{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:T3EUFXLQRHP4CAIBHAV5LY34Z7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"623b4cb45a910420632c0821072e2f083e6f99f42b2aeb270084bd3c51b355c2","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2014-07-20T03:41:25Z","title_canon_sha256":"b9fed715bbc629f7b41b59227caed54130c052ec4f40bfb743c89f600b44add4"},"schema_version":"1.0","source":{"id":"1407.5241","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.5241","created_at":"2026-05-18T01:24:14Z"},{"alias_kind":"arxiv_version","alias_value":"1407.5241v3","created_at":"2026-05-18T01:24:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.5241","created_at":"2026-05-18T01:24:14Z"},{"alias_kind":"pith_short_12","alias_value":"T3EUFXLQRHP4","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"T3EUFXLQRHP4CAIB","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"T3EUFXLQ","created_at":"2026-05-18T12:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:9abd2e4056d69a5c37457af324f29185c0bafbe486a9a4aee139cac429902a66","target":"graph","created_at":"2026-05-18T01:24:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We consider a clustering problem where we observe feature vectors $X_i \\in R^p$, $i = 1, 2, \\ldots, n$, from $K$ possible classes. The class labels are unknown and the main interest is to estimate them. We are primarily interested in the modern regime of $p \\gg n$, where classical clustering methods face challenges.\n  We propose Influential Features PCA (IF-PCA) as a new clustering procedure. In IF-PCA, we select a small fraction of features with the largest Kolmogorov-Smirnov (KS) scores, where the threshold is chosen by adapting the recent notion of Higher Criticism, obtain the first $(K-1)$","authors_text":"Jiashun Jin, Wanjie Wang","cross_cats":["math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2014-07-20T03:41:25Z","title":"Influential Feature PCA for high dimensional clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.5241","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1000d6065e0d16b48361538fcddfc85bb7c013182716043fa82f978e37cc6adb","target":"record","created_at":"2026-05-18T01:24:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"623b4cb45a910420632c0821072e2f083e6f99f42b2aeb270084bd3c51b355c2","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2014-07-20T03:41:25Z","title_canon_sha256":"b9fed715bbc629f7b41b59227caed54130c052ec4f40bfb743c89f600b44add4"},"schema_version":"1.0","source":{"id":"1407.5241","kind":"arxiv","version":3}},"canonical_sha256":"9ec942dd7089dfc10101382bd5e37ccff1c7e68cc7b5fd1a838107d369c9003b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ec942dd7089dfc10101382bd5e37ccff1c7e68cc7b5fd1a838107d369c9003b","first_computed_at":"2026-05-18T01:24:14.776296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:24:14.776296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gkjllsMN8T0ExWL5hN/h30XkzeCc16oTaBpwnA+AC9O8Z6n1wnfuqgoDTgmTx4PG8Dl88ZMSIESEtQw2IKLdBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:24:14.776933Z","signed_message":"canonical_sha256_bytes"},"source_id":"1407.5241","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1000d6065e0d16b48361538fcddfc85bb7c013182716043fa82f978e37cc6adb","sha256:9abd2e4056d69a5c37457af324f29185c0bafbe486a9a4aee139cac429902a66"],"state_sha256":"739389b0f521c1c9d4075a82f8b76ce9b8a45188ac4a22cab68ab34fcb0e0a4d"}