{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M5QFQ7LY7J6LLXHJTNLNRYXZ7V","short_pith_number":"pith:M5QFQ7LY","schema_version":"1.0","canonical_sha256":"6760587d78fa7cb5dce99b56d8e2f9fd74f260cc06eb84aa21e5001cc65cf46b","source":{"kind":"arxiv","id":"2601.23124","version":2},"attestation_state":"computed","paper":{"title":"Semi-knockoffs: a model-agnostic conditional independence testing method with finite-sample guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Angel Reyero-Lobo, Bertrand Thirion, Pierre Neuvial","submitted_at":"2026-01-30T16:10:26Z","abstract_excerpt":"Conditional independence testing (CIT) is essential for reliable scientific discovery. It prevents spurious findings and enables controlled feature selection. Recent CIT methods have used machine learning (ML) models as surrogates of the underlying distribution. However, model-agnostic approaches require a train-test split, which reduces statistical power. We introduce Semi-knockoffs, a CIT method that can accommodate any pre-trained model, avoids this split, and provides valid p-values and false discovery rate (FDR) control for high-dimensional settings. Unlike methods that rely on the model-"},"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":"2601.23124","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2026-01-30T16:10:26Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"37ee52b5064e24781e3f7e4f01281b9c73b9181ef41b8f522b637770415fc531","abstract_canon_sha256":"bb6e4807a5b57fde2a864d3c3809e907e3c39a86b9fd9f0d6b588112fc6e195a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:20.499090Z","signature_b64":"fzhhLTOjDSOk6+oO/bwrlwhWWTp5ZseB9xd9suVqvqGXrhR909v4WYrOjjkULHLH1XCdS2mhW12a+xlrBUyCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6760587d78fa7cb5dce99b56d8e2f9fd74f260cc06eb84aa21e5001cc65cf46b","last_reissued_at":"2026-06-23T02:13:20.498616Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:20.498616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-knockoffs: a model-agnostic conditional independence testing method with finite-sample guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Angel Reyero-Lobo, Bertrand Thirion, Pierre Neuvial","submitted_at":"2026-01-30T16:10:26Z","abstract_excerpt":"Conditional independence testing (CIT) is essential for reliable scientific discovery. It prevents spurious findings and enables controlled feature selection. Recent CIT methods have used machine learning (ML) models as surrogates of the underlying distribution. However, model-agnostic approaches require a train-test split, which reduces statistical power. We introduce Semi-knockoffs, a CIT method that can accommodate any pre-trained model, avoids this split, and provides valid p-values and false discovery rate (FDR) control for high-dimensional settings. Unlike methods that rely on the model-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.23124","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/2601.23124/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":"2601.23124","created_at":"2026-06-23T02:13:20.498674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.23124v2","created_at":"2026-06-23T02:13:20.498674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.23124","created_at":"2026-06-23T02:13:20.498674+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5QFQ7LY7J6L","created_at":"2026-06-23T02:13:20.498674+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5QFQ7LY7J6LLXHJ","created_at":"2026-06-23T02:13:20.498674+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5QFQ7LY","created_at":"2026-06-23T02:13:20.498674+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/M5QFQ7LY7J6LLXHJTNLNRYXZ7V","json":"https://pith.science/pith/M5QFQ7LY7J6LLXHJTNLNRYXZ7V.json","graph_json":"https://pith.science/api/pith-number/M5QFQ7LY7J6LLXHJTNLNRYXZ7V/graph.json","events_json":"https://pith.science/api/pith-number/M5QFQ7LY7J6LLXHJTNLNRYXZ7V/events.json","paper":"https://pith.science/paper/M5QFQ7LY"},"agent_actions":{"view_html":"https://pith.science/pith/M5QFQ7LY7J6LLXHJTNLNRYXZ7V","download_json":"https://pith.science/pith/M5QFQ7LY7J6LLXHJTNLNRYXZ7V.json","view_paper":"https://pith.science/paper/M5QFQ7LY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.23124&json=true","fetch_graph":"https://pith.science/api/pith-number/M5QFQ7LY7J6LLXHJTNLNRYXZ7V/graph.json","fetch_events":"https://pith.science/api/pith-number/M5QFQ7LY7J6LLXHJTNLNRYXZ7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5QFQ7LY7J6LLXHJTNLNRYXZ7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5QFQ7LY7J6LLXHJTNLNRYXZ7V/action/storage_attestation","attest_author":"https://pith.science/pith/M5QFQ7LY7J6LLXHJTNLNRYXZ7V/action/author_attestation","sign_citation":"https://pith.science/pith/M5QFQ7LY7J6LLXHJTNLNRYXZ7V/action/citation_signature","submit_replication":"https://pith.science/pith/M5QFQ7LY7J6LLXHJTNLNRYXZ7V/action/replication_record"}},"created_at":"2026-06-23T02:13:20.498674+00:00","updated_at":"2026-06-23T02:13:20.498674+00:00"}