{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UJ2ZTEXRIRY7C4GF7MTP4IL3II","short_pith_number":"pith:UJ2ZTEXR","schema_version":"1.0","canonical_sha256":"a2759992f14471f170c5fb26fe217b42322aee789b794fa75a6da9a4e259f371","source":{"kind":"arxiv","id":"2305.10383","version":2},"attestation_state":"computed","paper":{"title":"Large-Scale Text Analysis Using Generative Language Models: A Case Study in Discovering Public Value Expressions in AI Patents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Barbara Ribeiro, Gaurav Verma, Philip Shapira, Sergio Pelaez","submitted_at":"2023-05-17T17:18:26Z","abstract_excerpt":"Labeling data is essential for training text classifiers but is often difficult to accomplish accurately, especially for complex and abstract concepts. Seeking an improved method, this paper employs a novel approach using a generative language model (GPT-4) to produce labels and rationales for large-scale text analysis. We apply this approach to the task of discovering public value expressions in US AI patents. We collect a database comprising 154,934 patent documents using an advanced Boolean query submitted to InnovationQ+. The results are merged with full patent text from the USPTO, resulti"},"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":"2305.10383","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:18:26Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"ccdb55524636ab4cc3048f656df56e308157b1a0fb67139c7cf688a84fa4bd70","abstract_canon_sha256":"8bed137d5b6efff6449301b239e3c18a37acb526a3354d5bb0686dcc49e96b1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:06.145165Z","signature_b64":"z7SGdJUCRlZyk3thafxKHr5bN5nhz6kbTikwBOGuwfysWZEdaCDglkf8pynRAO9V3m1biY1NnVK4eyqfPTdIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2759992f14471f170c5fb26fe217b42322aee789b794fa75a6da9a4e259f371","last_reissued_at":"2026-07-05T09:55:06.144669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:06.144669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Text Analysis Using Generative Language Models: A Case Study in Discovering Public Value Expressions in AI Patents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Barbara Ribeiro, Gaurav Verma, Philip Shapira, Sergio Pelaez","submitted_at":"2023-05-17T17:18:26Z","abstract_excerpt":"Labeling data is essential for training text classifiers but is often difficult to accomplish accurately, especially for complex and abstract concepts. Seeking an improved method, this paper employs a novel approach using a generative language model (GPT-4) to produce labels and rationales for large-scale text analysis. We apply this approach to the task of discovering public value expressions in US AI patents. We collect a database comprising 154,934 patent documents using an advanced Boolean query submitted to InnovationQ+. The results are merged with full patent text from the USPTO, resulti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10383","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/2305.10383/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":"2305.10383","created_at":"2026-07-05T09:55:06.144725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10383v2","created_at":"2026-07-05T09:55:06.144725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10383","created_at":"2026-07-05T09:55:06.144725+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJ2ZTEXRIRY7","created_at":"2026-07-05T09:55:06.144725+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJ2ZTEXRIRY7C4GF","created_at":"2026-07-05T09:55:06.144725+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJ2ZTEXR","created_at":"2026-07-05T09:55:06.144725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16662","citing_title":"A Supervised Machine Learning Approach for Assessing Grant Peer Review Reports","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJ2ZTEXRIRY7C4GF7MTP4IL3II","json":"https://pith.science/pith/UJ2ZTEXRIRY7C4GF7MTP4IL3II.json","graph_json":"https://pith.science/api/pith-number/UJ2ZTEXRIRY7C4GF7MTP4IL3II/graph.json","events_json":"https://pith.science/api/pith-number/UJ2ZTEXRIRY7C4GF7MTP4IL3II/events.json","paper":"https://pith.science/paper/UJ2ZTEXR"},"agent_actions":{"view_html":"https://pith.science/pith/UJ2ZTEXRIRY7C4GF7MTP4IL3II","download_json":"https://pith.science/pith/UJ2ZTEXRIRY7C4GF7MTP4IL3II.json","view_paper":"https://pith.science/paper/UJ2ZTEXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10383&json=true","fetch_graph":"https://pith.science/api/pith-number/UJ2ZTEXRIRY7C4GF7MTP4IL3II/graph.json","fetch_events":"https://pith.science/api/pith-number/UJ2ZTEXRIRY7C4GF7MTP4IL3II/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJ2ZTEXRIRY7C4GF7MTP4IL3II/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJ2ZTEXRIRY7C4GF7MTP4IL3II/action/storage_attestation","attest_author":"https://pith.science/pith/UJ2ZTEXRIRY7C4GF7MTP4IL3II/action/author_attestation","sign_citation":"https://pith.science/pith/UJ2ZTEXRIRY7C4GF7MTP4IL3II/action/citation_signature","submit_replication":"https://pith.science/pith/UJ2ZTEXRIRY7C4GF7MTP4IL3II/action/replication_record"}},"created_at":"2026-07-05T09:55:06.144725+00:00","updated_at":"2026-07-05T09:55:06.144725+00:00"}