{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AW7UU4FQLG5QOW5M64FMK5CRKT","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":"ff982a285f0b215eb09693d36a681f42fcf5a3744451c0901c2d69f1caa5bc14","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2020-03-03T10:28:14Z","title_canon_sha256":"00e97c5c6705a39ab0a5c3ef0ab66e5edf7489765834dcaeefa7834a813670c5"},"schema_version":"1.0","source":{"id":"2003.01430","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.01430","created_at":"2026-07-05T02:08:17Z"},{"alias_kind":"arxiv_version","alias_value":"2003.01430v3","created_at":"2026-07-05T02:08:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.01430","created_at":"2026-07-05T02:08:17Z"},{"alias_kind":"pith_short_12","alias_value":"AW7UU4FQLG5Q","created_at":"2026-07-05T02:08:17Z"},{"alias_kind":"pith_short_16","alias_value":"AW7UU4FQLG5QOW5M","created_at":"2026-07-05T02:08:17Z"},{"alias_kind":"pith_short_8","alias_value":"AW7UU4FQ","created_at":"2026-07-05T02:08:17Z"}],"graph_snapshots":[{"event_id":"sha256:9d7235f797443a8068361413ac5addd6e946f2b703096eafb3d51f0ff352b0cf","target":"graph","created_at":"2026-07-05T02:08:17Z","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/2003.01430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The most widely used internal measure for clustering evaluation is the silhouette coefficient, whose naive computation requires a quadratic number of distance calculations, which is clearly unfeasible for massive datasets. Surprisingly, there are no known general methods to efficiently approximate the silhouette coefficient of a clustering with rigorously provable high accuracy. In this paper, we present the first scalable algorithm to compute such a rigorous approximation for the evaluation of clusterings based on any metric distances. Our algorithm hinges on a Probability Proportional to Siz","authors_text":"Andrea Pietracaprina, Fabio Vandin, Federico Altieri, Geppino Pucci","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2020-03-03T10:28:14Z","title":"Scalable Distributed Approximation of Internal Measures for Clustering Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.01430","kind":"arxiv","version":3},"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":"sha256:40c8435f7991192ca7249211d31a9dee48a0c1ef3076d6928e67397cdbd028ba","target":"record","created_at":"2026-07-05T02:08:17Z","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":"ff982a285f0b215eb09693d36a681f42fcf5a3744451c0901c2d69f1caa5bc14","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2020-03-03T10:28:14Z","title_canon_sha256":"00e97c5c6705a39ab0a5c3ef0ab66e5edf7489765834dcaeefa7834a813670c5"},"schema_version":"1.0","source":{"id":"2003.01430","kind":"arxiv","version":3}},"canonical_sha256":"05bf4a70b059bb075bacf70ac5745154d1ae6f814d9f05693a52259f3fe2d72d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05bf4a70b059bb075bacf70ac5745154d1ae6f814d9f05693a52259f3fe2d72d","first_computed_at":"2026-07-05T02:08:17.556388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:08:17.556388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Sbr6+nMK2pi1BNE9yVuPZHJaBnGCQw1o3744rHxihMu6oZhJi2eUu45Gqa6aOl1gYIWEpXqtZWT6byoPe3YAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:08:17.556842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.01430","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40c8435f7991192ca7249211d31a9dee48a0c1ef3076d6928e67397cdbd028ba","sha256:9d7235f797443a8068361413ac5addd6e946f2b703096eafb3d51f0ff352b0cf"],"state_sha256":"e9228c9843a3865432b157ceb15e02159e7fa654e4571c4ce84a5838e72bcb99"}