{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MM6TOBH2U6YJIWCHV7Y7PXE2RG","short_pith_number":"pith:MM6TOBH2","schema_version":"1.0","canonical_sha256":"633d3704faa7b0945847aff1f7dc9a89a1c2b828d9e5223bda61e4dfadf0df1e","source":{"kind":"arxiv","id":"2202.09784","version":1},"attestation_state":"computed","paper":{"title":"Clustering by the Probability Distributions from Extreme Value Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ME"],"primary_cat":"cs.LG","authors_text":"Jianfeng Feng, Ke Fan, Sixiao Zheng, Yanwei Fu, Yanxi Hou","submitted_at":"2022-02-20T10:52:43Z","abstract_excerpt":"Clustering is an essential task to unsupervised learning. It tries to automatically separate instances into coherent subsets. As one of the most well-known clustering algorithms, k-means assigns sample points at the boundary to a unique cluster, while it does not utilize the information of sample distribution or density. Comparably, it would potentially be more beneficial to consider the probability of each sample in a possible cluster. To this end, this paper generalizes k-means to model the distribution of clusters. Our novel clustering algorithm thus models the distributions of distances to"},"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":"2202.09784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-20T10:52:43Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ME"],"title_canon_sha256":"60761e8764a5ac4a8a6da2d8661137ed046cf0c28ca38efbf5c9b18e7d42decf","abstract_canon_sha256":"d2fb8afe49d8c3246f8fda0784111add865fc0314d518f81267beaafeda58095"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:26.052466Z","signature_b64":"U6y0E7XlKy/iSZ/I1qGue2y7wt9NXLfmMMe3pCd7JM48kra+l6yPK+kUpdHBn0jvPBBwHR3Jw1BnjIRqqcpKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"633d3704faa7b0945847aff1f7dc9a89a1c2b828d9e5223bda61e4dfadf0df1e","last_reissued_at":"2026-07-05T03:58:26.051984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:26.051984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustering by the Probability Distributions from Extreme Value Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ME"],"primary_cat":"cs.LG","authors_text":"Jianfeng Feng, Ke Fan, Sixiao Zheng, Yanwei Fu, Yanxi Hou","submitted_at":"2022-02-20T10:52:43Z","abstract_excerpt":"Clustering is an essential task to unsupervised learning. It tries to automatically separate instances into coherent subsets. As one of the most well-known clustering algorithms, k-means assigns sample points at the boundary to a unique cluster, while it does not utilize the information of sample distribution or density. Comparably, it would potentially be more beneficial to consider the probability of each sample in a possible cluster. To this end, this paper generalizes k-means to model the distribution of clusters. Our novel clustering algorithm thus models the distributions of distances to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09784","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/2202.09784/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":"2202.09784","created_at":"2026-07-05T03:58:26.052041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.09784v1","created_at":"2026-07-05T03:58:26.052041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09784","created_at":"2026-07-05T03:58:26.052041+00:00"},{"alias_kind":"pith_short_12","alias_value":"MM6TOBH2U6YJ","created_at":"2026-07-05T03:58:26.052041+00:00"},{"alias_kind":"pith_short_16","alias_value":"MM6TOBH2U6YJIWCH","created_at":"2026-07-05T03:58:26.052041+00:00"},{"alias_kind":"pith_short_8","alias_value":"MM6TOBH2","created_at":"2026-07-05T03:58:26.052041+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/MM6TOBH2U6YJIWCHV7Y7PXE2RG","json":"https://pith.science/pith/MM6TOBH2U6YJIWCHV7Y7PXE2RG.json","graph_json":"https://pith.science/api/pith-number/MM6TOBH2U6YJIWCHV7Y7PXE2RG/graph.json","events_json":"https://pith.science/api/pith-number/MM6TOBH2U6YJIWCHV7Y7PXE2RG/events.json","paper":"https://pith.science/paper/MM6TOBH2"},"agent_actions":{"view_html":"https://pith.science/pith/MM6TOBH2U6YJIWCHV7Y7PXE2RG","download_json":"https://pith.science/pith/MM6TOBH2U6YJIWCHV7Y7PXE2RG.json","view_paper":"https://pith.science/paper/MM6TOBH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.09784&json=true","fetch_graph":"https://pith.science/api/pith-number/MM6TOBH2U6YJIWCHV7Y7PXE2RG/graph.json","fetch_events":"https://pith.science/api/pith-number/MM6TOBH2U6YJIWCHV7Y7PXE2RG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MM6TOBH2U6YJIWCHV7Y7PXE2RG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MM6TOBH2U6YJIWCHV7Y7PXE2RG/action/storage_attestation","attest_author":"https://pith.science/pith/MM6TOBH2U6YJIWCHV7Y7PXE2RG/action/author_attestation","sign_citation":"https://pith.science/pith/MM6TOBH2U6YJIWCHV7Y7PXE2RG/action/citation_signature","submit_replication":"https://pith.science/pith/MM6TOBH2U6YJIWCHV7Y7PXE2RG/action/replication_record"}},"created_at":"2026-07-05T03:58:26.052041+00:00","updated_at":"2026-07-05T03:58:26.052041+00:00"}