{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HW7IO7MZSW44L4VS7JQRROARFZ","short_pith_number":"pith:HW7IO7MZ","schema_version":"1.0","canonical_sha256":"3dbe877d9995b9c5f2b2fa6118b8112e666a86aab5aff305a039311aef465899","source":{"kind":"arxiv","id":"1705.07837","version":3},"attestation_state":"computed","paper":{"title":"Size Matters: Cardinality-Constrained Clustering and Outlier Detection via Conic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Daniel Kuhn, Kilian Schindler, Napat Rujeerapaiboon, Wolfram Wiesemann","submitted_at":"2017-05-22T16:32:23Z","abstract_excerpt":"Plain vanilla K-means clustering has proven to be successful in practice, yet it suffers from outlier sensitivity and may produce highly unbalanced clusters. To mitigate both shortcomings, we formulate a joint outlier detection and clustering problem, which assigns a prescribed number of datapoints to an auxiliary outlier cluster and performs cardinality-constrained K-means clustering on the residual dataset, treating the cluster cardinalities as a given input. We cast this problem as a mixed-integer linear program (MILP) that admits tractable semidefinite and linear programming relaxations. W"},"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":"1705.07837","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-05-22T16:32:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dad2adffd35c10072e5ad62d3ba1656b1926a1077f4a5c3ffb0abaabdf9d1b4e","abstract_canon_sha256":"10d23a482783159d594884709eb09b5e54c4e432b5de1fa7392c24a3c05d5dc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:39.041009Z","signature_b64":"Epno48erfgEdN7GYBe657M8GQzlvT2Kthg8TyBm3dQgUIhOIniBEktAjGbV2H2k6Z2onX49hdVGAQR9FfnFBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dbe877d9995b9c5f2b2fa6118b8112e666a86aab5aff305a039311aef465899","last_reissued_at":"2026-05-17T23:56:39.040531Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:39.040531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Size Matters: Cardinality-Constrained Clustering and Outlier Detection via Conic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Daniel Kuhn, Kilian Schindler, Napat Rujeerapaiboon, Wolfram Wiesemann","submitted_at":"2017-05-22T16:32:23Z","abstract_excerpt":"Plain vanilla K-means clustering has proven to be successful in practice, yet it suffers from outlier sensitivity and may produce highly unbalanced clusters. To mitigate both shortcomings, we formulate a joint outlier detection and clustering problem, which assigns a prescribed number of datapoints to an auxiliary outlier cluster and performs cardinality-constrained K-means clustering on the residual dataset, treating the cluster cardinalities as a given input. We cast this problem as a mixed-integer linear program (MILP) that admits tractable semidefinite and linear programming relaxations. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07837","kind":"arxiv","version":3},"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":"1705.07837","created_at":"2026-05-17T23:56:39.040602+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07837v3","created_at":"2026-05-17T23:56:39.040602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07837","created_at":"2026-05-17T23:56:39.040602+00:00"},{"alias_kind":"pith_short_12","alias_value":"HW7IO7MZSW44","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"HW7IO7MZSW44L4VS","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"HW7IO7MZ","created_at":"2026-05-18T12:31:21.493067+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/HW7IO7MZSW44L4VS7JQRROARFZ","json":"https://pith.science/pith/HW7IO7MZSW44L4VS7JQRROARFZ.json","graph_json":"https://pith.science/api/pith-number/HW7IO7MZSW44L4VS7JQRROARFZ/graph.json","events_json":"https://pith.science/api/pith-number/HW7IO7MZSW44L4VS7JQRROARFZ/events.json","paper":"https://pith.science/paper/HW7IO7MZ"},"agent_actions":{"view_html":"https://pith.science/pith/HW7IO7MZSW44L4VS7JQRROARFZ","download_json":"https://pith.science/pith/HW7IO7MZSW44L4VS7JQRROARFZ.json","view_paper":"https://pith.science/paper/HW7IO7MZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07837&json=true","fetch_graph":"https://pith.science/api/pith-number/HW7IO7MZSW44L4VS7JQRROARFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/HW7IO7MZSW44L4VS7JQRROARFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HW7IO7MZSW44L4VS7JQRROARFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HW7IO7MZSW44L4VS7JQRROARFZ/action/storage_attestation","attest_author":"https://pith.science/pith/HW7IO7MZSW44L4VS7JQRROARFZ/action/author_attestation","sign_citation":"https://pith.science/pith/HW7IO7MZSW44L4VS7JQRROARFZ/action/citation_signature","submit_replication":"https://pith.science/pith/HW7IO7MZSW44L4VS7JQRROARFZ/action/replication_record"}},"created_at":"2026-05-17T23:56:39.040602+00:00","updated_at":"2026-05-17T23:56:39.040602+00:00"}