{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:X2OTXPYUTB26OQHH2SIHVL4K7O","short_pith_number":"pith:X2OTXPYU","schema_version":"1.0","canonical_sha256":"be9d3bbf149875e740e7d4907aaf8afb8918ed80fed20ac758b45bd36c948779","source":{"kind":"arxiv","id":"1408.2045","version":1},"attestation_state":"computed","paper":{"title":"Efficient Clustering with Limited Distance Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Heiko Roglin, Konstantin Voevodski, Maria-Florina Balcan, Shang-Hua Teng, Yu Xia","submitted_at":"2014-08-09T05:41:26Z","abstract_excerpt":"Given a point set S and an unknown metric d on S, we study the problem of efficiently partitioning S into k clusters while querying few distances between the points. In our model we assume that we have access to one versus all queries that given a point s 2 S return the distances between s and all other points. We show that given a natural assumption about the structure of the instance, we can efficiently find an accurate clustering using only O(k) distance queries. We use our algorithm to cluster proteins by sequence similarity. This setting nicely fits our model because we can use a fast seq"},"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":"1408.2045","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-08-09T05:41:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a136ee2ef325a1f6ffda06baf08f920520dbeb16fc678033aecf49d914a1a884","abstract_canon_sha256":"09d94db7f8ffade6a16a7e10d286c9ba0bcc2bff450b002d40a6f2769ae35000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:30.580955Z","signature_b64":"DWrS9tuRmqSVjsNFckqg4HBrzf0pnF9skB3gIVCRsLA5qP4DEylwLqmh2UOK+/0ReedY0hz+R0aydgeNl7GYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be9d3bbf149875e740e7d4907aaf8afb8918ed80fed20ac758b45bd36c948779","last_reissued_at":"2026-05-18T02:45:30.580362Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:30.580362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Clustering with Limited Distance Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Heiko Roglin, Konstantin Voevodski, Maria-Florina Balcan, Shang-Hua Teng, Yu Xia","submitted_at":"2014-08-09T05:41:26Z","abstract_excerpt":"Given a point set S and an unknown metric d on S, we study the problem of efficiently partitioning S into k clusters while querying few distances between the points. In our model we assume that we have access to one versus all queries that given a point s 2 S return the distances between s and all other points. We show that given a natural assumption about the structure of the instance, we can efficiently find an accurate clustering using only O(k) distance queries. We use our algorithm to cluster proteins by sequence similarity. This setting nicely fits our model because we can use a fast seq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.2045","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":""},"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":"1408.2045","created_at":"2026-05-18T02:45:30.580443+00:00"},{"alias_kind":"arxiv_version","alias_value":"1408.2045v1","created_at":"2026-05-18T02:45:30.580443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.2045","created_at":"2026-05-18T02:45:30.580443+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2OTXPYUTB26","created_at":"2026-05-18T12:28:54.890064+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2OTXPYUTB26OQHH","created_at":"2026-05-18T12:28:54.890064+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2OTXPYU","created_at":"2026-05-18T12:28:54.890064+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/X2OTXPYUTB26OQHH2SIHVL4K7O","json":"https://pith.science/pith/X2OTXPYUTB26OQHH2SIHVL4K7O.json","graph_json":"https://pith.science/api/pith-number/X2OTXPYUTB26OQHH2SIHVL4K7O/graph.json","events_json":"https://pith.science/api/pith-number/X2OTXPYUTB26OQHH2SIHVL4K7O/events.json","paper":"https://pith.science/paper/X2OTXPYU"},"agent_actions":{"view_html":"https://pith.science/pith/X2OTXPYUTB26OQHH2SIHVL4K7O","download_json":"https://pith.science/pith/X2OTXPYUTB26OQHH2SIHVL4K7O.json","view_paper":"https://pith.science/paper/X2OTXPYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1408.2045&json=true","fetch_graph":"https://pith.science/api/pith-number/X2OTXPYUTB26OQHH2SIHVL4K7O/graph.json","fetch_events":"https://pith.science/api/pith-number/X2OTXPYUTB26OQHH2SIHVL4K7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2OTXPYUTB26OQHH2SIHVL4K7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2OTXPYUTB26OQHH2SIHVL4K7O/action/storage_attestation","attest_author":"https://pith.science/pith/X2OTXPYUTB26OQHH2SIHVL4K7O/action/author_attestation","sign_citation":"https://pith.science/pith/X2OTXPYUTB26OQHH2SIHVL4K7O/action/citation_signature","submit_replication":"https://pith.science/pith/X2OTXPYUTB26OQHH2SIHVL4K7O/action/replication_record"}},"created_at":"2026-05-18T02:45:30.580443+00:00","updated_at":"2026-05-18T02:45:30.580443+00:00"}