{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M6MPXTKLKGMI5H4LKFLL6DL6HM","short_pith_number":"pith:M6MPXTKL","schema_version":"1.0","canonical_sha256":"6798fbcd4b51988e9f8b5156bf0d7e3b3586a39c01c11cff8ac470ded9358031","source":{"kind":"arxiv","id":"2505.22991","version":1},"attestation_state":"computed","paper":{"title":"Number of Clusters in a Dataset: A Regularized K-means Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Behrooz Kamgar-Parsi, Behzad Kamgar-Parsi","submitted_at":"2025-05-29T01:58:44Z","abstract_excerpt":"Finding the number of meaningful clusters in an unlabeled dataset is important in many applications. Regularized k-means algorithm is a possible approach frequently used to find the correct number of distinct clusters in datasets. The most common formulation of the regularization function is the additive linear term $\\lambda k$, where $k$ is the number of clusters and $\\lambda$ a positive coefficient. Currently, there are no principled guidelines for setting a value for the critical hyperparameter $\\lambda$. In this paper, we derive rigorous bounds for $\\lambda$ assuming clusters are {\\em idea"},"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":"2505.22991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T01:58:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"071f704d158782c2a690802816e1a2eea25bf66594d985676978a83a126a17f0","abstract_canon_sha256":"fb47e4aba98561c5565a209aa78c05b51042fa689f54f4e8202990c9d565d928"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:53.157870Z","signature_b64":"BtWPcZtUOkg/fS/ZsyA5vbGs4HMeCmIOXF+aqscVW5QMwBBYEtCrkOHrlNucBUQHzGm2Ouoi3Sj21woxX4lrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6798fbcd4b51988e9f8b5156bf0d7e3b3586a39c01c11cff8ac470ded9358031","last_reissued_at":"2026-07-05T11:11:53.157388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:53.157388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Number of Clusters in a Dataset: A Regularized K-means Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Behrooz Kamgar-Parsi, Behzad Kamgar-Parsi","submitted_at":"2025-05-29T01:58:44Z","abstract_excerpt":"Finding the number of meaningful clusters in an unlabeled dataset is important in many applications. Regularized k-means algorithm is a possible approach frequently used to find the correct number of distinct clusters in datasets. The most common formulation of the regularization function is the additive linear term $\\lambda k$, where $k$ is the number of clusters and $\\lambda$ a positive coefficient. Currently, there are no principled guidelines for setting a value for the critical hyperparameter $\\lambda$. In this paper, we derive rigorous bounds for $\\lambda$ assuming clusters are {\\em idea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22991","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/2505.22991/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":"2505.22991","created_at":"2026-07-05T11:11:53.157446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22991v1","created_at":"2026-07-05T11:11:53.157446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22991","created_at":"2026-07-05T11:11:53.157446+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6MPXTKLKGMI","created_at":"2026-07-05T11:11:53.157446+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6MPXTKLKGMI5H4L","created_at":"2026-07-05T11:11:53.157446+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6MPXTKL","created_at":"2026-07-05T11:11:53.157446+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/M6MPXTKLKGMI5H4LKFLL6DL6HM","json":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM.json","graph_json":"https://pith.science/api/pith-number/M6MPXTKLKGMI5H4LKFLL6DL6HM/graph.json","events_json":"https://pith.science/api/pith-number/M6MPXTKLKGMI5H4LKFLL6DL6HM/events.json","paper":"https://pith.science/paper/M6MPXTKL"},"agent_actions":{"view_html":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM","download_json":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM.json","view_paper":"https://pith.science/paper/M6MPXTKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22991&json=true","fetch_graph":"https://pith.science/api/pith-number/M6MPXTKLKGMI5H4LKFLL6DL6HM/graph.json","fetch_events":"https://pith.science/api/pith-number/M6MPXTKLKGMI5H4LKFLL6DL6HM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/action/storage_attestation","attest_author":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/action/author_attestation","sign_citation":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/action/citation_signature","submit_replication":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/action/replication_record"}},"created_at":"2026-07-05T11:11:53.157446+00:00","updated_at":"2026-07-05T11:11:53.157446+00:00"}