{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:HFDDGZIAWDPZNIWA26SHVNFT26","short_pith_number":"pith:HFDDGZIA","schema_version":"1.0","canonical_sha256":"3946336500b0df96a2c0d7a47ab4b3d79bd82fc5173f41328cce1b188630b6b2","source":{"kind":"arxiv","id":"1301.7401","version":2},"attestation_state":"computed","paper":{"title":"An Experimental Comparison of Several Clustering and Initialization Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Heckerman, Marina Meila","submitted_at":"2013-01-30T15:05:55Z","abstract_excerpt":"We examine methods for clustering in high dimensions. In the first part of the paper, we perform an experimental comparison between three batch clustering algorithms: the Expectation-Maximization (EM) algorithm, a winner take all version of the EM algorithm reminiscent of the K-means algorithm, and model-based hierarchical agglomerative clustering. We learn naive-Bayes models with a hidden root node, using high-dimensional discrete-variable data sets (both real and synthetic). We find that the EM algorithm significantly outperforms the other methods, and proceed to investigate the effect of va"},"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":"1301.7401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-30T15:05:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"96f7b42edae1f34ba03e8714d60860e02440777e22dc44c64824d266e8275f20","abstract_canon_sha256":"c8f1d1fb207d5a5af8eb29b51c02690ae104da7d50d77fed0c5fd6c503df0669"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:07:32.454037Z","signature_b64":"AaKENJ073OJFOG19JO8GqSrAmmW0rEFxaI+bfVWtbjmmWfupr2F+8ca1Zz+vovOx0t6mEFom69HR7dLETEqZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3946336500b0df96a2c0d7a47ab4b3d79bd82fc5173f41328cce1b188630b6b2","last_reissued_at":"2026-05-18T02:07:32.453612Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:07:32.453612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Experimental Comparison of Several Clustering and Initialization Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Heckerman, Marina Meila","submitted_at":"2013-01-30T15:05:55Z","abstract_excerpt":"We examine methods for clustering in high dimensions. In the first part of the paper, we perform an experimental comparison between three batch clustering algorithms: the Expectation-Maximization (EM) algorithm, a winner take all version of the EM algorithm reminiscent of the K-means algorithm, and model-based hierarchical agglomerative clustering. We learn naive-Bayes models with a hidden root node, using high-dimensional discrete-variable data sets (both real and synthetic). We find that the EM algorithm significantly outperforms the other methods, and proceed to investigate the effect of va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.7401","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":""},"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":"1301.7401","created_at":"2026-05-18T02:07:32.453672+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.7401v2","created_at":"2026-05-18T02:07:32.453672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.7401","created_at":"2026-05-18T02:07:32.453672+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFDDGZIAWDPZ","created_at":"2026-05-18T12:27:46.883200+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFDDGZIAWDPZNIWA","created_at":"2026-05-18T12:27:46.883200+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFDDGZIA","created_at":"2026-05-18T12:27:46.883200+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/HFDDGZIAWDPZNIWA26SHVNFT26","json":"https://pith.science/pith/HFDDGZIAWDPZNIWA26SHVNFT26.json","graph_json":"https://pith.science/api/pith-number/HFDDGZIAWDPZNIWA26SHVNFT26/graph.json","events_json":"https://pith.science/api/pith-number/HFDDGZIAWDPZNIWA26SHVNFT26/events.json","paper":"https://pith.science/paper/HFDDGZIA"},"agent_actions":{"view_html":"https://pith.science/pith/HFDDGZIAWDPZNIWA26SHVNFT26","download_json":"https://pith.science/pith/HFDDGZIAWDPZNIWA26SHVNFT26.json","view_paper":"https://pith.science/paper/HFDDGZIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.7401&json=true","fetch_graph":"https://pith.science/api/pith-number/HFDDGZIAWDPZNIWA26SHVNFT26/graph.json","fetch_events":"https://pith.science/api/pith-number/HFDDGZIAWDPZNIWA26SHVNFT26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFDDGZIAWDPZNIWA26SHVNFT26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFDDGZIAWDPZNIWA26SHVNFT26/action/storage_attestation","attest_author":"https://pith.science/pith/HFDDGZIAWDPZNIWA26SHVNFT26/action/author_attestation","sign_citation":"https://pith.science/pith/HFDDGZIAWDPZNIWA26SHVNFT26/action/citation_signature","submit_replication":"https://pith.science/pith/HFDDGZIAWDPZNIWA26SHVNFT26/action/replication_record"}},"created_at":"2026-05-18T02:07:32.453672+00:00","updated_at":"2026-05-18T02:07:32.453672+00:00"}