{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DJIWNL24JLTC5Q3NEVQ4UNYGAZ","short_pith_number":"pith:DJIWNL24","schema_version":"1.0","canonical_sha256":"1a5166af5c4ae62ec36d2561ca37060676f9116fda8e2d5632288ba8a65a9748","source":{"kind":"arxiv","id":"1711.04359","version":1},"attestation_state":"computed","paper":{"title":"K-groups: A Generalization of K-means Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Maria L. Rizzo, Songzi Li","submitted_at":"2017-11-12T21:18:12Z","abstract_excerpt":"We propose a new class of distribution-based clustering algorithms, called k-groups, based on energy distance between samples. The energy distance clustering criterion assigns observations to clusters according to a multi-sample energy statistic that measures the distance between distributions. The energy distance determines a consistent test for equality of distributions, and it is based on a population distance that characterizes equality of distributions. The k-groups procedure therefore generalizes the k-means method, which separates clusters that have different means. We propose two k-gro"},"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":"1711.04359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-11-12T21:18:12Z","cross_cats_sorted":[],"title_canon_sha256":"4e46a86cf43d8201564fdbae6c1ac8ac1de49c4d342c81ce73edf875e1ff2147","abstract_canon_sha256":"ea1336ca139cf543fe05a25a8b1ba23b39ac431b5a8d5b4d4c89f245e0e2fb6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:39.272235Z","signature_b64":"a5q4tHOmB3zvaGWPP/Ua7ybb9i60dUrTR4ZhQrlwQSssNC+o4JolqKnKU+sXu//oAP2Hf3WAOPON/4nOjXmXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a5166af5c4ae62ec36d2561ca37060676f9116fda8e2d5632288ba8a65a9748","last_reissued_at":"2026-05-18T00:30:39.271539Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:39.271539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"K-groups: A Generalization of K-means Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Maria L. Rizzo, Songzi Li","submitted_at":"2017-11-12T21:18:12Z","abstract_excerpt":"We propose a new class of distribution-based clustering algorithms, called k-groups, based on energy distance between samples. The energy distance clustering criterion assigns observations to clusters according to a multi-sample energy statistic that measures the distance between distributions. The energy distance determines a consistent test for equality of distributions, and it is based on a population distance that characterizes equality of distributions. The k-groups procedure therefore generalizes the k-means method, which separates clusters that have different means. We propose two k-gro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04359","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":""},"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":"1711.04359","created_at":"2026-05-18T00:30:39.271652+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04359v1","created_at":"2026-05-18T00:30:39.271652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04359","created_at":"2026-05-18T00:30:39.271652+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJIWNL24JLTC","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJIWNL24JLTC5Q3N","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJIWNL24","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20681","citing_title":"Scale-Calibrated Median-of-Means for Robust Distributed Principal Component Analysis","ref_index":87,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08001","citing_title":"Scale selection for geometric medians on product manifolds","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00363","citing_title":"Profile Likelihood Inference for Anisotropic Hyperbolic Wrapped Normal Models on Hyperbolic Space","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03266","citing_title":"Intrinsic effective sample size for manifold-valued Markov chain Monte Carlo via kernel discrepancy","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJIWNL24JLTC5Q3NEVQ4UNYGAZ","json":"https://pith.science/pith/DJIWNL24JLTC5Q3NEVQ4UNYGAZ.json","graph_json":"https://pith.science/api/pith-number/DJIWNL24JLTC5Q3NEVQ4UNYGAZ/graph.json","events_json":"https://pith.science/api/pith-number/DJIWNL24JLTC5Q3NEVQ4UNYGAZ/events.json","paper":"https://pith.science/paper/DJIWNL24"},"agent_actions":{"view_html":"https://pith.science/pith/DJIWNL24JLTC5Q3NEVQ4UNYGAZ","download_json":"https://pith.science/pith/DJIWNL24JLTC5Q3NEVQ4UNYGAZ.json","view_paper":"https://pith.science/paper/DJIWNL24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04359&json=true","fetch_graph":"https://pith.science/api/pith-number/DJIWNL24JLTC5Q3NEVQ4UNYGAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DJIWNL24JLTC5Q3NEVQ4UNYGAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJIWNL24JLTC5Q3NEVQ4UNYGAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJIWNL24JLTC5Q3NEVQ4UNYGAZ/action/storage_attestation","attest_author":"https://pith.science/pith/DJIWNL24JLTC5Q3NEVQ4UNYGAZ/action/author_attestation","sign_citation":"https://pith.science/pith/DJIWNL24JLTC5Q3NEVQ4UNYGAZ/action/citation_signature","submit_replication":"https://pith.science/pith/DJIWNL24JLTC5Q3NEVQ4UNYGAZ/action/replication_record"}},"created_at":"2026-05-18T00:30:39.271652+00:00","updated_at":"2026-05-18T00:30:39.271652+00:00"}