{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OIVXGZKQSW2UJDP2QMFBH2REHT","short_pith_number":"pith:OIVXGZKQ","schema_version":"1.0","canonical_sha256":"722b73655095b5448dfa830a13ea243cd9407cfd04b9101ef0667dfdf925dbf8","source":{"kind":"arxiv","id":"1904.12728","version":2},"attestation_state":"computed","paper":{"title":"Accurate MapReduce Algorithms for $k$-median and $k$-means in General Metric Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.DC","authors_text":"Alessio Mazzetto, Andrea Pietracaprina, Geppino Pucci","submitted_at":"2019-04-29T14:12:15Z","abstract_excerpt":"Center-based clustering is a fundamental primitive for data analysis and becomes very challenging for large datasets. In this paper, we focus on the popular $k$-median and $k$-means variants which, given a set $P$ of points from a metric space and a parameter $k<|P|$, require to identify a set $S$ of $k$ centers minimizing, respectively, the sum of the distances and of the squared distances of all points in $P$ from their closest centers. Our specific focus is on general metric spaces, for which it is reasonable to require that the centers belong to the input set (i.e., $S \\subseteq P$). We pr"},"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":"1904.12728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2019-04-29T14:12:15Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"f09a9a8a803f5413d145811caedc92e595addc71cc0e672479fe5dc0633f2ec0","abstract_canon_sha256":"370e81b19a7bdbc198a00d16b7ae1c5f5150cc5f89800888ef9c35b130de5c09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:08:05.227797Z","signature_b64":"TdmxoPKpDnWxL7MBtd+21vhLxP60nbRy3k8EwrdNNXRGcA9e7rJdJiJqu+bR+QTbbjCYtQFH6tyJxIfvt/SmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"722b73655095b5448dfa830a13ea243cd9407cfd04b9101ef0667dfdf925dbf8","last_reissued_at":"2026-07-05T00:08:05.227254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:08:05.227254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate MapReduce Algorithms for $k$-median and $k$-means in General Metric Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.DC","authors_text":"Alessio Mazzetto, Andrea Pietracaprina, Geppino Pucci","submitted_at":"2019-04-29T14:12:15Z","abstract_excerpt":"Center-based clustering is a fundamental primitive for data analysis and becomes very challenging for large datasets. In this paper, we focus on the popular $k$-median and $k$-means variants which, given a set $P$ of points from a metric space and a parameter $k<|P|$, require to identify a set $S$ of $k$ centers minimizing, respectively, the sum of the distances and of the squared distances of all points in $P$ from their closest centers. Our specific focus is on general metric spaces, for which it is reasonable to require that the centers belong to the input set (i.e., $S \\subseteq P$). We pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12728","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1904.12728/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1904.12728","created_at":"2026-07-05T00:08:05.227311+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.12728v2","created_at":"2026-07-05T00:08:05.227311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12728","created_at":"2026-07-05T00:08:05.227311+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIVXGZKQSW2U","created_at":"2026-07-05T00:08:05.227311+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIVXGZKQSW2UJDP2","created_at":"2026-07-05T00:08:05.227311+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIVXGZKQ","created_at":"2026-07-05T00:08:05.227311+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/OIVXGZKQSW2UJDP2QMFBH2REHT","json":"https://pith.science/pith/OIVXGZKQSW2UJDP2QMFBH2REHT.json","graph_json":"https://pith.science/api/pith-number/OIVXGZKQSW2UJDP2QMFBH2REHT/graph.json","events_json":"https://pith.science/api/pith-number/OIVXGZKQSW2UJDP2QMFBH2REHT/events.json","paper":"https://pith.science/paper/OIVXGZKQ"},"agent_actions":{"view_html":"https://pith.science/pith/OIVXGZKQSW2UJDP2QMFBH2REHT","download_json":"https://pith.science/pith/OIVXGZKQSW2UJDP2QMFBH2REHT.json","view_paper":"https://pith.science/paper/OIVXGZKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.12728&json=true","fetch_graph":"https://pith.science/api/pith-number/OIVXGZKQSW2UJDP2QMFBH2REHT/graph.json","fetch_events":"https://pith.science/api/pith-number/OIVXGZKQSW2UJDP2QMFBH2REHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIVXGZKQSW2UJDP2QMFBH2REHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIVXGZKQSW2UJDP2QMFBH2REHT/action/storage_attestation","attest_author":"https://pith.science/pith/OIVXGZKQSW2UJDP2QMFBH2REHT/action/author_attestation","sign_citation":"https://pith.science/pith/OIVXGZKQSW2UJDP2QMFBH2REHT/action/citation_signature","submit_replication":"https://pith.science/pith/OIVXGZKQSW2UJDP2QMFBH2REHT/action/replication_record"}},"created_at":"2026-07-05T00:08:05.227311+00:00","updated_at":"2026-07-05T00:08:05.227311+00:00"}