{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ECTXVY5HKWMWPDBM4COCGVZ7HE","short_pith_number":"pith:ECTXVY5H","schema_version":"1.0","canonical_sha256":"20a77ae3a75599678c2ce09c23573f39288959e75a734113bd6313f4d8f78786","source":{"kind":"arxiv","id":"2111.06985","version":2},"attestation_state":"computed","paper":{"title":"Nonparametric Bayesian Knockoff Generators for Feature Selection Under Complex Data Structure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Anjishnu Banerjee, Michael J. Martens, Xinran Qi, Yushu Shi","submitted_at":"2021-11-12T23:42:12Z","abstract_excerpt":"The recent proliferation of high-dimensional data, such as electronic health records and genetics data, offers new opportunities to find novel predictors of outcomes. Presented with a large set of candidate features, interest often lies in selecting the ones most likely to be predictive of an outcome for further study. Controlling the false discovery rate (FDR) at a specified level is often desired in evaluating these variables. Knockoff filtering is an innovative strategy for conducting FDR-controlled feature selection. This paper proposes a nonparametric Bayesian model for generating high-qu"},"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":"2111.06985","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2021-11-12T23:42:12Z","cross_cats_sorted":[],"title_canon_sha256":"a7491c7eb85224ef52908409ffbaa3f51387257b0d500afd24bf461e15d9545f","abstract_canon_sha256":"42a4355c9cd8b94465effda67b13abc55679ffd6fe1b3807105afc7d5b5bb176"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:48.280627Z","signature_b64":"5+K1NBlG62CuH4efQhm1wx2f7RPaWqOoTYYsereaYIa7kxl//d2HexjSh7NBLP676QUZbNBrqrK9uA9JZjU+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20a77ae3a75599678c2ce09c23573f39288959e75a734113bd6313f4d8f78786","last_reissued_at":"2026-07-05T09:09:48.280002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:48.280002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonparametric Bayesian Knockoff Generators for Feature Selection Under Complex Data Structure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Anjishnu Banerjee, Michael J. Martens, Xinran Qi, Yushu Shi","submitted_at":"2021-11-12T23:42:12Z","abstract_excerpt":"The recent proliferation of high-dimensional data, such as electronic health records and genetics data, offers new opportunities to find novel predictors of outcomes. Presented with a large set of candidate features, interest often lies in selecting the ones most likely to be predictive of an outcome for further study. Controlling the false discovery rate (FDR) at a specified level is often desired in evaluating these variables. Knockoff filtering is an innovative strategy for conducting FDR-controlled feature selection. This paper proposes a nonparametric Bayesian model for generating high-qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06985","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/2111.06985/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":"2111.06985","created_at":"2026-07-05T09:09:48.280067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.06985v2","created_at":"2026-07-05T09:09:48.280067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06985","created_at":"2026-07-05T09:09:48.280067+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECTXVY5HKWMW","created_at":"2026-07-05T09:09:48.280067+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECTXVY5HKWMWPDBM","created_at":"2026-07-05T09:09:48.280067+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECTXVY5H","created_at":"2026-07-05T09:09:48.280067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14881","citing_title":"Compute-Optimal Scaling for Value-Based Deep RL","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECTXVY5HKWMWPDBM4COCGVZ7HE","json":"https://pith.science/pith/ECTXVY5HKWMWPDBM4COCGVZ7HE.json","graph_json":"https://pith.science/api/pith-number/ECTXVY5HKWMWPDBM4COCGVZ7HE/graph.json","events_json":"https://pith.science/api/pith-number/ECTXVY5HKWMWPDBM4COCGVZ7HE/events.json","paper":"https://pith.science/paper/ECTXVY5H"},"agent_actions":{"view_html":"https://pith.science/pith/ECTXVY5HKWMWPDBM4COCGVZ7HE","download_json":"https://pith.science/pith/ECTXVY5HKWMWPDBM4COCGVZ7HE.json","view_paper":"https://pith.science/paper/ECTXVY5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.06985&json=true","fetch_graph":"https://pith.science/api/pith-number/ECTXVY5HKWMWPDBM4COCGVZ7HE/graph.json","fetch_events":"https://pith.science/api/pith-number/ECTXVY5HKWMWPDBM4COCGVZ7HE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECTXVY5HKWMWPDBM4COCGVZ7HE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECTXVY5HKWMWPDBM4COCGVZ7HE/action/storage_attestation","attest_author":"https://pith.science/pith/ECTXVY5HKWMWPDBM4COCGVZ7HE/action/author_attestation","sign_citation":"https://pith.science/pith/ECTXVY5HKWMWPDBM4COCGVZ7HE/action/citation_signature","submit_replication":"https://pith.science/pith/ECTXVY5HKWMWPDBM4COCGVZ7HE/action/replication_record"}},"created_at":"2026-07-05T09:09:48.280067+00:00","updated_at":"2026-07-05T09:09:48.280067+00:00"}