{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GZK2E5MWQ2INLC3BN7NTCNQG3P","short_pith_number":"pith:GZK2E5MW","schema_version":"1.0","canonical_sha256":"3655a275968690d58b616fdb313606dbe58f8f5a372cabc47e82fc0032eeb0a2","source":{"kind":"arxiv","id":"2403.04105","version":3},"attestation_state":"computed","paper":{"title":"Natural Language Processing in the Patent Domain: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lekang Jiang, Stephan Goetz","submitted_at":"2024-03-06T23:17:16Z","abstract_excerpt":"Patents, which encapsulate crucial technical and legal information in text form and referenced drawings, present a rich domain for natural language processing (NLP) applications. As NLP technologies evolve, large language models (LLMs) have demonstrated outstanding capabilities in general text processing and generation tasks. However, the application of LLMs in the patent domain remains under-explored and under-developed due to the complexity of patents, particularly their language and legal framework. Understanding the unique characteristics of patent documents and related research in the pat"},"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":"2403.04105","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-06T23:17:16Z","cross_cats_sorted":[],"title_canon_sha256":"f14d26402b3c0ff1746aeaf0839a563e32e39ce26461e88a42895cdb84318424","abstract_canon_sha256":"e6cbe36087deb2dad6a073ac74089e27d62f8119aa17d67da009cd066f8e4f73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:54.061779Z","signature_b64":"1NBP477HqtOWNmg51/755air9ldG4ne/3mQdx566ayyXadJ4cTxh0eZq7TbpH6isQSGYOq/c3Ld1tLw8+9AEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3655a275968690d58b616fdb313606dbe58f8f5a372cabc47e82fc0032eeb0a2","last_reissued_at":"2026-07-05T10:52:54.061334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:54.061334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Natural Language Processing in the Patent Domain: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lekang Jiang, Stephan Goetz","submitted_at":"2024-03-06T23:17:16Z","abstract_excerpt":"Patents, which encapsulate crucial technical and legal information in text form and referenced drawings, present a rich domain for natural language processing (NLP) applications. As NLP technologies evolve, large language models (LLMs) have demonstrated outstanding capabilities in general text processing and generation tasks. However, the application of LLMs in the patent domain remains under-explored and under-developed due to the complexity of patents, particularly their language and legal framework. Understanding the unique characteristics of patent documents and related research in the pat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04105","kind":"arxiv","version":3},"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/2403.04105/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":"2403.04105","created_at":"2026-07-05T10:52:54.061398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.04105v3","created_at":"2026-07-05T10:52:54.061398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04105","created_at":"2026-07-05T10:52:54.061398+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZK2E5MWQ2IN","created_at":"2026-07-05T10:52:54.061398+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZK2E5MWQ2INLC3B","created_at":"2026-07-05T10:52:54.061398+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZK2E5MW","created_at":"2026-07-05T10:52:54.061398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01717","citing_title":"Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AI","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZK2E5MWQ2INLC3BN7NTCNQG3P","json":"https://pith.science/pith/GZK2E5MWQ2INLC3BN7NTCNQG3P.json","graph_json":"https://pith.science/api/pith-number/GZK2E5MWQ2INLC3BN7NTCNQG3P/graph.json","events_json":"https://pith.science/api/pith-number/GZK2E5MWQ2INLC3BN7NTCNQG3P/events.json","paper":"https://pith.science/paper/GZK2E5MW"},"agent_actions":{"view_html":"https://pith.science/pith/GZK2E5MWQ2INLC3BN7NTCNQG3P","download_json":"https://pith.science/pith/GZK2E5MWQ2INLC3BN7NTCNQG3P.json","view_paper":"https://pith.science/paper/GZK2E5MW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.04105&json=true","fetch_graph":"https://pith.science/api/pith-number/GZK2E5MWQ2INLC3BN7NTCNQG3P/graph.json","fetch_events":"https://pith.science/api/pith-number/GZK2E5MWQ2INLC3BN7NTCNQG3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZK2E5MWQ2INLC3BN7NTCNQG3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZK2E5MWQ2INLC3BN7NTCNQG3P/action/storage_attestation","attest_author":"https://pith.science/pith/GZK2E5MWQ2INLC3BN7NTCNQG3P/action/author_attestation","sign_citation":"https://pith.science/pith/GZK2E5MWQ2INLC3BN7NTCNQG3P/action/citation_signature","submit_replication":"https://pith.science/pith/GZK2E5MWQ2INLC3BN7NTCNQG3P/action/replication_record"}},"created_at":"2026-07-05T10:52:54.061398+00:00","updated_at":"2026-07-05T10:52:54.061398+00:00"}