{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZWYS6WGCCDT3I6JS4XNG6QIDI4","short_pith_number":"pith:ZWYS6WGC","schema_version":"1.0","canonical_sha256":"cdb12f58c210e7b47932e5da6f4103472796758da6da8f5889dbd38afb369ca5","source":{"kind":"arxiv","id":"2202.01456","version":2},"attestation_state":"computed","paper":{"title":"Fast and explainable clustering based on sorting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Stefan G\\\"uttel, Xinye Chen","submitted_at":"2022-02-03T08:24:21Z","abstract_excerpt":"We introduce a fast and explainable clustering method called CLASSIX. It consists of two phases, namely a greedy aggregation phase of the sorted data into groups of nearby data points, followed by the merging of groups into clusters. The algorithm is controlled by two scalar parameters, namely a distance parameter for the aggregation and another parameter controlling the minimal cluster size. Extensive experiments are conducted to give a comprehensive evaluation of the clustering performance on synthetic and real-world datasets, with various cluster shapes and low to high feature dimensionalit"},"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":"2202.01456","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-03T08:24:21Z","cross_cats_sorted":["cs.DS","stat.CO","stat.ML"],"title_canon_sha256":"9e1a3be84454a5d5ff6679a4e8823f7ab6a2527d439b1bc2517ce3549b7c6c96","abstract_canon_sha256":"0961696f9a5c65390dc2a32bbf1edba713cb07a5451c8994042fb42dbc7dd48a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:24.749562Z","signature_b64":"VpGPoVFfP2TQeff+BOr7b5/W3aXUkoMCA4W+N3JytvqUFpM3sVUF73+Fgf1S9E+Ew9l8Ca26Kut+dUWDXK50Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdb12f58c210e7b47932e5da6f4103472796758da6da8f5889dbd38afb369ca5","last_reissued_at":"2026-07-05T07:45:24.749098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:24.749098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and explainable clustering based on sorting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Stefan G\\\"uttel, Xinye Chen","submitted_at":"2022-02-03T08:24:21Z","abstract_excerpt":"We introduce a fast and explainable clustering method called CLASSIX. It consists of two phases, namely a greedy aggregation phase of the sorted data into groups of nearby data points, followed by the merging of groups into clusters. The algorithm is controlled by two scalar parameters, namely a distance parameter for the aggregation and another parameter controlling the minimal cluster size. Extensive experiments are conducted to give a comprehensive evaluation of the clustering performance on synthetic and real-world datasets, with various cluster shapes and low to high feature dimensionalit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01456","kind":"arxiv","version":2},"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/2202.01456/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":"2202.01456","created_at":"2026-07-05T07:45:24.749155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01456v2","created_at":"2026-07-05T07:45:24.749155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01456","created_at":"2026-07-05T07:45:24.749155+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWYS6WGCCDT3","created_at":"2026-07-05T07:45:24.749155+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWYS6WGCCDT3I6JS","created_at":"2026-07-05T07:45:24.749155+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWYS6WGC","created_at":"2026-07-05T07:45:24.749155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.00109","citing_title":"Parallel Two-Stage Approach for Joint Symbolic Approximation of Time Series","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWYS6WGCCDT3I6JS4XNG6QIDI4","json":"https://pith.science/pith/ZWYS6WGCCDT3I6JS4XNG6QIDI4.json","graph_json":"https://pith.science/api/pith-number/ZWYS6WGCCDT3I6JS4XNG6QIDI4/graph.json","events_json":"https://pith.science/api/pith-number/ZWYS6WGCCDT3I6JS4XNG6QIDI4/events.json","paper":"https://pith.science/paper/ZWYS6WGC"},"agent_actions":{"view_html":"https://pith.science/pith/ZWYS6WGCCDT3I6JS4XNG6QIDI4","download_json":"https://pith.science/pith/ZWYS6WGCCDT3I6JS4XNG6QIDI4.json","view_paper":"https://pith.science/paper/ZWYS6WGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01456&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWYS6WGCCDT3I6JS4XNG6QIDI4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWYS6WGCCDT3I6JS4XNG6QIDI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWYS6WGCCDT3I6JS4XNG6QIDI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWYS6WGCCDT3I6JS4XNG6QIDI4/action/storage_attestation","attest_author":"https://pith.science/pith/ZWYS6WGCCDT3I6JS4XNG6QIDI4/action/author_attestation","sign_citation":"https://pith.science/pith/ZWYS6WGCCDT3I6JS4XNG6QIDI4/action/citation_signature","submit_replication":"https://pith.science/pith/ZWYS6WGCCDT3I6JS4XNG6QIDI4/action/replication_record"}},"created_at":"2026-07-05T07:45:24.749155+00:00","updated_at":"2026-07-05T07:45:24.749155+00:00"}