{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XHENOZMVELLXXPE423XCJWB6UM","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":"8e38d66333887c54a0fc4dd1813d6a5bc8dd9790d79fff5203ee9b1cc4e6f48b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T14:24:41Z","title_canon_sha256":"72d05a9accaec310101eeabfa6a1915cd03553f4d10f5999d5344a6d68cba700"},"schema_version":"1.0","source":{"id":"2506.06114","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06114","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06114v5","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06114","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"XHENOZMVELLX","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"XHENOZMVELLXXPE4","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"XHENOZMV","created_at":"2026-05-20T00:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:4aeb87d9bc0cd5bade10a07e83758de666cf06cb7149da4b3c3fee5daa03a2f2","target":"graph","created_at":"2026-05-20T00:04:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Under explicit assumptions on noise features and cluster structure, relevant features are assigned consistently higher weights than noise features across a range of Minkowski exponents."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The paper relies on explicit assumptions about the properties of noise features and the underlying cluster structure that allow the weight stability to separate signal from noise."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Proposes FS-MWK++ and scalable SFS-MWK++ for unsupervised feature selection by aggregating stable feature weights from Minkowski weighted k-means++ across exponents, backed by theoretical analysis under noise and cluster assumptions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Relevant features are assigned consistently higher weights than noise features across a range of Minkowski exponents."}],"snapshot_sha256":"75ebb09882505900bddc2665017a21a72536cb8db59be01d5cf35c3748f1efd0"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5dd76052a0f0cdfcd3d284a62af23465ae65f875659988cb4b5778cf68b1c389"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.06114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised feature selection is critical for improving clustering performance in high-dimensional data, where irrelevant features can obscure meaningful structure. In this work, we introduce the Minkowski weighted $k$-means++, a novel initialisation strategy for the Minkowski Weighted $k$-means. Our initialisation selects centroids probabilistically using feature relevance estimates derived from the data itself. Building on this, we propose two new feature selection algorithms, FS-MWK++, which aggregates feature weights across a range of Minkowski exponents to identify stable and informative","authors_text":"Renato Cordeiro de Amorim, Xudong Zhang","cross_cats":[],"headline":"Relevant features are assigned consistently higher weights than noise features across a range of Minkowski exponents.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T14:24:41Z","title":"Scalable unsupervised feature selection via weight stability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06114","kind":"arxiv","version":5},"verdict":{"created_at":"2026-05-19T10:26:36.878416Z","id":"9761e992-79d1-49ac-ada3-a7666dae5802","model_set":{"reader":"grok-4.3"},"one_line_summary":"Proposes FS-MWK++ and scalable SFS-MWK++ for unsupervised feature selection by aggregating stable feature weights from Minkowski weighted k-means++ across exponents, backed by theoretical analysis under noise and cluster assumptions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Relevant features are assigned consistently higher weights than noise features across a range of Minkowski exponents.","strongest_claim":"Under explicit assumptions on noise features and cluster structure, relevant features are assigned consistently higher weights than noise features across a range of Minkowski exponents.","weakest_assumption":"The paper relies on explicit assumptions about the properties of noise features and the underlying cluster structure that allow the weight stability to separate signal from noise."}},"verdict_id":"9761e992-79d1-49ac-ada3-a7666dae5802"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1d7a2523997ea8ce5340ce8e3617d5b83e151626e5df4c595f93fef2cdadcbc7","target":"record","created_at":"2026-05-20T00:04:10Z","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":"8e38d66333887c54a0fc4dd1813d6a5bc8dd9790d79fff5203ee9b1cc4e6f48b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T14:24:41Z","title_canon_sha256":"72d05a9accaec310101eeabfa6a1915cd03553f4d10f5999d5344a6d68cba700"},"schema_version":"1.0","source":{"id":"2506.06114","kind":"arxiv","version":5}},"canonical_sha256":"b9c8d7659522d77bbc9cd6ee24d83ea31b08f81181d06acaa2475086d2d338f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9c8d7659522d77bbc9cd6ee24d83ea31b08f81181d06acaa2475086d2d338f7","first_computed_at":"2026-05-20T00:04:10.555881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:10.555881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VF/zucpYKb0BQT+iXkAsqO1mJGcDmwTM0pQmkmapdZkjIDAq6mbPDbGQXrNmaf2LqA8YcFGlqur0t2YPlHFbAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:10.556703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06114","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d7a2523997ea8ce5340ce8e3617d5b83e151626e5df4c595f93fef2cdadcbc7","sha256:4aeb87d9bc0cd5bade10a07e83758de666cf06cb7149da4b3c3fee5daa03a2f2"],"state_sha256":"ac23dc128e599e70f3e157e27c0842470003a64380b2008bc0e46fd37d679495"}