{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AW7UU4FQLG5QOW5M64FMK5CRKT","short_pith_number":"pith:AW7UU4FQ","schema_version":"1.0","canonical_sha256":"05bf4a70b059bb075bacf70ac5745154d1ae6f814d9f05693a52259f3fe2d72d","source":{"kind":"arxiv","id":"2003.01430","version":3},"attestation_state":"computed","paper":{"title":"Scalable Distributed Approximation of Internal Measures for Clustering Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Andrea Pietracaprina, Fabio Vandin, Federico Altieri, Geppino Pucci","submitted_at":"2020-03-03T10:28:14Z","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"},"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":"2003.01430","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2020-03-03T10:28:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"00e97c5c6705a39ab0a5c3ef0ab66e5edf7489765834dcaeefa7834a813670c5","abstract_canon_sha256":"ff982a285f0b215eb09693d36a681f42fcf5a3744451c0901c2d69f1caa5bc14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:17.556842Z","signature_b64":"4Sbr6+nMK2pi1BNE9yVuPZHJaBnGCQw1o3744rHxihMu6oZhJi2eUu45Gqa6aOl1gYIWEpXqtZWT6byoPe3YAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05bf4a70b059bb075bacf70ac5745154d1ae6f814d9f05693a52259f3fe2d72d","last_reissued_at":"2026-07-05T02:08:17.556388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:17.556388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Distributed Approximation of Internal Measures for Clustering Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Andrea Pietracaprina, Fabio Vandin, Federico Altieri, Geppino Pucci","submitted_at":"2020-03-03T10:28:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.01430","kind":"arxiv","version":3},"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/2003.01430/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":"2003.01430","created_at":"2026-07-05T02:08:17.556445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.01430v3","created_at":"2026-07-05T02:08:17.556445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.01430","created_at":"2026-07-05T02:08:17.556445+00:00"},{"alias_kind":"pith_short_12","alias_value":"AW7UU4FQLG5Q","created_at":"2026-07-05T02:08:17.556445+00:00"},{"alias_kind":"pith_short_16","alias_value":"AW7UU4FQLG5QOW5M","created_at":"2026-07-05T02:08:17.556445+00:00"},{"alias_kind":"pith_short_8","alias_value":"AW7UU4FQ","created_at":"2026-07-05T02:08:17.556445+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/AW7UU4FQLG5QOW5M64FMK5CRKT","json":"https://pith.science/pith/AW7UU4FQLG5QOW5M64FMK5CRKT.json","graph_json":"https://pith.science/api/pith-number/AW7UU4FQLG5QOW5M64FMK5CRKT/graph.json","events_json":"https://pith.science/api/pith-number/AW7UU4FQLG5QOW5M64FMK5CRKT/events.json","paper":"https://pith.science/paper/AW7UU4FQ"},"agent_actions":{"view_html":"https://pith.science/pith/AW7UU4FQLG5QOW5M64FMK5CRKT","download_json":"https://pith.science/pith/AW7UU4FQLG5QOW5M64FMK5CRKT.json","view_paper":"https://pith.science/paper/AW7UU4FQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.01430&json=true","fetch_graph":"https://pith.science/api/pith-number/AW7UU4FQLG5QOW5M64FMK5CRKT/graph.json","fetch_events":"https://pith.science/api/pith-number/AW7UU4FQLG5QOW5M64FMK5CRKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AW7UU4FQLG5QOW5M64FMK5CRKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AW7UU4FQLG5QOW5M64FMK5CRKT/action/storage_attestation","attest_author":"https://pith.science/pith/AW7UU4FQLG5QOW5M64FMK5CRKT/action/author_attestation","sign_citation":"https://pith.science/pith/AW7UU4FQLG5QOW5M64FMK5CRKT/action/citation_signature","submit_replication":"https://pith.science/pith/AW7UU4FQLG5QOW5M64FMK5CRKT/action/replication_record"}},"created_at":"2026-07-05T02:08:17.556445+00:00","updated_at":"2026-07-05T02:08:17.556445+00:00"}