{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6LZNJ4IWAROV47EVEL6ILCSAXA","short_pith_number":"pith:6LZNJ4IW","schema_version":"1.0","canonical_sha256":"f2f2d4f116045d5e7c9522fc858a40b83f9d9adec26b740081cf74ac0da74816","source":{"kind":"arxiv","id":"2507.06226","version":1},"attestation_state":"computed","paper":{"title":"Consistency and Inconsistency in $K$-Means Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Adam Quinn Jaffe, Mo\\\"ise Blanchard, Nikita Zhivotovskiy","submitted_at":"2025-07-08T17:59:02Z","abstract_excerpt":"A celebrated result of Pollard proves asymptotic consistency for $k$-means clustering when the population distribution has finite variance. In this work, we point out that the population-level $k$-means clustering problem is, in fact, well-posed under the weaker assumption of a finite expectation, and we investigate whether some form of asymptotic consistency holds in this setting. As we illustrate in a variety of negative results, the complete story is quite subtle; for example, the empirical $k$-means cluster centers may fail to converge even if there exists a unique set of population $k$-me"},"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":"2507.06226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-07-08T17:59:02Z","cross_cats_sorted":["math.PR","stat.ML","stat.TH"],"title_canon_sha256":"547f7f7d6f376aa35de7da9fb53b9769261afcdf974a99de855797333eeff82b","abstract_canon_sha256":"94bbbb7bc03d30cff076b421b3b300b2734dc8eb6cf592ce0ed3f38cdcaeae39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:54.593358Z","signature_b64":"LXXrKdnqwxrCi3+kgFTt5dzgnk7LyYj6N1Q0nHbm9tAszFtABjef81Bzu+0ebYNZGVsS1XXc4TuQggAoBk+6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2f2d4f116045d5e7c9522fc858a40b83f9d9adec26b740081cf74ac0da74816","last_reissued_at":"2026-07-05T11:33:54.592874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:54.592874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistency and Inconsistency in $K$-Means Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Adam Quinn Jaffe, Mo\\\"ise Blanchard, Nikita Zhivotovskiy","submitted_at":"2025-07-08T17:59:02Z","abstract_excerpt":"A celebrated result of Pollard proves asymptotic consistency for $k$-means clustering when the population distribution has finite variance. In this work, we point out that the population-level $k$-means clustering problem is, in fact, well-posed under the weaker assumption of a finite expectation, and we investigate whether some form of asymptotic consistency holds in this setting. As we illustrate in a variety of negative results, the complete story is quite subtle; for example, the empirical $k$-means cluster centers may fail to converge even if there exists a unique set of population $k$-me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06226","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/2507.06226/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":"2507.06226","created_at":"2026-07-05T11:33:54.592932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06226v1","created_at":"2026-07-05T11:33:54.592932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06226","created_at":"2026-07-05T11:33:54.592932+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LZNJ4IWAROV","created_at":"2026-07-05T11:33:54.592932+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LZNJ4IWAROV47EV","created_at":"2026-07-05T11:33:54.592932+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LZNJ4IW","created_at":"2026-07-05T11:33:54.592932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01602","citing_title":"Estimating Mutual Information between Time Series and Temporal Event Sequences Across Diverse Analysis Tasks","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LZNJ4IWAROV47EVEL6ILCSAXA","json":"https://pith.science/pith/6LZNJ4IWAROV47EVEL6ILCSAXA.json","graph_json":"https://pith.science/api/pith-number/6LZNJ4IWAROV47EVEL6ILCSAXA/graph.json","events_json":"https://pith.science/api/pith-number/6LZNJ4IWAROV47EVEL6ILCSAXA/events.json","paper":"https://pith.science/paper/6LZNJ4IW"},"agent_actions":{"view_html":"https://pith.science/pith/6LZNJ4IWAROV47EVEL6ILCSAXA","download_json":"https://pith.science/pith/6LZNJ4IWAROV47EVEL6ILCSAXA.json","view_paper":"https://pith.science/paper/6LZNJ4IW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06226&json=true","fetch_graph":"https://pith.science/api/pith-number/6LZNJ4IWAROV47EVEL6ILCSAXA/graph.json","fetch_events":"https://pith.science/api/pith-number/6LZNJ4IWAROV47EVEL6ILCSAXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LZNJ4IWAROV47EVEL6ILCSAXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LZNJ4IWAROV47EVEL6ILCSAXA/action/storage_attestation","attest_author":"https://pith.science/pith/6LZNJ4IWAROV47EVEL6ILCSAXA/action/author_attestation","sign_citation":"https://pith.science/pith/6LZNJ4IWAROV47EVEL6ILCSAXA/action/citation_signature","submit_replication":"https://pith.science/pith/6LZNJ4IWAROV47EVEL6ILCSAXA/action/replication_record"}},"created_at":"2026-07-05T11:33:54.592932+00:00","updated_at":"2026-07-05T11:33:54.592932+00:00"}