{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4T76F2LUUAIHPXCPXOB4T55IAJ","short_pith_number":"pith:4T76F2LU","schema_version":"1.0","canonical_sha256":"e4ffe2e974a01077dc4fbb83c9f7a802457ece31ec318569079e153a8e1cbd4f","source":{"kind":"arxiv","id":"2306.04217","version":1},"attestation_state":"computed","paper":{"title":"Effective Neural Topic Modeling with Embedding Clustering Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Thong Nguyen, Xiaobao Wu, Xinshuai Dong","submitted_at":"2023-06-07T07:45:38Z","abstract_excerpt":"Topic models have been prevalent for decades with various applications. However, existing topic models commonly suffer from the notorious topic collapsing: discovered topics semantically collapse towards each other, leading to highly repetitive topics, insufficient topic discovery, and damaged model interpretability. In this paper, we propose a new neural topic model, Embedding Clustering Regularization Topic Model (ECRTM). Besides the existing reconstruction error, we propose a novel Embedding Clustering Regularization (ECR), which forces each topic embedding to be the center of a separately "},"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":"2306.04217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T07:45:38Z","cross_cats_sorted":[],"title_canon_sha256":"a618267b21024e6e93fc84e07966ca5cf10ac0386f3af68f19deaaf39ee56d4e","abstract_canon_sha256":"cacd01747257e1bb2b498e0af96efd33295c649a30d6c557e5006ade579b32c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:27.219018Z","signature_b64":"UVmuWyLZ3XWTy/E+P8Ofkehrd6uf5BECgGZUja0U4GIIjoZQf5sNMDLkIjGSI7rcgoyc4fD4KiN8Lw5ofkm0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4ffe2e974a01077dc4fbb83c9f7a802457ece31ec318569079e153a8e1cbd4f","last_reissued_at":"2026-07-05T06:18:27.218494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:27.218494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Neural Topic Modeling with Embedding Clustering Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Thong Nguyen, Xiaobao Wu, Xinshuai Dong","submitted_at":"2023-06-07T07:45:38Z","abstract_excerpt":"Topic models have been prevalent for decades with various applications. However, existing topic models commonly suffer from the notorious topic collapsing: discovered topics semantically collapse towards each other, leading to highly repetitive topics, insufficient topic discovery, and damaged model interpretability. In this paper, we propose a new neural topic model, Embedding Clustering Regularization Topic Model (ECRTM). Besides the existing reconstruction error, we propose a novel Embedding Clustering Regularization (ECR), which forces each topic embedding to be the center of a separately "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04217","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/2306.04217/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":"2306.04217","created_at":"2026-07-05T06:18:27.218554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04217v1","created_at":"2026-07-05T06:18:27.218554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04217","created_at":"2026-07-05T06:18:27.218554+00:00"},{"alias_kind":"pith_short_12","alias_value":"4T76F2LUUAIH","created_at":"2026-07-05T06:18:27.218554+00:00"},{"alias_kind":"pith_short_16","alias_value":"4T76F2LUUAIHPXCP","created_at":"2026-07-05T06:18:27.218554+00:00"},{"alias_kind":"pith_short_8","alias_value":"4T76F2LU","created_at":"2026-07-05T06:18:27.218554+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/4T76F2LUUAIHPXCPXOB4T55IAJ","json":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ.json","graph_json":"https://pith.science/api/pith-number/4T76F2LUUAIHPXCPXOB4T55IAJ/graph.json","events_json":"https://pith.science/api/pith-number/4T76F2LUUAIHPXCPXOB4T55IAJ/events.json","paper":"https://pith.science/paper/4T76F2LU"},"agent_actions":{"view_html":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ","download_json":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ.json","view_paper":"https://pith.science/paper/4T76F2LU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04217&json=true","fetch_graph":"https://pith.science/api/pith-number/4T76F2LUUAIHPXCPXOB4T55IAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4T76F2LUUAIHPXCPXOB4T55IAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/action/storage_attestation","attest_author":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/action/author_attestation","sign_citation":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/action/citation_signature","submit_replication":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/action/replication_record"}},"created_at":"2026-07-05T06:18:27.218554+00:00","updated_at":"2026-07-05T06:18:27.218554+00:00"}