{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:324ENFY4EQOPNRZJX5OMDNUBWH","short_pith_number":"pith:324ENFY4","schema_version":"1.0","canonical_sha256":"deb846971c241cf6c729bf5cc1b681b1c7097a831276fcfd3e0d246126f480ce","source":{"kind":"arxiv","id":"2507.06539","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.06539","created_at":"2026-07-05T11:34:54.113667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06539v2","created_at":"2026-07-05T11:34:54.113667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06539","created_at":"2026-07-05T11:34:54.113667+00:00"},{"alias_kind":"pith_short_12","alias_value":"324ENFY4EQOP","created_at":"2026-07-05T11:34:54.113667+00:00"},{"alias_kind":"pith_short_16","alias_value":"324ENFY4EQOPNRZJ","created_at":"2026-07-05T11:34:54.113667+00:00"},{"alias_kind":"pith_short_8","alias_value":"324ENFY4","created_at":"2026-07-05T11:34:54.113667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH","json":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH.json","graph_json":"https://pith.science/api/pith-number/324ENFY4EQOPNRZJX5OMDNUBWH/graph.json","events_json":"https://pith.science/api/pith-number/324ENFY4EQOPNRZJX5OMDNUBWH/events.json","paper":"https://pith.science/paper/324ENFY4"},"agent_actions":{"view_html":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH","download_json":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH.json","view_paper":"https://pith.science/paper/324ENFY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06539&json=true","fetch_graph":"https://pith.science/api/pith-number/324ENFY4EQOPNRZJX5OMDNUBWH/graph.json","fetch_events":"https://pith.science/api/pith-number/324ENFY4EQOPNRZJX5OMDNUBWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH/action/storage_attestation","attest_author":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH/action/author_attestation","sign_citation":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH/action/citation_signature","submit_replication":"https://pith.science/pith/324ENFY4EQOPNRZJX5OMDNUBWH/action/replication_record"}},"created_at":"2026-07-05T11:34:54.113667+00:00","updated_at":"2026-07-05T11:34:54.113667+00:00"}