{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EMWJQV5HHPR4DPYOR545AOUNVY","short_pith_number":"pith:EMWJQV5H","schema_version":"1.0","canonical_sha256":"232c9857a73be3c1bf0e8f79d03a8dae29c29ccbd7959cb35b9126de192739f8","source":{"kind":"arxiv","id":"2212.08766","version":2},"attestation_state":"computed","paper":{"title":"Asymptotically Optimal Knockoff Statistics via the Masked Likelihood Ratio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Asher Spector, William Fithian","submitted_at":"2022-12-17T00:30:55Z","abstract_excerpt":"In feature selection problems, knockoffs are synthetic controls for the original features. Employing knockoffs allows analysts to use nearly any variable importance measure or \"feature statistic\" to select features while rigorously controlling false positives. However, it is not clear which statistic maximizes power. In this paper, we argue that state-of-the-art lasso-based feature statistics often prioritize features that are unlikely to be discovered, leading to low power in real applications. Instead, we introduce masked likelihood ratio (MLR) statistics, which prioritize features according"},"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":"2212.08766","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2022-12-17T00:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"5d2f63bfba3e5fc9d62b93a79a10ef2bedfb97e2611755390e6de20f5bcc0154","abstract_canon_sha256":"5921ad99e6b4b53a63b18a519e13702792ada8814f839df08f215f73beaedda5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:46.480926Z","signature_b64":"up/dkWDpqdSPraZmrVw38EqVhgWizRw8+qASmgzFzDQPqjokNRfQC7AUd++IRjBELkCBVd6i1MYnZ/etQp+nAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"232c9857a73be3c1bf0e8f79d03a8dae29c29ccbd7959cb35b9126de192739f8","last_reissued_at":"2026-07-05T09:13:46.480482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:46.480482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymptotically Optimal Knockoff Statistics via the Masked Likelihood Ratio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Asher Spector, William Fithian","submitted_at":"2022-12-17T00:30:55Z","abstract_excerpt":"In feature selection problems, knockoffs are synthetic controls for the original features. Employing knockoffs allows analysts to use nearly any variable importance measure or \"feature statistic\" to select features while rigorously controlling false positives. However, it is not clear which statistic maximizes power. In this paper, we argue that state-of-the-art lasso-based feature statistics often prioritize features that are unlikely to be discovered, leading to low power in real applications. Instead, we introduce masked likelihood ratio (MLR) statistics, which prioritize features according"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08766","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/2212.08766/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":"2212.08766","created_at":"2026-07-05T09:13:46.480541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08766v2","created_at":"2026-07-05T09:13:46.480541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08766","created_at":"2026-07-05T09:13:46.480541+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMWJQV5HHPR4","created_at":"2026-07-05T09:13:46.480541+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMWJQV5HHPR4DPYO","created_at":"2026-07-05T09:13:46.480541+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMWJQV5H","created_at":"2026-07-05T09:13:46.480541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11548","citing_title":"Estimating the local false discovery rate under an unknown symmetric null","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19517","citing_title":"PRADAS: PRior-Assisted DAta Splitting for False Discovery Rate Control","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMWJQV5HHPR4DPYOR545AOUNVY","json":"https://pith.science/pith/EMWJQV5HHPR4DPYOR545AOUNVY.json","graph_json":"https://pith.science/api/pith-number/EMWJQV5HHPR4DPYOR545AOUNVY/graph.json","events_json":"https://pith.science/api/pith-number/EMWJQV5HHPR4DPYOR545AOUNVY/events.json","paper":"https://pith.science/paper/EMWJQV5H"},"agent_actions":{"view_html":"https://pith.science/pith/EMWJQV5HHPR4DPYOR545AOUNVY","download_json":"https://pith.science/pith/EMWJQV5HHPR4DPYOR545AOUNVY.json","view_paper":"https://pith.science/paper/EMWJQV5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08766&json=true","fetch_graph":"https://pith.science/api/pith-number/EMWJQV5HHPR4DPYOR545AOUNVY/graph.json","fetch_events":"https://pith.science/api/pith-number/EMWJQV5HHPR4DPYOR545AOUNVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMWJQV5HHPR4DPYOR545AOUNVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMWJQV5HHPR4DPYOR545AOUNVY/action/storage_attestation","attest_author":"https://pith.science/pith/EMWJQV5HHPR4DPYOR545AOUNVY/action/author_attestation","sign_citation":"https://pith.science/pith/EMWJQV5HHPR4DPYOR545AOUNVY/action/citation_signature","submit_replication":"https://pith.science/pith/EMWJQV5HHPR4DPYOR545AOUNVY/action/replication_record"}},"created_at":"2026-07-05T09:13:46.480541+00:00","updated_at":"2026-07-05T09:13:46.480541+00:00"}