{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:47Q4VG6RFOZNPJABPB73BZAQT4","short_pith_number":"pith:47Q4VG6R","schema_version":"1.0","canonical_sha256":"e7e1ca9bd12bb2d7a401787fb0e4109f23dec863ca640e10c81a3860fa0e9f4e","source":{"kind":"arxiv","id":"2311.01449","version":2},"attestation_state":"computed","paper":{"title":"TopicGPT: A Prompt-based Topic Modeling Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hoyle, Chau Minh Pham, Mohit Iyyer, Philip Resnik, Simeng Sun","submitted_at":"2023-11-02T17:57:10Z","abstract_excerpt":"Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require \"reading the tea leaves\" to interpret; additionally, they offer users minimal control over the formatting and specificity of resulting topics. To tackle these issues, we introduce TopicGPT, a prompt-based framework that uses large language models (LLMs) to uncover latent topics in a text collection. TopicGPT produces topics that align better with human categorizations compared to competing methods: it achieves a harmonic mean puri"},"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":"2311.01449","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-02T17:57:10Z","cross_cats_sorted":[],"title_canon_sha256":"82ac4a2b2e819ed144517120a84e1ed40ba9ddc1b79299894290b67e086ca99a","abstract_canon_sha256":"8d8e3155611a36c1767140e863a0350b9443a695c176edcc1b1e4bc321c33904"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:08.058988Z","signature_b64":"VWMBuAnKaODRtK+kD2Q+jU+fete/lCQzKOBeaN+p1D6P2kLQutvJF71oClefrOdLJmTMnOGeRDLF5yrYnWT2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7e1ca9bd12bb2d7a401787fb0e4109f23dec863ca640e10c81a3860fa0e9f4e","last_reissued_at":"2026-07-05T08:03:08.058472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:08.058472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TopicGPT: A Prompt-based Topic Modeling Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hoyle, Chau Minh Pham, Mohit Iyyer, Philip Resnik, Simeng Sun","submitted_at":"2023-11-02T17:57:10Z","abstract_excerpt":"Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require \"reading the tea leaves\" to interpret; additionally, they offer users minimal control over the formatting and specificity of resulting topics. To tackle these issues, we introduce TopicGPT, a prompt-based framework that uses large language models (LLMs) to uncover latent topics in a text collection. TopicGPT produces topics that align better with human categorizations compared to competing methods: it achieves a harmonic mean puri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01449","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/2311.01449/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":"2311.01449","created_at":"2026-07-05T08:03:08.058531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01449v2","created_at":"2026-07-05T08:03:08.058531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01449","created_at":"2026-07-05T08:03:08.058531+00:00"},{"alias_kind":"pith_short_12","alias_value":"47Q4VG6RFOZN","created_at":"2026-07-05T08:03:08.058531+00:00"},{"alias_kind":"pith_short_16","alias_value":"47Q4VG6RFOZNPJAB","created_at":"2026-07-05T08:03:08.058531+00:00"},{"alias_kind":"pith_short_8","alias_value":"47Q4VG6R","created_at":"2026-07-05T08:03:08.058531+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30775","citing_title":"A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2506.21582","citing_title":"VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2506.12605","citing_title":"The Rise of AI Companions: Interaction with AI Companions and Psychological Well-being","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16453","citing_title":"Understanding the Challenges and Opportunities of Generative AI Apps: An Empirical Study","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18919","citing_title":"Proposing Topic Models and Evaluation Frameworks for Analyzing Associations with External Outcomes: An Application to Leadership Analysis Using Large-Scale Corporate Review Data","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07562","citing_title":"Reasoning-Based Refinement of Unsupervised Text Clusters with LLMs","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47Q4VG6RFOZNPJABPB73BZAQT4","json":"https://pith.science/pith/47Q4VG6RFOZNPJABPB73BZAQT4.json","graph_json":"https://pith.science/api/pith-number/47Q4VG6RFOZNPJABPB73BZAQT4/graph.json","events_json":"https://pith.science/api/pith-number/47Q4VG6RFOZNPJABPB73BZAQT4/events.json","paper":"https://pith.science/paper/47Q4VG6R"},"agent_actions":{"view_html":"https://pith.science/pith/47Q4VG6RFOZNPJABPB73BZAQT4","download_json":"https://pith.science/pith/47Q4VG6RFOZNPJABPB73BZAQT4.json","view_paper":"https://pith.science/paper/47Q4VG6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01449&json=true","fetch_graph":"https://pith.science/api/pith-number/47Q4VG6RFOZNPJABPB73BZAQT4/graph.json","fetch_events":"https://pith.science/api/pith-number/47Q4VG6RFOZNPJABPB73BZAQT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47Q4VG6RFOZNPJABPB73BZAQT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47Q4VG6RFOZNPJABPB73BZAQT4/action/storage_attestation","attest_author":"https://pith.science/pith/47Q4VG6RFOZNPJABPB73BZAQT4/action/author_attestation","sign_citation":"https://pith.science/pith/47Q4VG6RFOZNPJABPB73BZAQT4/action/citation_signature","submit_replication":"https://pith.science/pith/47Q4VG6RFOZNPJABPB73BZAQT4/action/replication_record"}},"created_at":"2026-07-05T08:03:08.058531+00:00","updated_at":"2026-07-05T08:03:08.058531+00:00"}