{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCSBN7WJHFEU6EBAQOSYA3HYPY","short_pith_number":"pith:YCSBN7WJ","schema_version":"1.0","canonical_sha256":"c0a416fec939494f102083a5806cf87e097604ff70dd47d9d6763dee951c5a11","source":{"kind":"arxiv","id":"2505.04604","version":2},"attestation_state":"computed","paper":{"title":"Feature Selection and Junta Testing are Statistically Equivalent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Caleb Koch, Lorenzo Beretta, Nathaniel Harms","submitted_at":"2025-05-07T17:50:15Z","abstract_excerpt":"For a function $f \\colon \\{0,1\\}^n \\to \\{0,1\\}$, the junta testing problem asks whether $f$ depends on only $k$ variables. If $f$ depends on only $k$ variables, the feature selection problem asks to find those variables. We prove that these two tasks are statistically equivalent. Specifically, we show that the ``brute-force'' algorithm, which checks for any set of $k$ variables consistent with the sample, is simultaneously sample-optimal for both problems, and the optimal sample size is \\[ \\Theta\\left(\\frac 1 \\varepsilon \\left( \\sqrt{2^k \\log {n \\choose k}} + \\log {n \\choose k}\\right)\\right). "},"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":"2505.04604","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T17:50:15Z","cross_cats_sorted":["cs.CC","cs.DS","stat.ML"],"title_canon_sha256":"615f0da9609e496a083df1a0473d252f9380a9105bb110e5818b679b0ef5c4c1","abstract_canon_sha256":"07e5c184d2415c921ff3d3fcaa18a82f2e2ec62d62c2557dceedf15e0b74dd7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:54.677106Z","signature_b64":"KM0/mFLkA6uvAZCA+JasnwfwP3i9ezJKGWZFE7vEwVlM14v7neEr1pEimXG4CzXUrECdFddNSEdvj+JOdikFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0a416fec939494f102083a5806cf87e097604ff70dd47d9d6763dee951c5a11","last_reissued_at":"2026-07-05T11:40:54.676607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:54.676607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Selection and Junta Testing are Statistically Equivalent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Caleb Koch, Lorenzo Beretta, Nathaniel Harms","submitted_at":"2025-05-07T17:50:15Z","abstract_excerpt":"For a function $f \\colon \\{0,1\\}^n \\to \\{0,1\\}$, the junta testing problem asks whether $f$ depends on only $k$ variables. If $f$ depends on only $k$ variables, the feature selection problem asks to find those variables. We prove that these two tasks are statistically equivalent. Specifically, we show that the ``brute-force'' algorithm, which checks for any set of $k$ variables consistent with the sample, is simultaneously sample-optimal for both problems, and the optimal sample size is \\[ \\Theta\\left(\\frac 1 \\varepsilon \\left( \\sqrt{2^k \\log {n \\choose k}} + \\log {n \\choose k}\\right)\\right). "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04604","kind":"arxiv","version":2},"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/2505.04604/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":"2505.04604","created_at":"2026-07-05T11:40:54.676666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04604v2","created_at":"2026-07-05T11:40:54.676666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04604","created_at":"2026-07-05T11:40:54.676666+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCSBN7WJHFEU","created_at":"2026-07-05T11:40:54.676666+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCSBN7WJHFEU6EBA","created_at":"2026-07-05T11:40:54.676666+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCSBN7WJ","created_at":"2026-07-05T11:40:54.676666+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/YCSBN7WJHFEU6EBAQOSYA3HYPY","json":"https://pith.science/pith/YCSBN7WJHFEU6EBAQOSYA3HYPY.json","graph_json":"https://pith.science/api/pith-number/YCSBN7WJHFEU6EBAQOSYA3HYPY/graph.json","events_json":"https://pith.science/api/pith-number/YCSBN7WJHFEU6EBAQOSYA3HYPY/events.json","paper":"https://pith.science/paper/YCSBN7WJ"},"agent_actions":{"view_html":"https://pith.science/pith/YCSBN7WJHFEU6EBAQOSYA3HYPY","download_json":"https://pith.science/pith/YCSBN7WJHFEU6EBAQOSYA3HYPY.json","view_paper":"https://pith.science/paper/YCSBN7WJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04604&json=true","fetch_graph":"https://pith.science/api/pith-number/YCSBN7WJHFEU6EBAQOSYA3HYPY/graph.json","fetch_events":"https://pith.science/api/pith-number/YCSBN7WJHFEU6EBAQOSYA3HYPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCSBN7WJHFEU6EBAQOSYA3HYPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCSBN7WJHFEU6EBAQOSYA3HYPY/action/storage_attestation","attest_author":"https://pith.science/pith/YCSBN7WJHFEU6EBAQOSYA3HYPY/action/author_attestation","sign_citation":"https://pith.science/pith/YCSBN7WJHFEU6EBAQOSYA3HYPY/action/citation_signature","submit_replication":"https://pith.science/pith/YCSBN7WJHFEU6EBAQOSYA3HYPY/action/replication_record"}},"created_at":"2026-07-05T11:40:54.676666+00:00","updated_at":"2026-07-05T11:40:54.676666+00:00"}