{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OG3OA2D2Y66WEF3SWD2UDDK6HR","short_pith_number":"pith:OG3OA2D2","schema_version":"1.0","canonical_sha256":"71b6e0687ac7bd621772b0f5418d5e3c4c708763b90dc0974786f99fca0a08f3","source":{"kind":"arxiv","id":"1810.07852","version":2},"attestation_state":"computed","paper":{"title":"Distributed $k$-Clustering for Data with Heavy Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"cs.DC","authors_text":"Shi Li, Xiangyu Guo","submitted_at":"2018-10-18T01:04:14Z","abstract_excerpt":"In this paper, we consider the $k$-center/median/means clustering with outliers problems (or the $(k, z)$-center/median/means problems) in the distributed setting. Most previous distributed algorithms have their communication costs linearly depending on $z$, the number of outliers. Recently Guha et al. overcame this dependence issue by considering bi-criteria approximation algorithms that output solutions with $2z$ outliers. For the case where $z$ is large, the extra $z$ outliers discarded by the algorithms might be too large, considering that the data gathering process might be costly. In thi"},"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":"1810.07852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-10-18T01:04:14Z","cross_cats_sorted":["cs.DS","cs.LG"],"title_canon_sha256":"1501f858175aaf6b8b73ca79a5a8ff3aa465f62b25d4e1c078ccaaa869b6b82d","abstract_canon_sha256":"d8013c42d00158869003f9e991c9d3ff90a1c024cdd5dafb62c7af1c2bdbd723"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:38.134992Z","signature_b64":"Mm6p2tWG7BL9Y1QD47hWi5bJI3HETXcPrf4t44nNsfMfbqXnUIayZ8toozS1VBQSvOHpAKr9TroiQVydinitAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71b6e0687ac7bd621772b0f5418d5e3c4c708763b90dc0974786f99fca0a08f3","last_reissued_at":"2026-05-17T23:59:38.134256Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:38.134256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed $k$-Clustering for Data with Heavy Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"cs.DC","authors_text":"Shi Li, Xiangyu Guo","submitted_at":"2018-10-18T01:04:14Z","abstract_excerpt":"In this paper, we consider the $k$-center/median/means clustering with outliers problems (or the $(k, z)$-center/median/means problems) in the distributed setting. Most previous distributed algorithms have their communication costs linearly depending on $z$, the number of outliers. Recently Guha et al. overcame this dependence issue by considering bi-criteria approximation algorithms that output solutions with $2z$ outliers. For the case where $z$ is large, the extra $z$ outliers discarded by the algorithms might be too large, considering that the data gathering process might be costly. In thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07852","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":"1810.07852","created_at":"2026-05-17T23:59:38.134402+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07852v2","created_at":"2026-05-17T23:59:38.134402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07852","created_at":"2026-05-17T23:59:38.134402+00:00"},{"alias_kind":"pith_short_12","alias_value":"OG3OA2D2Y66W","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OG3OA2D2Y66WEF3S","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OG3OA2D2","created_at":"2026-05-18T12:32:43.782077+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/OG3OA2D2Y66WEF3SWD2UDDK6HR","json":"https://pith.science/pith/OG3OA2D2Y66WEF3SWD2UDDK6HR.json","graph_json":"https://pith.science/api/pith-number/OG3OA2D2Y66WEF3SWD2UDDK6HR/graph.json","events_json":"https://pith.science/api/pith-number/OG3OA2D2Y66WEF3SWD2UDDK6HR/events.json","paper":"https://pith.science/paper/OG3OA2D2"},"agent_actions":{"view_html":"https://pith.science/pith/OG3OA2D2Y66WEF3SWD2UDDK6HR","download_json":"https://pith.science/pith/OG3OA2D2Y66WEF3SWD2UDDK6HR.json","view_paper":"https://pith.science/paper/OG3OA2D2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07852&json=true","fetch_graph":"https://pith.science/api/pith-number/OG3OA2D2Y66WEF3SWD2UDDK6HR/graph.json","fetch_events":"https://pith.science/api/pith-number/OG3OA2D2Y66WEF3SWD2UDDK6HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OG3OA2D2Y66WEF3SWD2UDDK6HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OG3OA2D2Y66WEF3SWD2UDDK6HR/action/storage_attestation","attest_author":"https://pith.science/pith/OG3OA2D2Y66WEF3SWD2UDDK6HR/action/author_attestation","sign_citation":"https://pith.science/pith/OG3OA2D2Y66WEF3SWD2UDDK6HR/action/citation_signature","submit_replication":"https://pith.science/pith/OG3OA2D2Y66WEF3SWD2UDDK6HR/action/replication_record"}},"created_at":"2026-05-17T23:59:38.134402+00:00","updated_at":"2026-05-17T23:59:38.134402+00:00"}