{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Q4JQUJ32RS2Z5MOJUFV2RWKN7U","short_pith_number":"pith:Q4JQUJ32","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"},"canonical_sha256":"87130a277a8cb59eb1c9a16ba8d94dfd2413a5be60f871d31cb4e093fdcfcbd7","source":{"kind":"arxiv","id":"2207.00966","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00966","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00966v1","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00966","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"Q4JQUJ32RS2Z","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"Q4JQUJ32RS2Z5MOJ","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"Q4JQUJ32","created_at":"2026-07-05T04:36:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Q4JQUJ32RS2Z5MOJUFV2RWKN7U","target":"record","payload":{"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"},"canonical_sha256":"87130a277a8cb59eb1c9a16ba8d94dfd2413a5be60f871d31cb4e093fdcfcbd7","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"},"source_kind":"arxiv","source_id":"2207.00966","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eUnP/BELwghigJ5lPg1Q9oSGAwl0+6G7diUtajdl8WwWRYK033nMLRtn394YVNBOCCsl2TYoFuN+vAdIvqTgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T06:37:17.976874Z"},"content_sha256":"ce9d5b4875c3fca13114618c2057313075a5c1bc0406d57e291db80db97ad1b6","schema_version":"1.0","event_id":"sha256:ce9d5b4875c3fca13114618c2057313075a5c1bc0406d57e291db80db97ad1b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Q4JQUJ32RS2Z5MOJUFV2RWKN7U","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3p1jbJqOMfNJxyDOuTNUXRb4mRVOsRVviUDOZpa9++0pYhOhLzKQw6BaI7bWeOsmmxUhTeNMFOOZ7CmWm2sEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T06:37:17.977275Z"},"content_sha256":"8ae348abf767988d4322857b3f791e3a7538455829c0947ef16183abda941596","schema_version":"1.0","event_id":"sha256:8ae348abf767988d4322857b3f791e3a7538455829c0947ef16183abda941596"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/bundle.json","state_url":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T06:37:17Z","links":{"resolver":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U","bundle":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/bundle.json","state":"https://pith.science/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4JQUJ32RS2Z5MOJUFV2RWKN7U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Q4JQUJ32RS2Z5MOJUFV2RWKN7U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3094148b17c243be28cd638a9360ec7ce3d34392ef138177835abb8f2b1d76f5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2022-07-03T06:47:53Z","title_canon_sha256":"161e3f6ba823a87fc53b8162dc3ae72eaedfb4fb11b1f132b845f23fc0d8ddbf"},"schema_version":"1.0","source":{"id":"2207.00966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00966","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00966v1","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00966","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"Q4JQUJ32RS2Z","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"Q4JQUJ32RS2Z5MOJ","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"Q4JQUJ32","created_at":"2026-07-05T04:36:54Z"}],"graph_snapshots":[{"event_id":"sha256:8ae348abf767988d4322857b3f791e3a7538455829c0947ef16183abda941596","target":"graph","created_at":"2026-07-05T04:36:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2207.00966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chris Schwiegelshohn, Omar Ali Sheikh-Omar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2022-07-03T06:47:53Z","title":"An Empirical Evaluation of $k$-Means Coresets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00966","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ce9d5b4875c3fca13114618c2057313075a5c1bc0406d57e291db80db97ad1b6","target":"record","created_at":"2026-07-05T04:36:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3094148b17c243be28cd638a9360ec7ce3d34392ef138177835abb8f2b1d76f5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2022-07-03T06:47:53Z","title_canon_sha256":"161e3f6ba823a87fc53b8162dc3ae72eaedfb4fb11b1f132b845f23fc0d8ddbf"},"schema_version":"1.0","source":{"id":"2207.00966","kind":"arxiv","version":1}},"canonical_sha256":"87130a277a8cb59eb1c9a16ba8d94dfd2413a5be60f871d31cb4e093fdcfcbd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87130a277a8cb59eb1c9a16ba8d94dfd2413a5be60f871d31cb4e093fdcfcbd7","first_computed_at":"2026-07-05T04:36:54.555440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:54.555440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V79x/6yqDtBCxArJkeOX9992VI2ojh98E6oo1fjipjDjWCjDO7CjIGmp8VuvRbPxs+rq4i8k+0ZpJoBllBRvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:54.555822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.00966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce9d5b4875c3fca13114618c2057313075a5c1bc0406d57e291db80db97ad1b6","sha256:8ae348abf767988d4322857b3f791e3a7538455829c0947ef16183abda941596"],"state_sha256":"429d1c17e734f06829378cee1179e9798d5cf5e3d14b0c9a56a2200cb583bd6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Taqcj/eqywF0c9bY6LOPWGafsO0A0ZJVgzQGEJoUyTMoooTJotVMn/sS75HNx4eNjFyhqljK46J2en+C+6DWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T06:37:17.979366Z","bundle_sha256":"d17e5ccc43e159f6b2012c033e110587289300b58dbeb135235bd275cf87933e"}}