{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5JA5PVES6YEQL44TGLUOGJMS66","short_pith_number":"pith:5JA5PVES","schema_version":"1.0","canonical_sha256":"ea41d7d492f60905f39332e8e32592f798eccfb86698a091307746af2cbdb81a","source":{"kind":"arxiv","id":"1909.01930","version":1},"attestation_state":"computed","paper":{"title":"Simultaneous Estimation of Number of Clusters and Feature Sparsity in Clustering High-Dimensional Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Chien-Wei Lin, George Tseng, Xiangrui Zeng, Yujia Li","submitted_at":"2019-09-04T16:36:34Z","abstract_excerpt":"Estimating the number of clusters (K) is a critical and often difficult task in cluster analysis. Many methods have been proposed to estimate K, including some top performers using resampling approach. When performing cluster analysis in high-dimensional data, simultaneous clustering and feature selection is needed for improved interpretation and performance. To our knowledge, none has investigated simultaneous estimation of K and feature selection in an exploratory cluster analysis. In this paper, we propose a resampling method to meet this gap and evaluate its performance under the sparse K-"},"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":"1909.01930","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2019-09-04T16:36:34Z","cross_cats_sorted":[],"title_canon_sha256":"b33df9e1bbe3543bd0a71aad025c3254cd95613636f4fdeace931d3560af9f1b","abstract_canon_sha256":"2b17135e6b1c509285bbb127cdf599b0df92b694689016478f2212848a7881df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:21.822178Z","signature_b64":"kFpGOnJ0VgpUbWzpqe4NL4Nrqmkhxe3PtVtlABThkEQwUfN6WVjfznKN7pKA28saUZBw3wpgjahTsJNtkJm5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea41d7d492f60905f39332e8e32592f798eccfb86698a091307746af2cbdb81a","last_reissued_at":"2026-07-05T00:02:21.821797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:21.821797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simultaneous Estimation of Number of Clusters and Feature Sparsity in Clustering High-Dimensional Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Chien-Wei Lin, George Tseng, Xiangrui Zeng, Yujia Li","submitted_at":"2019-09-04T16:36:34Z","abstract_excerpt":"Estimating the number of clusters (K) is a critical and often difficult task in cluster analysis. Many methods have been proposed to estimate K, including some top performers using resampling approach. When performing cluster analysis in high-dimensional data, simultaneous clustering and feature selection is needed for improved interpretation and performance. To our knowledge, none has investigated simultaneous estimation of K and feature selection in an exploratory cluster analysis. In this paper, we propose a resampling method to meet this gap and evaluate its performance under the sparse K-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01930","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/1909.01930/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":"1909.01930","created_at":"2026-07-05T00:02:21.821850+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.01930v1","created_at":"2026-07-05T00:02:21.821850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01930","created_at":"2026-07-05T00:02:21.821850+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JA5PVES6YEQ","created_at":"2026-07-05T00:02:21.821850+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JA5PVES6YEQL44T","created_at":"2026-07-05T00:02:21.821850+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JA5PVES","created_at":"2026-07-05T00:02:21.821850+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/5JA5PVES6YEQL44TGLUOGJMS66","json":"https://pith.science/pith/5JA5PVES6YEQL44TGLUOGJMS66.json","graph_json":"https://pith.science/api/pith-number/5JA5PVES6YEQL44TGLUOGJMS66/graph.json","events_json":"https://pith.science/api/pith-number/5JA5PVES6YEQL44TGLUOGJMS66/events.json","paper":"https://pith.science/paper/5JA5PVES"},"agent_actions":{"view_html":"https://pith.science/pith/5JA5PVES6YEQL44TGLUOGJMS66","download_json":"https://pith.science/pith/5JA5PVES6YEQL44TGLUOGJMS66.json","view_paper":"https://pith.science/paper/5JA5PVES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.01930&json=true","fetch_graph":"https://pith.science/api/pith-number/5JA5PVES6YEQL44TGLUOGJMS66/graph.json","fetch_events":"https://pith.science/api/pith-number/5JA5PVES6YEQL44TGLUOGJMS66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JA5PVES6YEQL44TGLUOGJMS66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JA5PVES6YEQL44TGLUOGJMS66/action/storage_attestation","attest_author":"https://pith.science/pith/5JA5PVES6YEQL44TGLUOGJMS66/action/author_attestation","sign_citation":"https://pith.science/pith/5JA5PVES6YEQL44TGLUOGJMS66/action/citation_signature","submit_replication":"https://pith.science/pith/5JA5PVES6YEQL44TGLUOGJMS66/action/replication_record"}},"created_at":"2026-07-05T00:02:21.821850+00:00","updated_at":"2026-07-05T00:02:21.821850+00:00"}