{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DFAO6KWBIUPFSYV5K6GIXOZKHJ","short_pith_number":"pith:DFAO6KWB","schema_version":"1.0","canonical_sha256":"1940ef2ac1451e5962bd578c8bbb2a3a5c084cf8e113b72737c3783f2e981f88","source":{"kind":"arxiv","id":"2606.10673","version":1},"attestation_state":"computed","paper":{"title":"ClusBench: The Clustering Benchmark Data Resource You've All Been Waiting For (?)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.OT","authors_text":"David P. Hofmeyr","submitted_at":"2026-06-09T10:27:01Z","abstract_excerpt":"Although some very common test beds exist for assessing the performance of clustering methods, large scale benchmarking is typically limited to relatively simplistic simulation set-ups. Here we describe the production and curation of close to 3000 synthetic data sets, derived from more than 200 publicly available data sets; the majority of which arose from real-world applications. By fitting a flexible non-parametric distribution to each base data set we are able to retain much of the nuance in real-world data which is difficult to reproduce in standard simulations, while also producing data s"},"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":"2606.10673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.OT","submitted_at":"2026-06-09T10:27:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c3643ed8159123ce56ca394234b5cfea4c4047696e62d8af62299c7b80ae0fac","abstract_canon_sha256":"98fafa7b80affe568ae8dea484cf569ee86bb1bc7292cbff1b51bbbe2366914f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:33.518123Z","signature_b64":"B13hSvNrvdqICCTx3tNvJK0DDUx7chvfJR1U3tBQwnyXtUxubWu5eYnvlG8/OTUF8ocx9OlkjAmbEbj1iSlmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1940ef2ac1451e5962bd578c8bbb2a3a5c084cf8e113b72737c3783f2e981f88","last_reissued_at":"2026-06-10T01:10:33.517170Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:33.517170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClusBench: The Clustering Benchmark Data Resource You've All Been Waiting For (?)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.OT","authors_text":"David P. Hofmeyr","submitted_at":"2026-06-09T10:27:01Z","abstract_excerpt":"Although some very common test beds exist for assessing the performance of clustering methods, large scale benchmarking is typically limited to relatively simplistic simulation set-ups. Here we describe the production and curation of close to 3000 synthetic data sets, derived from more than 200 publicly available data sets; the majority of which arose from real-world applications. By fitting a flexible non-parametric distribution to each base data set we are able to retain much of the nuance in real-world data which is difficult to reproduce in standard simulations, while also producing data s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10673","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/2606.10673/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":"2606.10673","created_at":"2026-06-10T01:10:33.517337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10673v1","created_at":"2026-06-10T01:10:33.517337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10673","created_at":"2026-06-10T01:10:33.517337+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFAO6KWBIUPF","created_at":"2026-06-10T01:10:33.517337+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFAO6KWBIUPFSYV5","created_at":"2026-06-10T01:10:33.517337+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFAO6KWB","created_at":"2026-06-10T01:10:33.517337+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/DFAO6KWBIUPFSYV5K6GIXOZKHJ","json":"https://pith.science/pith/DFAO6KWBIUPFSYV5K6GIXOZKHJ.json","graph_json":"https://pith.science/api/pith-number/DFAO6KWBIUPFSYV5K6GIXOZKHJ/graph.json","events_json":"https://pith.science/api/pith-number/DFAO6KWBIUPFSYV5K6GIXOZKHJ/events.json","paper":"https://pith.science/paper/DFAO6KWB"},"agent_actions":{"view_html":"https://pith.science/pith/DFAO6KWBIUPFSYV5K6GIXOZKHJ","download_json":"https://pith.science/pith/DFAO6KWBIUPFSYV5K6GIXOZKHJ.json","view_paper":"https://pith.science/paper/DFAO6KWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10673&json=true","fetch_graph":"https://pith.science/api/pith-number/DFAO6KWBIUPFSYV5K6GIXOZKHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DFAO6KWBIUPFSYV5K6GIXOZKHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFAO6KWBIUPFSYV5K6GIXOZKHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFAO6KWBIUPFSYV5K6GIXOZKHJ/action/storage_attestation","attest_author":"https://pith.science/pith/DFAO6KWBIUPFSYV5K6GIXOZKHJ/action/author_attestation","sign_citation":"https://pith.science/pith/DFAO6KWBIUPFSYV5K6GIXOZKHJ/action/citation_signature","submit_replication":"https://pith.science/pith/DFAO6KWBIUPFSYV5K6GIXOZKHJ/action/replication_record"}},"created_at":"2026-06-10T01:10:33.517337+00:00","updated_at":"2026-06-10T01:10:33.517337+00:00"}