{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:324ENFY4EQOPNRZJX5OMDNUBWH","short_pith_number":"pith:324ENFY4","canonical_record":{"source":{"id":"2507.06539","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T04:46:31Z","cross_cats_sorted":[],"title_canon_sha256":"e78d36a59900582652e55bf68b0d4d6ea485d19f951a6ba3dc7def74692a76f9","abstract_canon_sha256":"4e43ef54720c3afac53b8e2a50d8d9c8710db85d5523ceb29b7d452c63dd8853"},"schema_version":"1.0"},"canonical_sha256":"deb846971c241cf6c729bf5cc1b681b1c7097a831276fcfd3e0d246126f480ce","source":{"kind":"arxiv","id":"2507.06539","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06539","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06539v2","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06539","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_12","alias_value":"324ENFY4EQOP","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_16","alias_value":"324ENFY4EQOPNRZJ","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_8","alias_value":"324ENFY4","created_at":"2026-07-05T11:34:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:324ENFY4EQOPNRZJX5OMDNUBWH","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06539","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T04:46:31Z","cross_cats_sorted":[],"title_canon_sha256":"e78d36a59900582652e55bf68b0d4d6ea485d19f951a6ba3dc7def74692a76f9","abstract_canon_sha256":"4e43ef54720c3afac53b8e2a50d8d9c8710db85d5523ceb29b7d452c63dd8853"},"schema_version":"1.0"},"canonical_sha256":"deb846971c241cf6c729bf5cc1b681b1c7097a831276fcfd3e0d246126f480ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:54.114098Z","signature_b64":"3ZI4HQJzOKQ3QVBQHHY0pLfwMSUixu8EJq3p3yCG0q00WcCb0EXR3IDDoyRBY6lmUgD+/i2IYG4KxLvmVRkcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"deb846971c241cf6c729bf5cc1b681b1c7097a831276fcfd3e0d246126f480ce","last_reissued_at":"2026-07-05T11:34:54.113606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:54.113606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06539","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":"2026-07-05T11:34:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQkKU9H54ZKjoTkk+b86fa16sp8Nc8qh7jiwIG1ZdRnXYTWSJuA6a8MzuvKbGzxooxcaxfW06ThDXvymm9nyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:25:08.864130Z"},"content_sha256":"0b3b2a5f304db5f3a1895878f15fdb18a95da133228f7bc02f03c781af06b350","schema_version":"1.0","event_id":"sha256:0b3b2a5f304db5f3a1895878f15fdb18a95da133228f7bc02f03c781af06b350"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:324ENFY4EQOPNRZJX5OMDNUBWH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Model for Extracting Complex Contract Information in Industrial Scenes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Silong Dai, Yanjun Li, Yunyang Cao","submitted_at":"2025-07-09T04:46:31Z","abstract_excerpt":"This paper proposes a high-quality dataset construction method for complex contract information extraction tasks in industrial scenarios and fine-tunes a large language model based on this dataset. Firstly, cluster analysis is performed on industrial contract texts, and GPT-4 and GPT-3.5 are used to extract key information from the original contract data, obtaining high-quality data annotations. Secondly, data augmentation is achieved by constructing new texts, and GPT-3.5 generates unstructured contract texts from randomly combined keywords, improving model robustness. Finally, the large lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06539","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/2507.06539/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":"2026-07-05T11:34:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"udpAXniQpdm72oisgKeM27QIIuuhOqvbXSqAB19R0XywI6l6wMEzKJWVQ8df+zaXmyA56G+7V6pjIxgnRtAwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:25:08.864649Z"},"content_sha256":"4de7a741f7689bcf4fa9584dff2a6c67a77a5c4749021c7c22dbdd1a85dfd9f1","schema_version":"1.0","event_id":"sha256:4de7a741f7689bcf4fa9584dff2a6c67a77a5c4749021c7c22dbdd1a85dfd9f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH/bundle.json","state_url":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/324ENFY4EQOPNRZJX5OMDNUBWH/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":"2026-08-08T16:25:08Z","links":{"resolver":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH","bundle":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH/bundle.json","state":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/324ENFY4EQOPNRZJX5OMDNUBWH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:324ENFY4EQOPNRZJX5OMDNUBWH","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":"4e43ef54720c3afac53b8e2a50d8d9c8710db85d5523ceb29b7d452c63dd8853","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T04:46:31Z","title_canon_sha256":"e78d36a59900582652e55bf68b0d4d6ea485d19f951a6ba3dc7def74692a76f9"},"schema_version":"1.0","source":{"id":"2507.06539","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06539","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06539v2","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06539","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_12","alias_value":"324ENFY4EQOP","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_16","alias_value":"324ENFY4EQOPNRZJ","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_8","alias_value":"324ENFY4","created_at":"2026-07-05T11:34:54Z"}],"graph_snapshots":[{"event_id":"sha256:4de7a741f7689bcf4fa9584dff2a6c67a77a5c4749021c7c22dbdd1a85dfd9f1","target":"graph","created_at":"2026-07-05T11:34:54Z","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/2507.06539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a high-quality dataset construction method for complex contract information extraction tasks in industrial scenarios and fine-tunes a large language model based on this dataset. Firstly, cluster analysis is performed on industrial contract texts, and GPT-4 and GPT-3.5 are used to extract key information from the original contract data, obtaining high-quality data annotations. Secondly, data augmentation is achieved by constructing new texts, and GPT-3.5 generates unstructured contract texts from randomly combined keywords, improving model robustness. Finally, the large lang","authors_text":"Silong Dai, Yanjun Li, Yunyang Cao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T04:46:31Z","title":"Large Language Model for Extracting Complex Contract Information in Industrial Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06539","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":"sha256:0b3b2a5f304db5f3a1895878f15fdb18a95da133228f7bc02f03c781af06b350","target":"record","created_at":"2026-07-05T11:34:54Z","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":"4e43ef54720c3afac53b8e2a50d8d9c8710db85d5523ceb29b7d452c63dd8853","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T04:46:31Z","title_canon_sha256":"e78d36a59900582652e55bf68b0d4d6ea485d19f951a6ba3dc7def74692a76f9"},"schema_version":"1.0","source":{"id":"2507.06539","kind":"arxiv","version":2}},"canonical_sha256":"deb846971c241cf6c729bf5cc1b681b1c7097a831276fcfd3e0d246126f480ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"deb846971c241cf6c729bf5cc1b681b1c7097a831276fcfd3e0d246126f480ce","first_computed_at":"2026-07-05T11:34:54.113606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:54.113606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ZI4HQJzOKQ3QVBQHHY0pLfwMSUixu8EJq3p3yCG0q00WcCb0EXR3IDDoyRBY6lmUgD+/i2IYG4KxLvmVRkcCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:54.114098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06539","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b3b2a5f304db5f3a1895878f15fdb18a95da133228f7bc02f03c781af06b350","sha256:4de7a741f7689bcf4fa9584dff2a6c67a77a5c4749021c7c22dbdd1a85dfd9f1"],"state_sha256":"72d960c31c717ed3ec3473ba6d15ce92be8b28dc9bd8ec362a308d6e6d44ee14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1RLSflePBWdGs7X/2zpOfXG1ZZ3EYYNQw1roJ241Gcp9xA/GhTMNNvPdxLaYacqwYzPquiybyirS0f8YgkBHAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:25:08.878721Z","bundle_sha256":"1903156eb8f8ca3af82f6cfd6d94ae5ae11af5a6d3026463dadffe886301679c"}}