{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DFAO6KWBIUPFSYV5K6GIXOZKHJ","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":"98fafa7b80affe568ae8dea484cf569ee86bb1bc7292cbff1b51bbbe2366914f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.OT","submitted_at":"2026-06-09T10:27:01Z","title_canon_sha256":"c3643ed8159123ce56ca394234b5cfea4c4047696e62d8af62299c7b80ae0fac"},"schema_version":"1.0","source":{"id":"2606.10673","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10673","created_at":"2026-06-10T01:10:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10673v1","created_at":"2026-06-10T01:10:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10673","created_at":"2026-06-10T01:10:33Z"},{"alias_kind":"pith_short_12","alias_value":"DFAO6KWBIUPF","created_at":"2026-06-10T01:10:33Z"},{"alias_kind":"pith_short_16","alias_value":"DFAO6KWBIUPFSYV5","created_at":"2026-06-10T01:10:33Z"},{"alias_kind":"pith_short_8","alias_value":"DFAO6KWB","created_at":"2026-06-10T01:10:33Z"}],"graph_snapshots":[{"event_id":"sha256:06091efc5667ab7d1f55be6d4baee6c8d1420f8173c0a85b0dfdf0747b912a6f","target":"graph","created_at":"2026-06-10T01:10:33Z","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/2606.10673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David P. Hofmeyr","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.OT","submitted_at":"2026-06-09T10:27:01Z","title":"ClusBench: The Clustering Benchmark Data Resource You've All Been Waiting For (?)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10673","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":"sha256:08e278671b9a160eb9debfa1db87d09bd6e0373e9a587eaa8f4b5a8cc487351e","target":"record","created_at":"2026-06-10T01:10:33Z","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":"98fafa7b80affe568ae8dea484cf569ee86bb1bc7292cbff1b51bbbe2366914f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.OT","submitted_at":"2026-06-09T10:27:01Z","title_canon_sha256":"c3643ed8159123ce56ca394234b5cfea4c4047696e62d8af62299c7b80ae0fac"},"schema_version":"1.0","source":{"id":"2606.10673","kind":"arxiv","version":1}},"canonical_sha256":"1940ef2ac1451e5962bd578c8bbb2a3a5c084cf8e113b72737c3783f2e981f88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1940ef2ac1451e5962bd578c8bbb2a3a5c084cf8e113b72737c3783f2e981f88","first_computed_at":"2026-06-10T01:10:33.517170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:33.517170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B13hSvNrvdqICCTx3tNvJK0DDUx7chvfJR1U3tBQwnyXtUxubWu5eYnvlG8/OTUF8ocx9OlkjAmbEbj1iSlmCA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:33.518123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10673","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08e278671b9a160eb9debfa1db87d09bd6e0373e9a587eaa8f4b5a8cc487351e","sha256:06091efc5667ab7d1f55be6d4baee6c8d1420f8173c0a85b0dfdf0747b912a6f"],"state_sha256":"4d305b5e29a70654b47e1dbe47fc1203f66b3242e5a2731cc3362f3b9522d0f0"}