{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PGBJCS54HUAXFIEBEHOKRQ5G43","short_pith_number":"pith:PGBJCS54","schema_version":"1.0","canonical_sha256":"7982914bbc3d0172a08121dca8c3a6e6ddaa6ce13331963617624f73c78a04b0","source":{"kind":"arxiv","id":"2605.22973","version":1},"attestation_state":"computed","paper":{"title":"Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arthur Zimek, Michael E. Houle, Muhammad Rajabinasab, Oussama Chelly","submitted_at":"2026-05-21T19:04:54Z","abstract_excerpt":"Many novel unsupervised feature selection methods are proposed each year, yet their empirical evaluation is limited to supervised and unsupervised evaluation metrics computed on selected datasets, along with comparisons to existing methods. However, in the absence of an established evaluation baseline, it is difficult to determine the value added to the existing literature by each of these methods, and how effective their underlying approaches are. We propose using random feature selection as a baseline for evaluating the unsupervised feature selection methods. We empirically show that many of"},"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":"2605.22973","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T19:04:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa9cafa33ca6d9d8a44fb18f9e4865d42e0fdda2daff3629dc288f66cafd2809","abstract_canon_sha256":"a85f1088eb01ff8b17283dbc7b3ebd45ff4d7988ee405b97f560ba0c07672587"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:32.773751Z","signature_b64":"j4u18b42LDHCCZWJR8pHECgTkbLMOgHKgqfwOJqYwbrt7tknGF/l5Km+a+aCzqhZVBt6Z5Gx99LhqEzk4fRQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7982914bbc3d0172a08121dca8c3a6e6ddaa6ce13331963617624f73c78a04b0","last_reissued_at":"2026-05-25T02:01:32.773067Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:32.773067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arthur Zimek, Michael E. Houle, Muhammad Rajabinasab, Oussama Chelly","submitted_at":"2026-05-21T19:04:54Z","abstract_excerpt":"Many novel unsupervised feature selection methods are proposed each year, yet their empirical evaluation is limited to supervised and unsupervised evaluation metrics computed on selected datasets, along with comparisons to existing methods. However, in the absence of an established evaluation baseline, it is difficult to determine the value added to the existing literature by each of these methods, and how effective their underlying approaches are. We propose using random feature selection as a baseline for evaluating the unsupervised feature selection methods. We empirically show that many of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22973","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/2605.22973/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":"2605.22973","created_at":"2026-05-25T02:01:32.773169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22973v1","created_at":"2026-05-25T02:01:32.773169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22973","created_at":"2026-05-25T02:01:32.773169+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGBJCS54HUAX","created_at":"2026-05-25T02:01:32.773169+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGBJCS54HUAXFIEB","created_at":"2026-05-25T02:01:32.773169+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGBJCS54","created_at":"2026-05-25T02:01:32.773169+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/PGBJCS54HUAXFIEBEHOKRQ5G43","json":"https://pith.science/pith/PGBJCS54HUAXFIEBEHOKRQ5G43.json","graph_json":"https://pith.science/api/pith-number/PGBJCS54HUAXFIEBEHOKRQ5G43/graph.json","events_json":"https://pith.science/api/pith-number/PGBJCS54HUAXFIEBEHOKRQ5G43/events.json","paper":"https://pith.science/paper/PGBJCS54"},"agent_actions":{"view_html":"https://pith.science/pith/PGBJCS54HUAXFIEBEHOKRQ5G43","download_json":"https://pith.science/pith/PGBJCS54HUAXFIEBEHOKRQ5G43.json","view_paper":"https://pith.science/paper/PGBJCS54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22973&json=true","fetch_graph":"https://pith.science/api/pith-number/PGBJCS54HUAXFIEBEHOKRQ5G43/graph.json","fetch_events":"https://pith.science/api/pith-number/PGBJCS54HUAXFIEBEHOKRQ5G43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGBJCS54HUAXFIEBEHOKRQ5G43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGBJCS54HUAXFIEBEHOKRQ5G43/action/storage_attestation","attest_author":"https://pith.science/pith/PGBJCS54HUAXFIEBEHOKRQ5G43/action/author_attestation","sign_citation":"https://pith.science/pith/PGBJCS54HUAXFIEBEHOKRQ5G43/action/citation_signature","submit_replication":"https://pith.science/pith/PGBJCS54HUAXFIEBEHOKRQ5G43/action/replication_record"}},"created_at":"2026-05-25T02:01:32.773169+00:00","updated_at":"2026-05-25T02:01:32.773169+00:00"}