{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3RRQXYSRX4ZY2WMJKYY7WDFWRE","short_pith_number":"pith:3RRQXYSR","schema_version":"1.0","canonical_sha256":"dc630be251bf338d59895631fb0cb68936a3cccd7a39d764587d887c804e2e27","source":{"kind":"arxiv","id":"2410.00134","version":1},"attestation_state":"computed","paper":{"title":"Semantic-Driven Topic Modeling Using Transformer-Based Embeddings and Clustering Algorithms","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jugal Kalita, Melkamu Abay Mersha, Mesay Gemeda Yigezu","submitted_at":"2024-09-30T18:15:31Z","abstract_excerpt":"Topic modeling is a powerful technique to discover hidden topics and patterns within a collection of documents without prior knowledge. Traditional topic modeling and clustering-based techniques encounter challenges in capturing contextual semantic information. This study introduces an innovative end-to-end semantic-driven topic modeling technique for the topic extraction process, utilizing advanced word and document embeddings combined with a powerful clustering algorithm. This semantic-driven approach represents a significant advancement in topic modeling methodologies. It leverages contextu"},"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":"2410.00134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T18:15:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ccf8b22053207363b0440942274ff2957705894fa9eb42284f86c9998e74fbb3","abstract_canon_sha256":"72064e2039c9076cfcfb6e695be429d5f423328152cec32e806536811a978de4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:55.883238Z","signature_b64":"aCIiKcWukxMsvweGlM3nRmS6hMbD3jyuZAl1gP89NjiP11qqsybI3NzJxhrw/wu0TrZW4bj0SRrRB1XJLwpqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc630be251bf338d59895631fb0cb68936a3cccd7a39d764587d887c804e2e27","last_reissued_at":"2026-07-05T09:14:55.882794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:55.882794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic-Driven Topic Modeling Using Transformer-Based Embeddings and Clustering Algorithms","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jugal Kalita, Melkamu Abay Mersha, Mesay Gemeda Yigezu","submitted_at":"2024-09-30T18:15:31Z","abstract_excerpt":"Topic modeling is a powerful technique to discover hidden topics and patterns within a collection of documents without prior knowledge. Traditional topic modeling and clustering-based techniques encounter challenges in capturing contextual semantic information. This study introduces an innovative end-to-end semantic-driven topic modeling technique for the topic extraction process, utilizing advanced word and document embeddings combined with a powerful clustering algorithm. This semantic-driven approach represents a significant advancement in topic modeling methodologies. It leverages contextu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00134","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/2410.00134/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":"2410.00134","created_at":"2026-07-05T09:14:55.882856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00134v1","created_at":"2026-07-05T09:14:55.882856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00134","created_at":"2026-07-05T09:14:55.882856+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RRQXYSRX4ZY","created_at":"2026-07-05T09:14:55.882856+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RRQXYSRX4ZY2WMJ","created_at":"2026-07-05T09:14:55.882856+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RRQXYSR","created_at":"2026-07-05T09:14:55.882856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27610","citing_title":"Eliot: Interactively $\\underline{E}$xploring Fast-Changing Scientific $\\underline{Li}$terature Trends with $\\underline{O}$nline Da$\\underline{t}$a and Learning","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RRQXYSRX4ZY2WMJKYY7WDFWRE","json":"https://pith.science/pith/3RRQXYSRX4ZY2WMJKYY7WDFWRE.json","graph_json":"https://pith.science/api/pith-number/3RRQXYSRX4ZY2WMJKYY7WDFWRE/graph.json","events_json":"https://pith.science/api/pith-number/3RRQXYSRX4ZY2WMJKYY7WDFWRE/events.json","paper":"https://pith.science/paper/3RRQXYSR"},"agent_actions":{"view_html":"https://pith.science/pith/3RRQXYSRX4ZY2WMJKYY7WDFWRE","download_json":"https://pith.science/pith/3RRQXYSRX4ZY2WMJKYY7WDFWRE.json","view_paper":"https://pith.science/paper/3RRQXYSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00134&json=true","fetch_graph":"https://pith.science/api/pith-number/3RRQXYSRX4ZY2WMJKYY7WDFWRE/graph.json","fetch_events":"https://pith.science/api/pith-number/3RRQXYSRX4ZY2WMJKYY7WDFWRE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RRQXYSRX4ZY2WMJKYY7WDFWRE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RRQXYSRX4ZY2WMJKYY7WDFWRE/action/storage_attestation","attest_author":"https://pith.science/pith/3RRQXYSRX4ZY2WMJKYY7WDFWRE/action/author_attestation","sign_citation":"https://pith.science/pith/3RRQXYSRX4ZY2WMJKYY7WDFWRE/action/citation_signature","submit_replication":"https://pith.science/pith/3RRQXYSRX4ZY2WMJKYY7WDFWRE/action/replication_record"}},"created_at":"2026-07-05T09:14:55.882856+00:00","updated_at":"2026-07-05T09:14:55.882856+00:00"}