{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YW4XCVNJHN35SKR6JMXRCIGTG6","short_pith_number":"pith:YW4XCVNJ","schema_version":"1.0","canonical_sha256":"c5b97155a93b77d92a3e4b2f1120d3378839fb4a7f5ac027c93f3b0848de82b6","source":{"kind":"arxiv","id":"2006.02954","version":1},"attestation_state":"computed","paper":{"title":"Handling missing data in model-based clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Alessio Serafini, Luca Scrucca, Thomas Brendan Murphy","submitted_at":"2020-06-04T15:36:31Z","abstract_excerpt":"Gaussian Mixture models (GMMs) are a powerful tool for clustering, classification and density estimation when clustering structures are embedded in the data. The presence of missing values can largely impact the GMMs estimation process, thus handling missing data turns out to be a crucial point in clustering, classification and density estimation. Several techniques have been developed to impute the missing values before model estimation. Among these, multiple imputation is a simple and useful general approach to handle missing data. In this paper we propose two different methods to fit Gaussi"},"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":"2006.02954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-04T15:36:31Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"c72b8a6abcd54bb9259a7780a0f6ed836700d09b6a206e74418669951a19689e","abstract_canon_sha256":"73c8a2ca2eec37f8a41f3adb30798fc1ef3b7058b593751491288d1e7dd5b991"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:01.931491Z","signature_b64":"nbdSbfo2GD5A+AnnbF9Bk4fAUwDqBmsGIB6lz19PNETgROtWHroSPljh0u1BQiNHhn54c2EUjsuyvKGMSQOcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5b97155a93b77d92a3e4b2f1120d3378839fb4a7f5ac027c93f3b0848de82b6","last_reissued_at":"2026-07-05T01:08:01.931014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:01.931014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Handling missing data in model-based clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Alessio Serafini, Luca Scrucca, Thomas Brendan Murphy","submitted_at":"2020-06-04T15:36:31Z","abstract_excerpt":"Gaussian Mixture models (GMMs) are a powerful tool for clustering, classification and density estimation when clustering structures are embedded in the data. The presence of missing values can largely impact the GMMs estimation process, thus handling missing data turns out to be a crucial point in clustering, classification and density estimation. Several techniques have been developed to impute the missing values before model estimation. Among these, multiple imputation is a simple and useful general approach to handle missing data. In this paper we propose two different methods to fit Gaussi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.02954","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/2006.02954/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":"2006.02954","created_at":"2026-07-05T01:08:01.931071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.02954v1","created_at":"2026-07-05T01:08:01.931071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.02954","created_at":"2026-07-05T01:08:01.931071+00:00"},{"alias_kind":"pith_short_12","alias_value":"YW4XCVNJHN35","created_at":"2026-07-05T01:08:01.931071+00:00"},{"alias_kind":"pith_short_16","alias_value":"YW4XCVNJHN35SKR6","created_at":"2026-07-05T01:08:01.931071+00:00"},{"alias_kind":"pith_short_8","alias_value":"YW4XCVNJ","created_at":"2026-07-05T01:08:01.931071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.03083","citing_title":"Causal K-Means Clustering","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YW4XCVNJHN35SKR6JMXRCIGTG6","json":"https://pith.science/pith/YW4XCVNJHN35SKR6JMXRCIGTG6.json","graph_json":"https://pith.science/api/pith-number/YW4XCVNJHN35SKR6JMXRCIGTG6/graph.json","events_json":"https://pith.science/api/pith-number/YW4XCVNJHN35SKR6JMXRCIGTG6/events.json","paper":"https://pith.science/paper/YW4XCVNJ"},"agent_actions":{"view_html":"https://pith.science/pith/YW4XCVNJHN35SKR6JMXRCIGTG6","download_json":"https://pith.science/pith/YW4XCVNJHN35SKR6JMXRCIGTG6.json","view_paper":"https://pith.science/paper/YW4XCVNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.02954&json=true","fetch_graph":"https://pith.science/api/pith-number/YW4XCVNJHN35SKR6JMXRCIGTG6/graph.json","fetch_events":"https://pith.science/api/pith-number/YW4XCVNJHN35SKR6JMXRCIGTG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YW4XCVNJHN35SKR6JMXRCIGTG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YW4XCVNJHN35SKR6JMXRCIGTG6/action/storage_attestation","attest_author":"https://pith.science/pith/YW4XCVNJHN35SKR6JMXRCIGTG6/action/author_attestation","sign_citation":"https://pith.science/pith/YW4XCVNJHN35SKR6JMXRCIGTG6/action/citation_signature","submit_replication":"https://pith.science/pith/YW4XCVNJHN35SKR6JMXRCIGTG6/action/replication_record"}},"created_at":"2026-07-05T01:08:01.931071+00:00","updated_at":"2026-07-05T01:08:01.931071+00:00"}