{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:ACQ6QDS6U2GVCO44WX5UNQ7NAY","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":"2705e00b0ac261b5bad1ace374d4d46986d0d205bc4f78dedc2b9d434a7035c7","cross_cats_sorted":["stat.OT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2014-09-25T21:03:00Z","title_canon_sha256":"d07c01047cac1a9c6a7c3c2058e12d9316208af510cb8c83b7445427d484459f"},"schema_version":"1.0","source":{"id":"1409.7419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.7419","created_at":"2026-05-18T02:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"1409.7419v1","created_at":"2026-05-18T02:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.7419","created_at":"2026-05-18T02:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"ACQ6QDS6U2GV","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"ACQ6QDS6U2GVCO44","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"ACQ6QDS6","created_at":"2026-05-18T12:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:fa3d40afa70ddfd577dce6012d0db34ef8ccead654a39d7905a8cb746b6e5f2c","target":"graph","created_at":"2026-05-18T02:41:52Z","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":"Research on cluster analysis for categorical data continues to develop, with new clustering algorithms being proposed. However, in this context, the determination of the number of clusters is rarely addressed. In this paper, we propose a new approach in which clustering of categorical data and the estimation of the number of clusters is carried out simultaneously. Assuming that the data originate from a finite mixture of multinomial distributions, we develop a method to select the number of mixture components based on a minimum message length (MML) criterion and implement a new expectation-max","authors_text":"Cl\\'audia Silvestre, Margarida G. M. S. Cardoso, M\\'ario A. T. Figueiredo","cross_cats":["stat.OT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2014-09-25T21:03:00Z","title":"Identifying the number of clusters in discrete mixture models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.7419","kind":"arxiv","version":1},"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":"sha256:0bae88e02e20b2ab1f2a240f2fcd4f87af347109e3f3aa7f23bc6f078d0792ed","target":"record","created_at":"2026-05-18T02:41:52Z","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":"2705e00b0ac261b5bad1ace374d4d46986d0d205bc4f78dedc2b9d434a7035c7","cross_cats_sorted":["stat.OT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2014-09-25T21:03:00Z","title_canon_sha256":"d07c01047cac1a9c6a7c3c2058e12d9316208af510cb8c83b7445427d484459f"},"schema_version":"1.0","source":{"id":"1409.7419","kind":"arxiv","version":1}},"canonical_sha256":"00a1e80e5ea68d513b9cb5fb46c3ed06385cd1520c7bd1b812fbe220e10ddb26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00a1e80e5ea68d513b9cb5fb46c3ed06385cd1520c7bd1b812fbe220e10ddb26","first_computed_at":"2026-05-18T02:41:52.722786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:41:52.722786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bIfXWI7Y/KbUs0V8kmU06XnB+frGomSHVgQHDzuUsFA5ka1xuats2KeueGsz60iW6U9ZyPcda9oSzwks1o/+DA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:41:52.723501Z","signed_message":"canonical_sha256_bytes"},"source_id":"1409.7419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bae88e02e20b2ab1f2a240f2fcd4f87af347109e3f3aa7f23bc6f078d0792ed","sha256:fa3d40afa70ddfd577dce6012d0db34ef8ccead654a39d7905a8cb746b6e5f2c"],"state_sha256":"991128057517aa03e94c1156c2be3c673e426b2e7824025b753e8709d0173a3c"}