{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JHGKPZ55AVINHMTL2EP7DYOEFF","short_pith_number":"pith:JHGKPZ55","schema_version":"1.0","canonical_sha256":"49cca7e7bd0550d3b26bd11ff1e1c42959c83781f221f97b45d655b45a8f7628","source":{"kind":"arxiv","id":"2312.09693","version":1},"attestation_state":"computed","paper":{"title":"Prompting Large Language Models for Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Han Wang, Ming Shan Hee, Nguyen Khoi Hoang, Nirmalendu Prakash, Roy Ka-Wei Lee, Usman Naseem","submitted_at":"2023-12-15T11:15:05Z","abstract_excerpt":"Topic modeling is a widely used technique for revealing underlying thematic structures within textual data. However, existing models have certain limitations, particularly when dealing with short text datasets that lack co-occurring words. Moreover, these models often neglect sentence-level semantics, focusing primarily on token-level semantics. In this paper, we propose PromptTopic, a novel topic modeling approach that harnesses the advanced language understanding of large language models (LLMs) to address these challenges. It involves extracting topics at the sentence level from individual d"},"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":"2312.09693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-15T11:15:05Z","cross_cats_sorted":[],"title_canon_sha256":"89a949153b241ebba5d7154d99731aa8f722c05a288ef35bcb5442b811066f59","abstract_canon_sha256":"3cadb5b3d71e0ed46645372e18b726085dfa34b0bdbafc3083ef2d29ca392dfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:29.444744Z","signature_b64":"npWzyLxJrCimKLS8b8Ua6A7J9lscFfHGmOJN9qfbxW9VIFzYD6OskiqrGn6Smz1xA8YMYB7rJ4oVD534nc49Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49cca7e7bd0550d3b26bd11ff1e1c42959c83781f221f97b45d655b45a8f7628","last_reissued_at":"2026-07-05T07:24:29.444253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:29.444253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompting Large Language Models for Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Han Wang, Ming Shan Hee, Nguyen Khoi Hoang, Nirmalendu Prakash, Roy Ka-Wei Lee, Usman Naseem","submitted_at":"2023-12-15T11:15:05Z","abstract_excerpt":"Topic modeling is a widely used technique for revealing underlying thematic structures within textual data. However, existing models have certain limitations, particularly when dealing with short text datasets that lack co-occurring words. Moreover, these models often neglect sentence-level semantics, focusing primarily on token-level semantics. In this paper, we propose PromptTopic, a novel topic modeling approach that harnesses the advanced language understanding of large language models (LLMs) to address these challenges. It involves extracting topics at the sentence level from individual d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09693","kind":"arxiv","version":1},"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/2312.09693/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":"2312.09693","created_at":"2026-07-05T07:24:29.444308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09693v1","created_at":"2026-07-05T07:24:29.444308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09693","created_at":"2026-07-05T07:24:29.444308+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHGKPZ55AVIN","created_at":"2026-07-05T07:24:29.444308+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHGKPZ55AVINHMTL","created_at":"2026-07-05T07:24:29.444308+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHGKPZ55","created_at":"2026-07-05T07:24:29.444308+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/JHGKPZ55AVINHMTL2EP7DYOEFF","json":"https://pith.science/pith/JHGKPZ55AVINHMTL2EP7DYOEFF.json","graph_json":"https://pith.science/api/pith-number/JHGKPZ55AVINHMTL2EP7DYOEFF/graph.json","events_json":"https://pith.science/api/pith-number/JHGKPZ55AVINHMTL2EP7DYOEFF/events.json","paper":"https://pith.science/paper/JHGKPZ55"},"agent_actions":{"view_html":"https://pith.science/pith/JHGKPZ55AVINHMTL2EP7DYOEFF","download_json":"https://pith.science/pith/JHGKPZ55AVINHMTL2EP7DYOEFF.json","view_paper":"https://pith.science/paper/JHGKPZ55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09693&json=true","fetch_graph":"https://pith.science/api/pith-number/JHGKPZ55AVINHMTL2EP7DYOEFF/graph.json","fetch_events":"https://pith.science/api/pith-number/JHGKPZ55AVINHMTL2EP7DYOEFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHGKPZ55AVINHMTL2EP7DYOEFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHGKPZ55AVINHMTL2EP7DYOEFF/action/storage_attestation","attest_author":"https://pith.science/pith/JHGKPZ55AVINHMTL2EP7DYOEFF/action/author_attestation","sign_citation":"https://pith.science/pith/JHGKPZ55AVINHMTL2EP7DYOEFF/action/citation_signature","submit_replication":"https://pith.science/pith/JHGKPZ55AVINHMTL2EP7DYOEFF/action/replication_record"}},"created_at":"2026-07-05T07:24:29.444308+00:00","updated_at":"2026-07-05T07:24:29.444308+00:00"}