{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3PR6UO4AGTGNZSAANUDEQ2PSGD","short_pith_number":"pith:3PR6UO4A","schema_version":"1.0","canonical_sha256":"dbe3ea3b8034ccdcc8006d064869f230f66b813d3b91554fa076534d988d6e9a","source":{"kind":"arxiv","id":"1702.02658","version":1},"attestation_state":"computed","paper":{"title":"Estimating the number of clusters using cross-validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ME","authors_text":"Patrick O. Perry, Wei Fu","submitted_at":"2017-02-09T00:11:27Z","abstract_excerpt":"Many clustering methods, including k-means, require the user to specify the number of clusters as an input parameter. A variety of methods have been devised to choose the number of clusters automatically, but they often rely on strong modeling assumptions. This paper proposes a data-driven approach to estimate the number of clusters based on a novel form of cross-validation. The proposed method differs from ordinary cross-validation, because clustering is fundamentally an unsupervised learning problem. Simulation and real data analysis results show that the proposed method outperforms existing"},"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":"1702.02658","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-02-09T00:11:27Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"e78dfa908eae95cd209cf32e36f19f456a803732ac14e3832b0736115b46428a","abstract_canon_sha256":"47d8aadbc90ac9e2c812520b71b2074be3f7aa80252f72a87ce4a411fb64ce24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:03.767160Z","signature_b64":"MEfYjTnsw5LopVqs+3blxT/l4Z3BIRpIddhr8CN5MkxOcm+ey+z/hKeAM+H9MZsD5RfXnGsFqbjqBp50VHxXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbe3ea3b8034ccdcc8006d064869f230f66b813d3b91554fa076534d988d6e9a","last_reissued_at":"2026-05-18T00:51:03.766750Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:03.766750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimating the number of clusters using cross-validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ME","authors_text":"Patrick O. Perry, Wei Fu","submitted_at":"2017-02-09T00:11:27Z","abstract_excerpt":"Many clustering methods, including k-means, require the user to specify the number of clusters as an input parameter. A variety of methods have been devised to choose the number of clusters automatically, but they often rely on strong modeling assumptions. This paper proposes a data-driven approach to estimate the number of clusters based on a novel form of cross-validation. The proposed method differs from ordinary cross-validation, because clustering is fundamentally an unsupervised learning problem. Simulation and real data analysis results show that the proposed method outperforms existing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02658","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":""},"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":"1702.02658","created_at":"2026-05-18T00:51:03.766808+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.02658v1","created_at":"2026-05-18T00:51:03.766808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02658","created_at":"2026-05-18T00:51:03.766808+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PR6UO4AGTGN","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PR6UO4AGTGNZSAA","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PR6UO4A","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PR6UO4AGTGNZSAANUDEQ2PSGD","json":"https://pith.science/pith/3PR6UO4AGTGNZSAANUDEQ2PSGD.json","graph_json":"https://pith.science/api/pith-number/3PR6UO4AGTGNZSAANUDEQ2PSGD/graph.json","events_json":"https://pith.science/api/pith-number/3PR6UO4AGTGNZSAANUDEQ2PSGD/events.json","paper":"https://pith.science/paper/3PR6UO4A"},"agent_actions":{"view_html":"https://pith.science/pith/3PR6UO4AGTGNZSAANUDEQ2PSGD","download_json":"https://pith.science/pith/3PR6UO4AGTGNZSAANUDEQ2PSGD.json","view_paper":"https://pith.science/paper/3PR6UO4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.02658&json=true","fetch_graph":"https://pith.science/api/pith-number/3PR6UO4AGTGNZSAANUDEQ2PSGD/graph.json","fetch_events":"https://pith.science/api/pith-number/3PR6UO4AGTGNZSAANUDEQ2PSGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PR6UO4AGTGNZSAANUDEQ2PSGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PR6UO4AGTGNZSAANUDEQ2PSGD/action/storage_attestation","attest_author":"https://pith.science/pith/3PR6UO4AGTGNZSAANUDEQ2PSGD/action/author_attestation","sign_citation":"https://pith.science/pith/3PR6UO4AGTGNZSAANUDEQ2PSGD/action/citation_signature","submit_replication":"https://pith.science/pith/3PR6UO4AGTGNZSAANUDEQ2PSGD/action/replication_record"}},"created_at":"2026-05-18T00:51:03.766808+00:00","updated_at":"2026-05-18T00:51:03.766808+00:00"}