{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:U6SKTFMI7KMJSV42YQGPOP6TSS","short_pith_number":"pith:U6SKTFMI","schema_version":"1.0","canonical_sha256":"a7a4a99588fa9899579ac40cf73fd394932e4937732b056ba8d22a452c571d4d","source":{"kind":"arxiv","id":"1602.06989","version":1},"attestation_state":"computed","paper":{"title":"Recovering the number of clusters in data sets with noise features using feature rescaling factors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christian Hennig, Renato Cordeiro de Amorim","submitted_at":"2016-02-22T22:40:00Z","abstract_excerpt":"In this paper we introduce three methods for re-scaling data sets aiming at improving the likelihood of clustering validity indexes to return the true number of spherical Gaussian clusters with additional noise features. Our method obtains feature re-scaling factors taking into account the structure of a given data set and the intuitive idea that different features may have different degrees of relevance at different clusters.\n  We experiment with the Silhouette (using squared Euclidean, Manhattan, and the p$^{th}$ power of the Minkowski distance), Dunn's, Calinski-Harabasz and Hartigan indexe"},"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":"1602.06989","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-22T22:40:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d697418de04964d073951b2912821403332131d12dd6ba68496cd5b5f8abab91","abstract_canon_sha256":"26f7658f9ad959dcd61e8b29c7cb1c4f0394f52391f77cc3bdd6058635500ea2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:07.473733Z","signature_b64":"fNqDTGJZtNFoxgO6vem7wCwsB0AddVXhEw3OD+lP1G/2bbZ+WSNViHLRxvTXOqO5SohlQ820ie1gPsLtLikXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7a4a99588fa9899579ac40cf73fd394932e4937732b056ba8d22a452c571d4d","last_reissued_at":"2026-05-18T01:20:07.473175Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:07.473175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recovering the number of clusters in data sets with noise features using feature rescaling factors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christian Hennig, Renato Cordeiro de Amorim","submitted_at":"2016-02-22T22:40:00Z","abstract_excerpt":"In this paper we introduce three methods for re-scaling data sets aiming at improving the likelihood of clustering validity indexes to return the true number of spherical Gaussian clusters with additional noise features. Our method obtains feature re-scaling factors taking into account the structure of a given data set and the intuitive idea that different features may have different degrees of relevance at different clusters.\n  We experiment with the Silhouette (using squared Euclidean, Manhattan, and the p$^{th}$ power of the Minkowski distance), Dunn's, Calinski-Harabasz and Hartigan indexe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06989","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":"1602.06989","created_at":"2026-05-18T01:20:07.473241+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.06989v1","created_at":"2026-05-18T01:20:07.473241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06989","created_at":"2026-05-18T01:20:07.473241+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6SKTFMI7KMJ","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6SKTFMI7KMJSV42","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6SKTFMI","created_at":"2026-05-18T12:30:46.583412+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/U6SKTFMI7KMJSV42YQGPOP6TSS","json":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS.json","graph_json":"https://pith.science/api/pith-number/U6SKTFMI7KMJSV42YQGPOP6TSS/graph.json","events_json":"https://pith.science/api/pith-number/U6SKTFMI7KMJSV42YQGPOP6TSS/events.json","paper":"https://pith.science/paper/U6SKTFMI"},"agent_actions":{"view_html":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS","download_json":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS.json","view_paper":"https://pith.science/paper/U6SKTFMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.06989&json=true","fetch_graph":"https://pith.science/api/pith-number/U6SKTFMI7KMJSV42YQGPOP6TSS/graph.json","fetch_events":"https://pith.science/api/pith-number/U6SKTFMI7KMJSV42YQGPOP6TSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/action/storage_attestation","attest_author":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/action/author_attestation","sign_citation":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/action/citation_signature","submit_replication":"https://pith.science/pith/U6SKTFMI7KMJSV42YQGPOP6TSS/action/replication_record"}},"created_at":"2026-05-18T01:20:07.473241+00:00","updated_at":"2026-05-18T01:20:07.473241+00:00"}