{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VJM65JCM4DRIMLHMJD5TD47ISN","short_pith_number":"pith:VJM65JCM","schema_version":"1.0","canonical_sha256":"aa59eea44ce0e2862cec48fb31f3e8936de5e4b857d5e5cfa9b31583e5951f36","source":{"kind":"arxiv","id":"1703.00830","version":3},"attestation_state":"computed","paper":{"title":"Robust Communication-Optimal Distributed Clustering Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.DS","authors_text":"Ainesh Bakshi, Colin White, David Woodruff, Maria-Florina Balcan, Pranjal Awasthi","submitted_at":"2017-03-02T15:27:14Z","abstract_excerpt":"In this work, we study the $k$-median and $k$-means clustering problems when the data is distributed across many servers and can contain outliers. While there has been a lot of work on these problems for worst-case instances, we focus on gaining a finer understanding through the lens of beyond worst-case analysis. Our main motivation is the following: for many applications such as clustering proteins by function or clustering communities in a social network, there is some unknown target clustering, and the hope is that running a $k$-median or $k$-means algorithm will produce clusterings which "},"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":"1703.00830","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-03-02T15:27:14Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"946b951d65655187d6797419cfb1729701562ca5d62619149b345b9f00e4444f","abstract_canon_sha256":"7336a660ac0a6d68fa9e26b42e6e1dfdd010ec9671dd379a132ea10d66a55a7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:54.904668Z","signature_b64":"j6SwbbuXVxLubj7GrPGOMnMie2t8hCZfx5TjRPZixkvjXdc3pALFTzMtoG+Vjfy3XYjOooPpw8nl0L7eKq4RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa59eea44ce0e2862cec48fb31f3e8936de5e4b857d5e5cfa9b31583e5951f36","last_reissued_at":"2026-05-17T23:51:54.904209Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:54.904209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Communication-Optimal Distributed Clustering Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.DS","authors_text":"Ainesh Bakshi, Colin White, David Woodruff, Maria-Florina Balcan, Pranjal Awasthi","submitted_at":"2017-03-02T15:27:14Z","abstract_excerpt":"In this work, we study the $k$-median and $k$-means clustering problems when the data is distributed across many servers and can contain outliers. While there has been a lot of work on these problems for worst-case instances, we focus on gaining a finer understanding through the lens of beyond worst-case analysis. Our main motivation is the following: for many applications such as clustering proteins by function or clustering communities in a social network, there is some unknown target clustering, and the hope is that running a $k$-median or $k$-means algorithm will produce clusterings which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00830","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":"1703.00830","created_at":"2026-05-17T23:51:54.904277+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00830v3","created_at":"2026-05-17T23:51:54.904277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00830","created_at":"2026-05-17T23:51:54.904277+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJM65JCM4DRI","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJM65JCM4DRIMLHM","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJM65JCM","created_at":"2026-05-18T12:31:49.984773+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/VJM65JCM4DRIMLHMJD5TD47ISN","json":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN.json","graph_json":"https://pith.science/api/pith-number/VJM65JCM4DRIMLHMJD5TD47ISN/graph.json","events_json":"https://pith.science/api/pith-number/VJM65JCM4DRIMLHMJD5TD47ISN/events.json","paper":"https://pith.science/paper/VJM65JCM"},"agent_actions":{"view_html":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN","download_json":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN.json","view_paper":"https://pith.science/paper/VJM65JCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00830&json=true","fetch_graph":"https://pith.science/api/pith-number/VJM65JCM4DRIMLHMJD5TD47ISN/graph.json","fetch_events":"https://pith.science/api/pith-number/VJM65JCM4DRIMLHMJD5TD47ISN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN/action/storage_attestation","attest_author":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN/action/author_attestation","sign_citation":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN/action/citation_signature","submit_replication":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN/action/replication_record"}},"created_at":"2026-05-17T23:51:54.904277+00:00","updated_at":"2026-05-17T23:51:54.904277+00:00"}