{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Q4JQUJ32RS2Z5MOJUFV2RWKN7U","short_pith_number":"pith:Q4JQUJ32","schema_version":"1.0","canonical_sha256":"87130a277a8cb59eb1c9a16ba8d94dfd2413a5be60f871d31cb4e093fdcfcbd7","source":{"kind":"arxiv","id":"2207.00966","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Evaluation of $k$-Means Coresets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Chris Schwiegelshohn, Omar Ali Sheikh-Omar","submitted_at":"2022-07-03T06:47:53Z","abstract_excerpt":"Coresets are among the most popular paradigms for summarizing data. In particular, there exist many high performance coresets for clustering problems such as $k$-means in both theory and practice. Curiously, there exists no work on comparing the quality of available $k$-means coresets.\n  In this paper we perform such an evaluation. There currently is no algorithm known to measure the distortion of a candidate coreset. We provide some evidence as to why this might be computationally difficult. To complement this, we propose a benchmark for which we argue that computing coresets is challenging a"},"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":"2207.00966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2022-07-03T06:47:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"161e3f6ba823a87fc53b8162dc3ae72eaedfb4fb11b1f132b845f23fc0d8ddbf","abstract_canon_sha256":"3094148b17c243be28cd638a9360ec7ce3d34392ef138177835abb8f2b1d76f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:54.555822Z","signature_b64":"V79x/6yqDtBCxArJkeOX9992VI2ojh98E6oo1fjipjDjWCjDO7CjIGmp8VuvRbPxs+rq4i8k+0ZpJoBllBRvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87130a277a8cb59eb1c9a16ba8d94dfd2413a5be60f871d31cb4e093fdcfcbd7","last_reissued_at":"2026-07-05T04:36:54.555440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:54.555440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Evaluation of $k$-Means Coresets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Chris Schwiegelshohn, Omar Ali Sheikh-Omar","submitted_at":"2022-07-03T06:47:53Z","abstract_excerpt":"Coresets are among the most popular paradigms for summarizing data. In particular, there exist many high performance coresets for clustering problems such as $k$-means in both theory and practice. Curiously, there exists no work on comparing the quality of available $k$-means coresets.\n  In this paper we perform such an evaluation. There currently is no algorithm known to measure the distortion of a candidate coreset. We provide some evidence as to why this might be computationally difficult. To complement this, we propose a benchmark for which we argue that computing coresets is challenging a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00966","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2207.00966/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":"2207.00966","created_at":"2026-07-05T04:36:54.555497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.00966v1","created_at":"2026-07-05T04:36:54.555497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00966","created_at":"2026-07-05T04:36:54.555497+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4JQUJ32RS2Z","created_at":"2026-07-05T04:36:54.555497+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4JQUJ32RS2Z5MOJ","created_at":"2026-07-05T04:36:54.555497+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4JQUJ32","created_at":"2026-07-05T04:36:54.555497+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/Q4JQUJ32RS2Z5MOJUFV2RWKN7U","json":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U.json","graph_json":"https://pith.science/api/pith-number/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/graph.json","events_json":"https://pith.science/api/pith-number/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/events.json","paper":"https://pith.science/paper/Q4JQUJ32"},"agent_actions":{"view_html":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U","download_json":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U.json","view_paper":"https://pith.science/paper/Q4JQUJ32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.00966&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/action/storage_attestation","attest_author":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/action/author_attestation","sign_citation":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/action/citation_signature","submit_replication":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/action/replication_record"}},"created_at":"2026-07-05T04:36:54.555497+00:00","updated_at":"2026-07-05T04:36:54.555497+00:00"}