{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V5APF6GASDR526QYLBZRI4GRVZ","short_pith_number":"pith:V5APF6GA","schema_version":"1.0","canonical_sha256":"af40f2f8c090e3dd7a1858731470d1ae46aa8da46b8d7c302b3ee01ee762c7cf","source":{"kind":"arxiv","id":"2403.16248","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models Offer an Alternative to the Traditional Approach of Topic Modelling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chun Dong, Kalina Bontcheva, Xingyi Song, Yida Mu","submitted_at":"2024-03-24T17:39:51Z","abstract_excerpt":"Topic modelling, as a well-established unsupervised technique, has found extensive use in automatically detecting significant topics within a corpus of documents. However, classic topic modelling approaches (e.g., LDA) have certain drawbacks, such as the lack of semantic understanding and the presence of overlapping topics. In this work, we investigate the untapped potential of large language models (LLMs) as an alternative for uncovering the underlying topics within extensive text corpora. To this end, we introduce a framework that prompts LLMs to generate topics from a given set of documents"},"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":"2403.16248","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-24T17:39:51Z","cross_cats_sorted":[],"title_canon_sha256":"3bd83aeb5bd8959dd2969747987b59ac1b7002ed07e98041902b3586c51b4800","abstract_canon_sha256":"054be43610b8b43296ef9e7f9a9a7e19e56e2e5224c303ffc55b44dece379f41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:43.564750Z","signature_b64":"+P/4+QtTdCymK+6oWQQ5Jcdom09U5/9dhZnPURx0ZEuADV+yEnXpIhAqcTrxO2W3eeAeiY73Jq1fpz56xNKuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af40f2f8c090e3dd7a1858731470d1ae46aa8da46b8d7c302b3ee01ee762c7cf","last_reissued_at":"2026-07-05T08:00:43.564337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:43.564337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Offer an Alternative to the Traditional Approach of Topic Modelling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chun Dong, Kalina Bontcheva, Xingyi Song, Yida Mu","submitted_at":"2024-03-24T17:39:51Z","abstract_excerpt":"Topic modelling, as a well-established unsupervised technique, has found extensive use in automatically detecting significant topics within a corpus of documents. However, classic topic modelling approaches (e.g., LDA) have certain drawbacks, such as the lack of semantic understanding and the presence of overlapping topics. In this work, we investigate the untapped potential of large language models (LLMs) as an alternative for uncovering the underlying topics within extensive text corpora. To this end, we introduce a framework that prompts LLMs to generate topics from a given set of documents"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16248","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/2403.16248/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":"2403.16248","created_at":"2026-07-05T08:00:43.564395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16248v2","created_at":"2026-07-05T08:00:43.564395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16248","created_at":"2026-07-05T08:00:43.564395+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5APF6GASDR5","created_at":"2026-07-05T08:00:43.564395+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5APF6GASDR526QY","created_at":"2026-07-05T08:00:43.564395+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5APF6GA","created_at":"2026-07-05T08:00:43.564395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00118","citing_title":"An Empirical Study on Logging Evolution On Stack Overflow: Trends, Topics, and Challenges","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15139","citing_title":"Investigating Notable Metadata Practices in PyPI Libraries: An Empirical Study about Repository and Donation Platform URLs","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18955","citing_title":"Assessing Capabilities of Large Language Models in Social Media Analytics: A Multi-task Quest","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V5APF6GASDR526QYLBZRI4GRVZ","json":"https://pith.science/pith/V5APF6GASDR526QYLBZRI4GRVZ.json","graph_json":"https://pith.science/api/pith-number/V5APF6GASDR526QYLBZRI4GRVZ/graph.json","events_json":"https://pith.science/api/pith-number/V5APF6GASDR526QYLBZRI4GRVZ/events.json","paper":"https://pith.science/paper/V5APF6GA"},"agent_actions":{"view_html":"https://pith.science/pith/V5APF6GASDR526QYLBZRI4GRVZ","download_json":"https://pith.science/pith/V5APF6GASDR526QYLBZRI4GRVZ.json","view_paper":"https://pith.science/paper/V5APF6GA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16248&json=true","fetch_graph":"https://pith.science/api/pith-number/V5APF6GASDR526QYLBZRI4GRVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/V5APF6GASDR526QYLBZRI4GRVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5APF6GASDR526QYLBZRI4GRVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5APF6GASDR526QYLBZRI4GRVZ/action/storage_attestation","attest_author":"https://pith.science/pith/V5APF6GASDR526QYLBZRI4GRVZ/action/author_attestation","sign_citation":"https://pith.science/pith/V5APF6GASDR526QYLBZRI4GRVZ/action/citation_signature","submit_replication":"https://pith.science/pith/V5APF6GASDR526QYLBZRI4GRVZ/action/replication_record"}},"created_at":"2026-07-05T08:00:43.564395+00:00","updated_at":"2026-07-05T08:00:43.564395+00:00"}