{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:IFSHLJNHCFO6C47AI4Q5FETAR4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b990d1c9e69eca632e088c337f186dd33d4352043aca27710b73a6c5ab7aba84","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2010-02-05T07:40:26Z","title_canon_sha256":"cbe7e572fd2fef1b7cbde14b72492bb69e168136d7a03149d7ae49e8032c2678"},"schema_version":"1.0","source":{"id":"1002.1142","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1002.1142","created_at":"2026-05-18T02:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"1002.1142v3","created_at":"2026-05-18T02:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1002.1142","created_at":"2026-05-18T02:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"IFSHLJNHCFO6","created_at":"2026-05-18T12:26:09Z"},{"alias_kind":"pith_short_16","alias_value":"IFSHLJNHCFO6C47A","created_at":"2026-05-18T12:26:09Z"},{"alias_kind":"pith_short_8","alias_value":"IFSHLJNH","created_at":"2026-05-18T12:26:09Z"}],"graph_snapshots":[{"event_id":"sha256:426876bb686fce3ead9045ce3c4291c8877216f7ee0e3f25bd64e1820dced2aa","target":"graph","created_at":"2026-05-18T02:56:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Dominique Bontemps (IMT), Wilson Toussile","cross_cats":["stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2010-02-05T07:40:26Z","title":"Clustering and variable selection for categorical multivariate data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1002.1142","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2031a05c8e78e69f591b7981a523484e4ed9d5ccbd0a7e14004935a422cce9ea","target":"record","created_at":"2026-05-18T02:56:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b990d1c9e69eca632e088c337f186dd33d4352043aca27710b73a6c5ab7aba84","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2010-02-05T07:40:26Z","title_canon_sha256":"cbe7e572fd2fef1b7cbde14b72492bb69e168136d7a03149d7ae49e8032c2678"},"schema_version":"1.0","source":{"id":"1002.1142","kind":"arxiv","version":3}},"canonical_sha256":"416475a5a7115de173e04721d292608f0f6cf508ddd9b52ee0bd55d2a71fd15e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"416475a5a7115de173e04721d292608f0f6cf508ddd9b52ee0bd55d2a71fd15e","first_computed_at":"2026-05-18T02:56:52.360299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:56:52.360299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nP+ubMr38t3ZTZ1ccy4urJDt4l40CgtoRWrGK2X7V6jlleyV7WvHevpcOUk/AgBeb9FW4DEUL+kAjyKjYTimDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:56:52.360746Z","signed_message":"canonical_sha256_bytes"},"source_id":"1002.1142","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2031a05c8e78e69f591b7981a523484e4ed9d5ccbd0a7e14004935a422cce9ea","sha256:426876bb686fce3ead9045ce3c4291c8877216f7ee0e3f25bd64e1820dced2aa"],"state_sha256":"bc306c3472a549dbac11e5c453d11ea073d8d99f88d0271cf5534a066168683c"}