{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:R4MZT466Z2LTY26P4WVQINASCP","short_pith_number":"pith:R4MZT466","schema_version":"1.0","canonical_sha256":"8f1999f3dece973c6bcfe5ab04341213d19bc9deab06e529a2bc3a1903866da6","source":{"kind":"arxiv","id":"1205.1053","version":1},"attestation_state":"computed","paper":{"title":"Variable Selection for Latent Dirichlet Allocation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alice Oh, Dongwoo Kim, Yeonseung Chung","submitted_at":"2012-05-04T03:14:18Z","abstract_excerpt":"In latent Dirichlet allocation (LDA), topics are multinomial distributions over the entire vocabulary. However, the vocabulary usually contains many words that are not relevant in forming the topics. We adopt a variable selection method widely used in statistical modeling as a dimension reduction tool and combine it with LDA. In this variable selection model for LDA (vsLDA), topics are multinomial distributions over a subset of the vocabulary, and by excluding words that are not informative for finding the latent topic structure of the corpus, vsLDA finds topics that are more robust and discri"},"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":"1205.1053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-04T03:14:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"740659d43fbfa01aa92d516a05b63ace5a3f06f03affec054e9f9c9f6e11f074","abstract_canon_sha256":"864bc81a5918d7201cdf2fc8e3caef292babe019ac0917e6bc9ed61482c28985"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:56:12.247890Z","signature_b64":"e2M23FMvO/y4hzge7GR5ogTkKxWYl5FEjVTKOu+Y0hioTPJZw/9jSMSXimFY4pwuWjOE2wuC1O1sGU2lE83kAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f1999f3dece973c6bcfe5ab04341213d19bc9deab06e529a2bc3a1903866da6","last_reissued_at":"2026-05-18T03:56:12.247373Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:56:12.247373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variable Selection for Latent Dirichlet Allocation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alice Oh, Dongwoo Kim, Yeonseung Chung","submitted_at":"2012-05-04T03:14:18Z","abstract_excerpt":"In latent Dirichlet allocation (LDA), topics are multinomial distributions over the entire vocabulary. However, the vocabulary usually contains many words that are not relevant in forming the topics. We adopt a variable selection method widely used in statistical modeling as a dimension reduction tool and combine it with LDA. In this variable selection model for LDA (vsLDA), topics are multinomial distributions over a subset of the vocabulary, and by excluding words that are not informative for finding the latent topic structure of the corpus, vsLDA finds topics that are more robust and discri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.1053","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":""},"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":"1205.1053","created_at":"2026-05-18T03:56:12.247467+00:00"},{"alias_kind":"arxiv_version","alias_value":"1205.1053v1","created_at":"2026-05-18T03:56:12.247467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.1053","created_at":"2026-05-18T03:56:12.247467+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4MZT466Z2LT","created_at":"2026-05-18T12:27:20.899486+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4MZT466Z2LTY26P","created_at":"2026-05-18T12:27:20.899486+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4MZT466","created_at":"2026-05-18T12:27:20.899486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15984","citing_title":"Rigidity of self-maps of $V_{n,2}$ and classification of manifolds tangentially homotopy equivalent to $V_{n,2} \\times S^k$","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP","json":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP.json","graph_json":"https://pith.science/api/pith-number/R4MZT466Z2LTY26P4WVQINASCP/graph.json","events_json":"https://pith.science/api/pith-number/R4MZT466Z2LTY26P4WVQINASCP/events.json","paper":"https://pith.science/paper/R4MZT466"},"agent_actions":{"view_html":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP","download_json":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP.json","view_paper":"https://pith.science/paper/R4MZT466","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1205.1053&json=true","fetch_graph":"https://pith.science/api/pith-number/R4MZT466Z2LTY26P4WVQINASCP/graph.json","fetch_events":"https://pith.science/api/pith-number/R4MZT466Z2LTY26P4WVQINASCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP/action/storage_attestation","attest_author":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP/action/author_attestation","sign_citation":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP/action/citation_signature","submit_replication":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP/action/replication_record"}},"created_at":"2026-05-18T03:56:12.247467+00:00","updated_at":"2026-05-18T03:56:12.247467+00:00"}