fce2d53db033e5","schema_version":"1.0","event_id":"sha256:e242c6521550a3c567746849d983f53dd089d278dc4f131a67fce2d53db033e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IQTKWHFNAG2BZUNLISURKCGSRS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chongjian Yue, Dongmei Zhang, Hengyu Liu, Lun Du, Shi Han, Xiaojun Ma, Xinrun Xu, Yanbing Jiang, Zhiming Ding","submitted_at":"2023-05-24T10:35:58Z","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 underexplored. In this research, we specialize in harnessing the potential of LLMs to comprehend critical information from financial reports, which are hybrid long-documents. We propose an Automated Financial Information Extraction (AFIE) framework that enhances LLMs' ability to comprehend and extract information from financial reports. To evaluate AFIE, we develop a Fina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16344","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/2305.16344/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":"2026-07-05T07:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xjCgCdx2mZnXO6+h8ghDMd6rw0UjM0N8hxw0bUPF2ir+0lwg9zLT5xg22cZNvqNmv0bSvnjBpobaZ/7fyML3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:13:02.494454Z"},"content_sha256":"d8bbf827b4e38f931621ed422da9a84fe8c3f89595afa26044f4bba40f05a01a","schema_version":"1.0","event_id":"sha256:d8bbf827b4e38f931621ed422da9a84fe8c3f89595afa26044f4bba40f05a01a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQTKWHFNAG2BZUNLISURKCGSRS/bundle.json","state_url":"https://pith.science/pith/IQTKWHFNAG2BZUNLISURKCGSRS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQTKWHFNAG2BZUNLISURKCGSRS/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":"2026-08-08T01:13:02Z","links":{"resolver":"https://pith.science/pith/IQTKWHFNAG2BZUNLISURKCGSRS","bundle":"https://pith.science/pith/IQTKWHFNAG2BZUNLISURKCGSRS/bundle.json","state":"https://pith.science/pith/IQTKWHFNAG2BZUNLISURKCGSRS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQTKWHFNAG2BZUNLISURKCGSRS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IQTKWHFNAG2BZUNLISURKCGSRS","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":"00fc3c38d32c9a64ecd0910e2c8d8066bad466c7d6afb08b69ab3c6a76772c40","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T10:35:58Z","title_canon_sha256":"eecc08677240198672e74ce4b1fd559beab18311c431d8ad73b6b6948acd9abf"},"schema_version":"1.0","source":{"id":"2305.16344","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16344","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16344v2","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16344","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"IQTKWHFNAG2B","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_16","alias_value":"IQTKWHFNAG2BZUNL","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_8","alias_value":"IQTKWHFN","created_at":"2026-07-05T07:53:08Z"}],"graph_snapshots":[{"event_id":"sha256:d8bbf827b4e38f931621ed422da9a84fe8c3f89595afa26044f4bba40f05a01a","target":"graph","created_at":"2026-07-05T07:53:08Z","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/2305.16344/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 underexplored. In this research, we specialize in harnessing the potential of LLMs to comprehend critical information from financial reports, which are hybrid long-documents. We propose an Automated Financial Information Extraction (AFIE) framework that enhances LLMs' ability to comprehend and extract information from financial reports. To evaluate AFIE, we develop a Fina","authors_text":"Chongjian Yue, Dongmei Zhang, Hengyu Liu, Lun Du, Shi Han, Xiaojun Ma, Xinrun Xu, Yanbing Jiang, Zhiming Ding","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T10:35:58Z","title":"Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16344","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:e242c6521550a3c567746849d983f53dd089d278dc4f131a67fce2d53db033e5","target":"record","created_at":"2026-07-05T07:53:08Z","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":"00fc3c38d32c9a64ecd0910e2c8d8066bad466c7d6afb08b69ab3c6a76772c40","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T10:35:58Z","title_canon_sha256":"eecc08677240198672e74ce4b1fd559beab18311c431d8ad73b6b6948acd9abf"},"schema_version":"1.0","source":{"id":"2305.16344","kind":"arxiv","version":2}},"canonical_sha256":"4426ab1cad01b41cd1ab44a91508d28c8501da64011175535162888ffd2a9ac6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4426ab1cad01b41cd1ab44a91508d28c8501da64011175535162888ffd2a9ac6","first_computed_at":"2026-07-05T07:53:08.429540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:08.429540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GB048DadqocT3W+q3ApE1lkLqxN22LvuopK6reXS9MKf0FnhiwLrR/2FZxkQAtjUOPh358i1aYRE8Vy/mAMABg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:08.429997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16344","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e242c6521550a3c567746849d983f53dd089d278dc4f131a67fce2d53db033e5","sha256:d8bbf827b4e38f931621ed422da9a84fe8c3f89595afa26044f4bba40f05a01a"],"state_sha256":"226fcf7df2b165e0a8f4282a43ad3dc142ebe1b6f93f70ae13defad85a949bc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z22PVtFUbCayZQ/vENODThV8FbagWjy5p3953+VMmwYru6tKiWgmNUdu9vgn6oCqQJfl0f2OJafh+mKoGWMLAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:13:02.500045Z","bundle_sha256":"a1c2515f7ff953805c3d75eb573b7020899db6e0082aa7e39d4ee5b2b6d15146"}}