{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T4TSMZF5YWH357CSXKQZXSAV7G","short_pith_number":"pith:T4TSMZF5","schema_version":"1.0","canonical_sha256":"9f272664bdc58fbefc52baa19bc815f9930845d77e8e17ff2b00495d4230d80b","source":{"kind":"arxiv","id":"2006.15666","version":5},"attestation_state":"computed","paper":{"title":"Breathing K-Means: Superior K-Means Solutions through Dynamic K-Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernd Fritzke (individual researcher)","submitted_at":"2020-06-28T17:49:37Z","abstract_excerpt":"We introduce the breathing k-means algorithm, which on average significantly improves solutions obtained by the widely-known greedy k-means++ algorithm, the default method for k-means clustering in the scikit-learn package. The improvements are achieved through a novel ``breathing'' technique, that cyclically increases and decreases the number of centroids based on local error and utility measures. We conducted experiments using greedy k-means++ as a baseline, comparing it with breathing k-means and five other k-means algorithms. Among the methods investigated, only breathing k-means and bette"},"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":"2006.15666","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-28T17:49:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e63483770899beaab400297007e26eee6d9e5dfbda2da3e133a156f716c60a9c","abstract_canon_sha256":"29da1cc4885913f1d7cfdfe76ca862198066e81835b782ec3571641a9819b753"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:10.119295Z","signature_b64":"2+1+LySoShZj1fC2Je96Ur18mf0/jkwx5GLKF4Hhgk0dZMnwXUVFXfqjbeIbOtgwUyRBbHId1o9Ez8MEHwuOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f272664bdc58fbefc52baa19bc815f9930845d77e8e17ff2b00495d4230d80b","last_reissued_at":"2026-07-05T08:56:10.118938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:10.118938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breathing K-Means: Superior K-Means Solutions through Dynamic K-Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernd Fritzke (individual researcher)","submitted_at":"2020-06-28T17:49:37Z","abstract_excerpt":"We introduce the breathing k-means algorithm, which on average significantly improves solutions obtained by the widely-known greedy k-means++ algorithm, the default method for k-means clustering in the scikit-learn package. The improvements are achieved through a novel ``breathing'' technique, that cyclically increases and decreases the number of centroids based on local error and utility measures. We conducted experiments using greedy k-means++ as a baseline, comparing it with breathing k-means and five other k-means algorithms. Among the methods investigated, only breathing k-means and bette"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15666","kind":"arxiv","version":5},"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/2006.15666/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":"2006.15666","created_at":"2026-07-05T08:56:10.118992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.15666v5","created_at":"2026-07-05T08:56:10.118992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15666","created_at":"2026-07-05T08:56:10.118992+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4TSMZF5YWH3","created_at":"2026-07-05T08:56:10.118992+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4TSMZF5YWH357CS","created_at":"2026-07-05T08:56:10.118992+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4TSMZF5","created_at":"2026-07-05T08:56:10.118992+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17528","citing_title":"Evolving Markov Chains: Unsupervised Mode Discovery and Recognition from Data Streams","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4TSMZF5YWH357CSXKQZXSAV7G","json":"https://pith.science/pith/T4TSMZF5YWH357CSXKQZXSAV7G.json","graph_json":"https://pith.science/api/pith-number/T4TSMZF5YWH357CSXKQZXSAV7G/graph.json","events_json":"https://pith.science/api/pith-number/T4TSMZF5YWH357CSXKQZXSAV7G/events.json","paper":"https://pith.science/paper/T4TSMZF5"},"agent_actions":{"view_html":"https://pith.science/pith/T4TSMZF5YWH357CSXKQZXSAV7G","download_json":"https://pith.science/pith/T4TSMZF5YWH357CSXKQZXSAV7G.json","view_paper":"https://pith.science/paper/T4TSMZF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.15666&json=true","fetch_graph":"https://pith.science/api/pith-number/T4TSMZF5YWH357CSXKQZXSAV7G/graph.json","fetch_events":"https://pith.science/api/pith-number/T4TSMZF5YWH357CSXKQZXSAV7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4TSMZF5YWH357CSXKQZXSAV7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4TSMZF5YWH357CSXKQZXSAV7G/action/storage_attestation","attest_author":"https://pith.science/pith/T4TSMZF5YWH357CSXKQZXSAV7G/action/author_attestation","sign_citation":"https://pith.science/pith/T4TSMZF5YWH357CSXKQZXSAV7G/action/citation_signature","submit_replication":"https://pith.science/pith/T4TSMZF5YWH357CSXKQZXSAV7G/action/replication_record"}},"created_at":"2026-07-05T08:56:10.118992+00:00","updated_at":"2026-07-05T08:56:10.118992+00:00"}