{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:CA7DWSWHTOXE2QEBZAGFHEA7YN","short_pith_number":"pith:CA7DWSWH","schema_version":"1.0","canonical_sha256":"103e3b4ac79bae4d4081c80c53901fc36ff6317da836e452e1af43648218825a","source":{"kind":"arxiv","id":"1302.1552","version":1},"attestation_state":"computed","paper":{"title":"An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Y. Ng, Michael Kearns, Yishay Mansour","submitted_at":"2013-02-06T15:57:20Z","abstract_excerpt":"Assignment methods are at the heart of many algorithms for unsupervised learning and clustering - in particular, the well-known K-means and Expectation-Maximization (EM) algorithms.  In this work, we study several different methods of assignment, including the \"hard\" assignments used by K-means and the ?soft' assignments used by EM. While it is known that K-means minimizes the distortion on the data and EM maximizes the likelihood, little is known about the systematic differences of behavior between the two algorithms. Here we shed light on these differences via an information-theoretic analys"},"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":"1302.1552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-02-06T15:57:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"42c4650a9ebbdd3b219c65c3bfd580bf26a8b4ac0e4d4505a9fe133ec2009570","abstract_canon_sha256":"f82d674e2b987ae13e487cec2055f7a604f10688ee4910bb1b176582340650f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:34:15.593069Z","signature_b64":"rQ/+ALVitJVBIndxwbAsu2ZZaV195sEckz+HMih/4PfErnseMOJHfPgrngpmPB2hj3Bp4GVZ2XKBCzAyPWTfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"103e3b4ac79bae4d4081c80c53901fc36ff6317da836e452e1af43648218825a","last_reissued_at":"2026-05-18T03:34:15.592362Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:34:15.592362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Y. Ng, Michael Kearns, Yishay Mansour","submitted_at":"2013-02-06T15:57:20Z","abstract_excerpt":"Assignment methods are at the heart of many algorithms for unsupervised learning and clustering - in particular, the well-known K-means and Expectation-Maximization (EM) algorithms.  In this work, we study several different methods of assignment, including the \"hard\" assignments used by K-means and the ?soft' assignments used by EM. While it is known that K-means minimizes the distortion on the data and EM maximizes the likelihood, little is known about the systematic differences of behavior between the two algorithms. Here we shed light on these differences via an information-theoretic analys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1302.1552","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":"1302.1552","created_at":"2026-05-18T03:34:15.592485+00:00"},{"alias_kind":"arxiv_version","alias_value":"1302.1552v1","created_at":"2026-05-18T03:34:15.592485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1302.1552","created_at":"2026-05-18T03:34:15.592485+00:00"},{"alias_kind":"pith_short_12","alias_value":"CA7DWSWHTOXE","created_at":"2026-05-18T12:27:40.988391+00:00"},{"alias_kind":"pith_short_16","alias_value":"CA7DWSWHTOXE2QEB","created_at":"2026-05-18T12:27:40.988391+00:00"},{"alias_kind":"pith_short_8","alias_value":"CA7DWSWH","created_at":"2026-05-18T12:27:40.988391+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/CA7DWSWHTOXE2QEBZAGFHEA7YN","json":"https://pith.science/pith/CA7DWSWHTOXE2QEBZAGFHEA7YN.json","graph_json":"https://pith.science/api/pith-number/CA7DWSWHTOXE2QEBZAGFHEA7YN/graph.json","events_json":"https://pith.science/api/pith-number/CA7DWSWHTOXE2QEBZAGFHEA7YN/events.json","paper":"https://pith.science/paper/CA7DWSWH"},"agent_actions":{"view_html":"https://pith.science/pith/CA7DWSWHTOXE2QEBZAGFHEA7YN","download_json":"https://pith.science/pith/CA7DWSWHTOXE2QEBZAGFHEA7YN.json","view_paper":"https://pith.science/paper/CA7DWSWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1302.1552&json=true","fetch_graph":"https://pith.science/api/pith-number/CA7DWSWHTOXE2QEBZAGFHEA7YN/graph.json","fetch_events":"https://pith.science/api/pith-number/CA7DWSWHTOXE2QEBZAGFHEA7YN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CA7DWSWHTOXE2QEBZAGFHEA7YN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CA7DWSWHTOXE2QEBZAGFHEA7YN/action/storage_attestation","attest_author":"https://pith.science/pith/CA7DWSWHTOXE2QEBZAGFHEA7YN/action/author_attestation","sign_citation":"https://pith.science/pith/CA7DWSWHTOXE2QEBZAGFHEA7YN/action/citation_signature","submit_replication":"https://pith.science/pith/CA7DWSWHTOXE2QEBZAGFHEA7YN/action/replication_record"}},"created_at":"2026-05-18T03:34:15.592485+00:00","updated_at":"2026-05-18T03:34:15.592485+00:00"}