{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:45ENPZFPMFT53PULP3DAYSENS7","short_pith_number":"pith:45ENPZFP","schema_version":"1.0","canonical_sha256":"e748d7e4af6167ddbe8b7ec60c488d97f4d7bfb8a2c9a86a4a35850546fe14a2","source":{"kind":"arxiv","id":"2112.00706","version":1},"attestation_state":"computed","paper":{"title":"Clustering Mixtures with Almost Optimal Separation in Polynomial Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Allen Liu, Jerry Li","submitted_at":"2021-12-01T18:34:09Z","abstract_excerpt":"We consider the problem of clustering mixtures of mean-separated Gaussians in high dimensions. We are given samples from a mixture of $k$ identity covariance Gaussians, so that the minimum pairwise distance between any two pairs of means is at least $\\Delta$, for some parameter $\\Delta > 0$, and the goal is to recover the ground truth clustering of these samples. It is folklore that separation $\\Delta = \\Theta (\\sqrt{\\log k})$ is both necessary and sufficient to recover a good clustering, at least information theoretically. However, the estimators which achieve this guarantee are inefficient. "},"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":"2112.00706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2021-12-01T18:34:09Z","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"3cca05993054c622f18dfe405ad310e4a5d36b7ca98ee587e11c4a105a501d73","abstract_canon_sha256":"8620fb2a40ac36e8d130bbb8ccc99677af18b3029c17d3b6550303cd81a096ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:49.549140Z","signature_b64":"caIz1/BWlhW3NFYGwaGDwzS45dkIrAidiINgEU6KfbTgdm2ZtFG7+T+xVS+8J26Chib529CoXnSShtAWKayMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e748d7e4af6167ddbe8b7ec60c488d97f4d7bfb8a2c9a86a4a35850546fe14a2","last_reissued_at":"2026-07-05T03:36:49.548698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:49.548698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustering Mixtures with Almost Optimal Separation in Polynomial Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Allen Liu, Jerry Li","submitted_at":"2021-12-01T18:34:09Z","abstract_excerpt":"We consider the problem of clustering mixtures of mean-separated Gaussians in high dimensions. We are given samples from a mixture of $k$ identity covariance Gaussians, so that the minimum pairwise distance between any two pairs of means is at least $\\Delta$, for some parameter $\\Delta > 0$, and the goal is to recover the ground truth clustering of these samples. It is folklore that separation $\\Delta = \\Theta (\\sqrt{\\log k})$ is both necessary and sufficient to recover a good clustering, at least information theoretically. However, the estimators which achieve this guarantee are inefficient. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00706","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/2112.00706/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":"2112.00706","created_at":"2026-07-05T03:36:49.548761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.00706v1","created_at":"2026-07-05T03:36:49.548761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00706","created_at":"2026-07-05T03:36:49.548761+00:00"},{"alias_kind":"pith_short_12","alias_value":"45ENPZFPMFT5","created_at":"2026-07-05T03:36:49.548761+00:00"},{"alias_kind":"pith_short_16","alias_value":"45ENPZFPMFT53PUL","created_at":"2026-07-05T03:36:49.548761+00:00"},{"alias_kind":"pith_short_8","alias_value":"45ENPZFP","created_at":"2026-07-05T03:36:49.548761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15669","citing_title":"Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/45ENPZFPMFT53PULP3DAYSENS7","json":"https://pith.science/pith/45ENPZFPMFT53PULP3DAYSENS7.json","graph_json":"https://pith.science/api/pith-number/45ENPZFPMFT53PULP3DAYSENS7/graph.json","events_json":"https://pith.science/api/pith-number/45ENPZFPMFT53PULP3DAYSENS7/events.json","paper":"https://pith.science/paper/45ENPZFP"},"agent_actions":{"view_html":"https://pith.science/pith/45ENPZFPMFT53PULP3DAYSENS7","download_json":"https://pith.science/pith/45ENPZFPMFT53PULP3DAYSENS7.json","view_paper":"https://pith.science/paper/45ENPZFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.00706&json=true","fetch_graph":"https://pith.science/api/pith-number/45ENPZFPMFT53PULP3DAYSENS7/graph.json","fetch_events":"https://pith.science/api/pith-number/45ENPZFPMFT53PULP3DAYSENS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45ENPZFPMFT53PULP3DAYSENS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45ENPZFPMFT53PULP3DAYSENS7/action/storage_attestation","attest_author":"https://pith.science/pith/45ENPZFPMFT53PULP3DAYSENS7/action/author_attestation","sign_citation":"https://pith.science/pith/45ENPZFPMFT53PULP3DAYSENS7/action/citation_signature","submit_replication":"https://pith.science/pith/45ENPZFPMFT53PULP3DAYSENS7/action/replication_record"}},"created_at":"2026-07-05T03:36:49.548761+00:00","updated_at":"2026-07-05T03:36:49.548761+00:00"}