{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:IFSHLJNHCFO6C47AI4Q5FETAR4","short_pith_number":"pith:IFSHLJNH","schema_version":"1.0","canonical_sha256":"416475a5a7115de173e04721d292608f0f6cf508ddd9b52ee0bd55d2a71fd15e","source":{"kind":"arxiv","id":"1002.1142","version":3},"attestation_state":"computed","paper":{"title":"Clustering and variable selection for categorical multivariate data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Dominique Bontemps (IMT), Wilson Toussile","submitted_at":"2010-02-05T07:40:26Z","abstract_excerpt":"This article investigates unsupervised classification techniques for categorical multivariate data. The study employs multivariate multinomial mixture modeling, which is a type of model particularly applicable to multilocus genotypic data. A model selection procedure is used to simultaneously select the number of components and the relevant variables. A non-asymptotic oracle inequality is obtained, leading to the proposal of a new penalized maximum likelihood criterion. The selected model proves to be asymptotically consistent under weak assumptions on the true probability underlying the obser"},"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":"1002.1142","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2010-02-05T07:40:26Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"cbe7e572fd2fef1b7cbde14b72492bb69e168136d7a03149d7ae49e8032c2678","abstract_canon_sha256":"b990d1c9e69eca632e088c337f186dd33d4352043aca27710b73a6c5ab7aba84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:56:52.360746Z","signature_b64":"nP+ubMr38t3ZTZ1ccy4urJDt4l40CgtoRWrGK2X7V6jlleyV7WvHevpcOUk/AgBeb9FW4DEUL+kAjyKjYTimDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"416475a5a7115de173e04721d292608f0f6cf508ddd9b52ee0bd55d2a71fd15e","last_reissued_at":"2026-05-18T02:56:52.360299Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:56:52.360299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustering and variable selection for categorical multivariate data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Dominique Bontemps (IMT), Wilson Toussile","submitted_at":"2010-02-05T07:40:26Z","abstract_excerpt":"This article investigates unsupervised classification techniques for categorical multivariate data. The study employs multivariate multinomial mixture modeling, which is a type of model particularly applicable to multilocus genotypic data. A model selection procedure is used to simultaneously select the number of components and the relevant variables. A non-asymptotic oracle inequality is obtained, leading to the proposal of a new penalized maximum likelihood criterion. The selected model proves to be asymptotically consistent under weak assumptions on the true probability underlying the obser"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1002.1142","kind":"arxiv","version":3},"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":"1002.1142","created_at":"2026-05-18T02:56:52.360369+00:00"},{"alias_kind":"arxiv_version","alias_value":"1002.1142v3","created_at":"2026-05-18T02:56:52.360369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1002.1142","created_at":"2026-05-18T02:56:52.360369+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFSHLJNHCFO6","created_at":"2026-05-18T12:26:09.077623+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFSHLJNHCFO6C47A","created_at":"2026-05-18T12:26:09.077623+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFSHLJNH","created_at":"2026-05-18T12:26:09.077623+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/IFSHLJNHCFO6C47AI4Q5FETAR4","json":"https://pith.science/pith/IFSHLJNHCFO6C47AI4Q5FETAR4.json","graph_json":"https://pith.science/api/pith-number/IFSHLJNHCFO6C47AI4Q5FETAR4/graph.json","events_json":"https://pith.science/api/pith-number/IFSHLJNHCFO6C47AI4Q5FETAR4/events.json","paper":"https://pith.science/paper/IFSHLJNH"},"agent_actions":{"view_html":"https://pith.science/pith/IFSHLJNHCFO6C47AI4Q5FETAR4","download_json":"https://pith.science/pith/IFSHLJNHCFO6C47AI4Q5FETAR4.json","view_paper":"https://pith.science/paper/IFSHLJNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1002.1142&json=true","fetch_graph":"https://pith.science/api/pith-number/IFSHLJNHCFO6C47AI4Q5FETAR4/graph.json","fetch_events":"https://pith.science/api/pith-number/IFSHLJNHCFO6C47AI4Q5FETAR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFSHLJNHCFO6C47AI4Q5FETAR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFSHLJNHCFO6C47AI4Q5FETAR4/action/storage_attestation","attest_author":"https://pith.science/pith/IFSHLJNHCFO6C47AI4Q5FETAR4/action/author_attestation","sign_citation":"https://pith.science/pith/IFSHLJNHCFO6C47AI4Q5FETAR4/action/citation_signature","submit_replication":"https://pith.science/pith/IFSHLJNHCFO6C47AI4Q5FETAR4/action/replication_record"}},"created_at":"2026-05-18T02:56:52.360369+00:00","updated_at":"2026-05-18T02:56:52.360369+00:00"}