{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LYOHMXHWPKVNORP7AWQBURQPHA","short_pith_number":"pith:LYOHMXHW","schema_version":"1.0","canonical_sha256":"5e1c765cf67aaad745ff05a01a460f381999a33195b28b3432d9af4e0504ce16","source":{"kind":"arxiv","id":"1905.09959","version":2},"attestation_state":"computed","paper":{"title":"Posterior Distribution for the Number of Clusters in Dirichlet Process Mixture Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Chiao-Yu Yang, Eric Xia, Michael I. Jordan, Nhat Ho","submitted_at":"2019-05-23T22:51:15Z","abstract_excerpt":"Dirichlet process mixture models (DPMM) play a central role in Bayesian nonparametrics, with applications throughout statistics and machine learning. DPMMs are generally used in clustering problems where the number of clusters is not known in advance, and the posterior distribution is treated as providing inference for this number. Recently, however, it has been shown that the DPMM is inconsistent in inferring the true number of components in certain cases. This is an asymptotic result, and it would be desirable to understand whether it holds with finite samples, and to more fully understand t"},"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":"1905.09959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-23T22:51:15Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"799a5affd7cda3682e59f0e787a82768def84053a2ffee6e6d79d9ec5a2ea7c4","abstract_canon_sha256":"07f85f1320ef038d442bf534be048dcf22e57a52e5617fe0fcee30efc63d950a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:54.486101Z","signature_b64":"g3/Pv7wluWLL4r1nAfcHa9n+18H6qFfUnu3V+k2JAoDpb2IfJ49/OIAToAvvob5rWBl+iDVezNr3Xp5OIZ1iCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e1c765cf67aaad745ff05a01a460f381999a33195b28b3432d9af4e0504ce16","last_reissued_at":"2026-07-05T01:43:54.485615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:54.485615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Posterior Distribution for the Number of Clusters in Dirichlet Process Mixture Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Chiao-Yu Yang, Eric Xia, Michael I. Jordan, Nhat Ho","submitted_at":"2019-05-23T22:51:15Z","abstract_excerpt":"Dirichlet process mixture models (DPMM) play a central role in Bayesian nonparametrics, with applications throughout statistics and machine learning. DPMMs are generally used in clustering problems where the number of clusters is not known in advance, and the posterior distribution is treated as providing inference for this number. Recently, however, it has been shown that the DPMM is inconsistent in inferring the true number of components in certain cases. This is an asymptotic result, and it would be desirable to understand whether it holds with finite samples, and to more fully understand t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09959","kind":"arxiv","version":2},"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/1905.09959/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":"1905.09959","created_at":"2026-07-05T01:43:54.485677+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09959v2","created_at":"2026-07-05T01:43:54.485677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09959","created_at":"2026-07-05T01:43:54.485677+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYOHMXHWPKVN","created_at":"2026-07-05T01:43:54.485677+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYOHMXHWPKVNORP7","created_at":"2026-07-05T01:43:54.485677+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYOHMXHW","created_at":"2026-07-05T01:43:54.485677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12305","citing_title":"Bayesian nonparametric Mallows model for clustering preference data","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYOHMXHWPKVNORP7AWQBURQPHA","json":"https://pith.science/pith/LYOHMXHWPKVNORP7AWQBURQPHA.json","graph_json":"https://pith.science/api/pith-number/LYOHMXHWPKVNORP7AWQBURQPHA/graph.json","events_json":"https://pith.science/api/pith-number/LYOHMXHWPKVNORP7AWQBURQPHA/events.json","paper":"https://pith.science/paper/LYOHMXHW"},"agent_actions":{"view_html":"https://pith.science/pith/LYOHMXHWPKVNORP7AWQBURQPHA","download_json":"https://pith.science/pith/LYOHMXHWPKVNORP7AWQBURQPHA.json","view_paper":"https://pith.science/paper/LYOHMXHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09959&json=true","fetch_graph":"https://pith.science/api/pith-number/LYOHMXHWPKVNORP7AWQBURQPHA/graph.json","fetch_events":"https://pith.science/api/pith-number/LYOHMXHWPKVNORP7AWQBURQPHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYOHMXHWPKVNORP7AWQBURQPHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYOHMXHWPKVNORP7AWQBURQPHA/action/storage_attestation","attest_author":"https://pith.science/pith/LYOHMXHWPKVNORP7AWQBURQPHA/action/author_attestation","sign_citation":"https://pith.science/pith/LYOHMXHWPKVNORP7AWQBURQPHA/action/citation_signature","submit_replication":"https://pith.science/pith/LYOHMXHWPKVNORP7AWQBURQPHA/action/replication_record"}},"created_at":"2026-07-05T01:43:54.485677+00:00","updated_at":"2026-07-05T01:43:54.485677+00:00"}