{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SPK2JFWG7RJXK4M2N4MCUG6GXR","short_pith_number":"pith:SPK2JFWG","schema_version":"1.0","canonical_sha256":"93d5a496c6fc5375719a6f182a1bc6bc48af4c48102e479cf6324dd2b9e3ff81","source":{"kind":"arxiv","id":"1806.05938","version":2},"attestation_state":"computed","paper":{"title":"Query K-means Clustering and the Double Dixie Cup Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chao Pan, I Chien, Olgica Milenkovic","submitted_at":"2018-06-15T13:04:13Z","abstract_excerpt":"We consider the problem of approximate $K$-means clustering with outliers and side information provided by same-cluster queries and possibly noisy answers. Our solution shows that, under some mild assumptions on the smallest cluster size, one can obtain an $(1+\\epsilon)$-approximation for the optimal potential with probability at least $1-\\delta$, where $\\epsilon>0$ and $\\delta\\in(0,1)$, using an expected number of $O(\\frac{K^3}{\\epsilon \\delta})$ noiseless same-cluster queries and comparison-based clustering of complexity $O(ndK + \\frac{K^3}{\\epsilon \\delta})$, here, $n$ denotes the number of"},"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":"1806.05938","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-15T13:04:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6700af9f98f0444ab43f2918561c097465b7dcb6043f7c81fe1ea88c15eb623e","abstract_canon_sha256":"8e52ba280a8336ef0bc7ff9f7afccd1d51abafc53e66bc59977c98ad32fd5126"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:09.229194Z","signature_b64":"mV0h52AhFIVdMW/EATAl3Y3K/bkxkejGoId+2qS4Op8uqysuCy3boY3HEtU40io66yhIXysZRJCG+2reP6pXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93d5a496c6fc5375719a6f182a1bc6bc48af4c48102e479cf6324dd2b9e3ff81","last_reissued_at":"2026-05-18T00:01:09.228581Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:09.228581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query K-means Clustering and the Double Dixie Cup Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chao Pan, I Chien, Olgica Milenkovic","submitted_at":"2018-06-15T13:04:13Z","abstract_excerpt":"We consider the problem of approximate $K$-means clustering with outliers and side information provided by same-cluster queries and possibly noisy answers. Our solution shows that, under some mild assumptions on the smallest cluster size, one can obtain an $(1+\\epsilon)$-approximation for the optimal potential with probability at least $1-\\delta$, where $\\epsilon>0$ and $\\delta\\in(0,1)$, using an expected number of $O(\\frac{K^3}{\\epsilon \\delta})$ noiseless same-cluster queries and comparison-based clustering of complexity $O(ndK + \\frac{K^3}{\\epsilon \\delta})$, here, $n$ denotes the number of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05938","kind":"arxiv","version":2},"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":"1806.05938","created_at":"2026-05-18T00:01:09.228698+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05938v2","created_at":"2026-05-18T00:01:09.228698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05938","created_at":"2026-05-18T00:01:09.228698+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPK2JFWG7RJX","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPK2JFWG7RJXK4M2","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPK2JFWG","created_at":"2026-05-18T12:32:53.628368+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/SPK2JFWG7RJXK4M2N4MCUG6GXR","json":"https://pith.science/pith/SPK2JFWG7RJXK4M2N4MCUG6GXR.json","graph_json":"https://pith.science/api/pith-number/SPK2JFWG7RJXK4M2N4MCUG6GXR/graph.json","events_json":"https://pith.science/api/pith-number/SPK2JFWG7RJXK4M2N4MCUG6GXR/events.json","paper":"https://pith.science/paper/SPK2JFWG"},"agent_actions":{"view_html":"https://pith.science/pith/SPK2JFWG7RJXK4M2N4MCUG6GXR","download_json":"https://pith.science/pith/SPK2JFWG7RJXK4M2N4MCUG6GXR.json","view_paper":"https://pith.science/paper/SPK2JFWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05938&json=true","fetch_graph":"https://pith.science/api/pith-number/SPK2JFWG7RJXK4M2N4MCUG6GXR/graph.json","fetch_events":"https://pith.science/api/pith-number/SPK2JFWG7RJXK4M2N4MCUG6GXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPK2JFWG7RJXK4M2N4MCUG6GXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPK2JFWG7RJXK4M2N4MCUG6GXR/action/storage_attestation","attest_author":"https://pith.science/pith/SPK2JFWG7RJXK4M2N4MCUG6GXR/action/author_attestation","sign_citation":"https://pith.science/pith/SPK2JFWG7RJXK4M2N4MCUG6GXR/action/citation_signature","submit_replication":"https://pith.science/pith/SPK2JFWG7RJXK4M2N4MCUG6GXR/action/replication_record"}},"created_at":"2026-05-18T00:01:09.228698+00:00","updated_at":"2026-05-18T00:01:09.228698+00:00"}