{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6J3NE5IE3WUWUGZDOPIHOGBRK4","short_pith_number":"pith:6J3NE5IE","schema_version":"1.0","canonical_sha256":"f276d27504dda96a1b2373d0771831571f1b1acadfbed679247d50413459019e","source":{"kind":"arxiv","id":"2404.18255","version":5},"attestation_state":"computed","paper":{"title":"PatentGPT: A Large Language Model for Intellectual Property","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changyang Tu, Chaochao Wang, Cheng Sun, Cong Wang, Fu Bian, Haoran Hua, Haowen Liu, Jianping Lu, Jie Fang, Jing Sun, Licong Xu, Linqing Chen, Lisha Zhang, Lizhi Zhou, Meng Hu, Peng Xu, Qijun Cai, ruiji zhang, Tian Qiu, Weikuan Wang, Weilei Wang, Xiaolong Gu, Yan Fang, Yixin Wang, Yuan Zhong, Yubin Xia, Zilong Bai","submitted_at":"2024-04-28T17:36:43Z","abstract_excerpt":"In recent years, large language models(LLMs) have attracted significant attention due to their exceptional performance across a multitude of natural language process tasks, and have been widely applied in various fields. However, the application of large language models in the Intellectual Property (IP) domain is challenging due to the strong need for specialized knowledge, privacy protection, processing of extremely long text in this field. In this technical report, we present for the first time a low-cost, standardized procedure for training IP-oriented LLMs, meeting the unique requirements "},"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":"2404.18255","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-28T17:36:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"46444318a5ae39f7f41965d614940ddcde28cf480a0a7e25a597ab4a18e89d64","abstract_canon_sha256":"9c98b991cfc2b5db61b400e7dc24ed406b1e6a1980b7532130d37492297dcfe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:26.049483Z","signature_b64":"51ydJCudOrxU816NjulMXm7FrIROh3FLj2Cts9xM266hIXLwvEYOEBWeWrIzMbBpr3Lqz4CCQTKaoiVW0Qz1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f276d27504dda96a1b2373d0771831571f1b1acadfbed679247d50413459019e","last_reissued_at":"2026-07-05T08:27:26.049032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:26.049032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PatentGPT: A Large Language Model for Intellectual Property","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changyang Tu, Chaochao Wang, Cheng Sun, Cong Wang, Fu Bian, Haoran Hua, Haowen Liu, Jianping Lu, Jie Fang, Jing Sun, Licong Xu, Linqing Chen, Lisha Zhang, Lizhi Zhou, Meng Hu, Peng Xu, Qijun Cai, ruiji zhang, Tian Qiu, Weikuan Wang, Weilei Wang, Xiaolong Gu, Yan Fang, Yixin Wang, Yuan Zhong, Yubin Xia, Zilong Bai","submitted_at":"2024-04-28T17:36:43Z","abstract_excerpt":"In recent years, large language models(LLMs) have attracted significant attention due to their exceptional performance across a multitude of natural language process tasks, and have been widely applied in various fields. However, the application of large language models in the Intellectual Property (IP) domain is challenging due to the strong need for specialized knowledge, privacy protection, processing of extremely long text in this field. In this technical report, we present for the first time a low-cost, standardized procedure for training IP-oriented LLMs, meeting the unique requirements "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18255","kind":"arxiv","version":5},"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/2404.18255/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":"2404.18255","created_at":"2026-07-05T08:27:26.049088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18255v5","created_at":"2026-07-05T08:27:26.049088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18255","created_at":"2026-07-05T08:27:26.049088+00:00"},{"alias_kind":"pith_short_12","alias_value":"6J3NE5IE3WUW","created_at":"2026-07-05T08:27:26.049088+00:00"},{"alias_kind":"pith_short_16","alias_value":"6J3NE5IE3WUWUGZD","created_at":"2026-07-05T08:27:26.049088+00:00"},{"alias_kind":"pith_short_8","alias_value":"6J3NE5IE","created_at":"2026-07-05T08:27:26.049088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24296","citing_title":"When Does Synthetic Patent Data Help? Volume-Fidelity Trade-offs in Low-Resource Multi-Label Classification","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6J3NE5IE3WUWUGZDOPIHOGBRK4","json":"https://pith.science/pith/6J3NE5IE3WUWUGZDOPIHOGBRK4.json","graph_json":"https://pith.science/api/pith-number/6J3NE5IE3WUWUGZDOPIHOGBRK4/graph.json","events_json":"https://pith.science/api/pith-number/6J3NE5IE3WUWUGZDOPIHOGBRK4/events.json","paper":"https://pith.science/paper/6J3NE5IE"},"agent_actions":{"view_html":"https://pith.science/pith/6J3NE5IE3WUWUGZDOPIHOGBRK4","download_json":"https://pith.science/pith/6J3NE5IE3WUWUGZDOPIHOGBRK4.json","view_paper":"https://pith.science/paper/6J3NE5IE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18255&json=true","fetch_graph":"https://pith.science/api/pith-number/6J3NE5IE3WUWUGZDOPIHOGBRK4/graph.json","fetch_events":"https://pith.science/api/pith-number/6J3NE5IE3WUWUGZDOPIHOGBRK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6J3NE5IE3WUWUGZDOPIHOGBRK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6J3NE5IE3WUWUGZDOPIHOGBRK4/action/storage_attestation","attest_author":"https://pith.science/pith/6J3NE5IE3WUWUGZDOPIHOGBRK4/action/author_attestation","sign_citation":"https://pith.science/pith/6J3NE5IE3WUWUGZDOPIHOGBRK4/action/citation_signature","submit_replication":"https://pith.science/pith/6J3NE5IE3WUWUGZDOPIHOGBRK4/action/replication_record"}},"created_at":"2026-07-05T08:27:26.049088+00:00","updated_at":"2026-07-05T08:27:26.049088+00:00"}