{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XHENOZMVELLXXPE423XCJWB6UM","short_pith_number":"pith:XHENOZMV","schema_version":"1.0","canonical_sha256":"b9c8d7659522d77bbc9cd6ee24d83ea31b08f81181d06acaa2475086d2d338f7","source":{"kind":"arxiv","id":"2506.06114","version":5},"attestation_state":"computed","paper":{"title":"Scalable unsupervised feature selection via weight stability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Relevant features are assigned consistently higher weights than noise features across a range of Minkowski exponents.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Renato Cordeiro de Amorim, Xudong Zhang","submitted_at":"2025-06-06T14:24:41Z","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"},"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":true},"canonical_record":{"source":{"id":"2506.06114","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T14:24:41Z","cross_cats_sorted":[],"title_canon_sha256":"72d05a9accaec310101eeabfa6a1915cd03553f4d10f5999d5344a6d68cba700","abstract_canon_sha256":"8e38d66333887c54a0fc4dd1813d6a5bc8dd9790d79fff5203ee9b1cc4e6f48b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:10.556703Z","signature_b64":"VF/zucpYKb0BQT+iXkAsqO1mJGcDmwTM0pQmkmapdZkjIDAq6mbPDbGQXrNmaf2LqA8YcFGlqur0t2YPlHFbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9c8d7659522d77bbc9cd6ee24d83ea31b08f81181d06acaa2475086d2d338f7","last_reissued_at":"2026-05-20T00:04:10.555881Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:10.555881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable unsupervised feature selection via weight stability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Relevant features are assigned consistently higher weights than noise features across a range of Minkowski exponents.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Renato Cordeiro de Amorim, Xudong Zhang","submitted_at":"2025-06-06T14:24:41Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Relevant features are assigned consistently higher weights than noise features across a range of Minkowski exponents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"75ebb09882505900bddc2665017a21a72536cb8db59be01d5cf35c3748f1efd0"},"source":{"id":"2506.06114","kind":"arxiv","version":5},"verdict":{"id":"9761e992-79d1-49ac-ada3-a7666dae5802","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T10:26:36.878416Z","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.","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","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.","pith_extraction_headline":"Relevant features are assigned consistently higher weights than noise features across a range of Minkowski exponents."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.06114/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":2,"snapshot_sha256":"5dd76052a0f0cdfcd3d284a62af23465ae65f875659988cb4b5778cf68b1c389"},"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":"2506.06114","created_at":"2026-05-20T00:04:10.556009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06114v5","created_at":"2026-05-20T00:04:10.556009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06114","created_at":"2026-05-20T00:04:10.556009+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHENOZMVELLX","created_at":"2026-05-20T00:04:10.556009+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHENOZMVELLXXPE4","created_at":"2026-05-20T00:04:10.556009+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHENOZMV","created_at":"2026-05-20T00:04:10.556009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHENOZMVELLXXPE423XCJWB6UM","json":"https://pith.science/pith/XHENOZMVELLXXPE423XCJWB6UM.json","graph_json":"https://pith.science/api/pith-number/XHENOZMVELLXXPE423XCJWB6UM/graph.json","events_json":"https://pith.science/api/pith-number/XHENOZMVELLXXPE423XCJWB6UM/events.json","paper":"https://pith.science/paper/XHENOZMV"},"agent_actions":{"view_html":"https://pith.science/pith/XHENOZMVELLXXPE423XCJWB6UM","download_json":"https://pith.science/pith/XHENOZMVELLXXPE423XCJWB6UM.json","view_paper":"https://pith.science/paper/XHENOZMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06114&json=true","fetch_graph":"https://pith.science/api/pith-number/XHENOZMVELLXXPE423XCJWB6UM/graph.json","fetch_events":"https://pith.science/api/pith-number/XHENOZMVELLXXPE423XCJWB6UM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHENOZMVELLXXPE423XCJWB6UM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHENOZMVELLXXPE423XCJWB6UM/action/storage_attestation","attest_author":"https://pith.science/pith/XHENOZMVELLXXPE423XCJWB6UM/action/author_attestation","sign_citation":"https://pith.science/pith/XHENOZMVELLXXPE423XCJWB6UM/action/citation_signature","submit_replication":"https://pith.science/pith/XHENOZMVELLXXPE423XCJWB6UM/action/replication_record"}},"created_at":"2026-05-20T00:04:10.556009+00:00","updated_at":"2026-05-20T00:04:10.556009+00:00"}