{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YCSBN7WJHFEU6EBAQOSYA3HYPY","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":"07e5c184d2415c921ff3d3fcaa18a82f2e2ec62d62c2557dceedf15e0b74dd7f","cross_cats_sorted":["cs.CC","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T17:50:15Z","title_canon_sha256":"615f0da9609e496a083df1a0473d252f9380a9105bb110e5818b679b0ef5c4c1"},"schema_version":"1.0","source":{"id":"2505.04604","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04604","created_at":"2026-07-05T11:40:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04604v2","created_at":"2026-07-05T11:40:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04604","created_at":"2026-07-05T11:40:54Z"},{"alias_kind":"pith_short_12","alias_value":"YCSBN7WJHFEU","created_at":"2026-07-05T11:40:54Z"},{"alias_kind":"pith_short_16","alias_value":"YCSBN7WJHFEU6EBA","created_at":"2026-07-05T11:40:54Z"},{"alias_kind":"pith_short_8","alias_value":"YCSBN7WJ","created_at":"2026-07-05T11:40:54Z"}],"graph_snapshots":[{"event_id":"sha256:6c097179bb0d2591af7b7f2eddc475b060f2036febaa5e3e35974001fb712029","target":"graph","created_at":"2026-07-05T11:40:54Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.04604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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). ","authors_text":"Caleb Koch, Lorenzo Beretta, Nathaniel Harms","cross_cats":["cs.CC","cs.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T17:50:15Z","title":"Feature Selection and Junta Testing are Statistically Equivalent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04604","kind":"arxiv","version":2},"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:b2cfa0e5a3face3532799e2567ab4bf152eed11948ab1e238f4df0bcdf637cb8","target":"record","created_at":"2026-07-05T11:40:54Z","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":"07e5c184d2415c921ff3d3fcaa18a82f2e2ec62d62c2557dceedf15e0b74dd7f","cross_cats_sorted":["cs.CC","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T17:50:15Z","title_canon_sha256":"615f0da9609e496a083df1a0473d252f9380a9105bb110e5818b679b0ef5c4c1"},"schema_version":"1.0","source":{"id":"2505.04604","kind":"arxiv","version":2}},"canonical_sha256":"c0a416fec939494f102083a5806cf87e097604ff70dd47d9d6763dee951c5a11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0a416fec939494f102083a5806cf87e097604ff70dd47d9d6763dee951c5a11","first_computed_at":"2026-07-05T11:40:54.676607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:54.676607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KM0/mFLkA6uvAZCA+JasnwfwP3i9ezJKGWZFE7vEwVlM14v7neEr1pEimXG4CzXUrECdFddNSEdvj+JOdikFCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:54.677106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04604","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2cfa0e5a3face3532799e2567ab4bf152eed11948ab1e238f4df0bcdf637cb8","sha256:6c097179bb0d2591af7b7f2eddc475b060f2036febaa5e3e35974001fb712029"],"state_sha256":"cd57410f90b460d97ca28b2ae26cb1b8823711e0f51e13c7e52b36f3b9bff823"}