{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WTMUFPP5TJFW65TW3W45DV52GN","short_pith_number":"pith:WTMUFPP5","schema_version":"1.0","canonical_sha256":"b4d942bdfd9a4b6f7676ddb9d1d7ba336b51a6e4882659eef57435a73037d01e","source":{"kind":"arxiv","id":"2608.00989","version":1},"attestation_state":"computed","paper":{"title":"Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jiaan Han, Junxiao Chen, Yanzhe Fu","submitted_at":"2026-08-02T04:39:27Z","abstract_excerpt":"Most FDR-controlled feature selection methods are designed for coordinate-wise hypotheses, where each feature has a single weight or importance score. This abstraction fails in sequential and grouped models, where one original feature is represented by a block of sub-features, such as lags, recurrent states, or attention-based interactions. We propose a grouped-feature FDR control framework for such settings. For grouped linear models, we construct null-symmetric block-level mirror statistics with matrix-valued perturbations. For neural sequential models, we combine Permutation SHAP derivative"},"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":"2608.00989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-08-02T04:39:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8df3f9cb05ce369504431ae4382f76f9573b3da0882763c0015b35d5fed76849","abstract_canon_sha256":"3d991d378711aa7ddf05a3f0f025ebb4c727135f9dfcf9bc7256027107c6af1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:56:10.402705Z","signature_b64":"m/BD7cJL7CQ/FY7JfXjlExNmpx8PIYV5F9dCqvqmb+o+829yU9l+w7qTWQs/sDI9E1eYW/sOIzUcCcPovx2GDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4d942bdfd9a4b6f7676ddb9d1d7ba336b51a6e4882659eef57435a73037d01e","last_reissued_at":"2026-08-04T01:56:10.401277Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:56:10.401277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jiaan Han, Junxiao Chen, Yanzhe Fu","submitted_at":"2026-08-02T04:39:27Z","abstract_excerpt":"Most FDR-controlled feature selection methods are designed for coordinate-wise hypotheses, where each feature has a single weight or importance score. This abstraction fails in sequential and grouped models, where one original feature is represented by a block of sub-features, such as lags, recurrent states, or attention-based interactions. We propose a grouped-feature FDR control framework for such settings. For grouped linear models, we construct null-symmetric block-level mirror statistics with matrix-valued perturbations. For neural sequential models, we combine Permutation SHAP derivative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00989","kind":"arxiv","version":1},"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/2608.00989/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":"2608.00989","created_at":"2026-08-04T01:56:10.402533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00989v1","created_at":"2026-08-04T01:56:10.402533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00989","created_at":"2026-08-04T01:56:10.402533+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTMUFPP5TJFW","created_at":"2026-08-04T01:56:10.402533+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTMUFPP5TJFW65TW","created_at":"2026-08-04T01:56:10.402533+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTMUFPP5","created_at":"2026-08-04T01:56:10.402533+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/WTMUFPP5TJFW65TW3W45DV52GN","json":"https://pith.science/pith/WTMUFPP5TJFW65TW3W45DV52GN.json","graph_json":"https://pith.science/api/pith-number/WTMUFPP5TJFW65TW3W45DV52GN/graph.json","events_json":"https://pith.science/api/pith-number/WTMUFPP5TJFW65TW3W45DV52GN/events.json","paper":"https://pith.science/paper/WTMUFPP5"},"agent_actions":{"view_html":"https://pith.science/pith/WTMUFPP5TJFW65TW3W45DV52GN","download_json":"https://pith.science/pith/WTMUFPP5TJFW65TW3W45DV52GN.json","view_paper":"https://pith.science/paper/WTMUFPP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00989&json=true","fetch_graph":"https://pith.science/api/pith-number/WTMUFPP5TJFW65TW3W45DV52GN/graph.json","fetch_events":"https://pith.science/api/pith-number/WTMUFPP5TJFW65TW3W45DV52GN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTMUFPP5TJFW65TW3W45DV52GN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTMUFPP5TJFW65TW3W45DV52GN/action/storage_attestation","attest_author":"https://pith.science/pith/WTMUFPP5TJFW65TW3W45DV52GN/action/author_attestation","sign_citation":"https://pith.science/pith/WTMUFPP5TJFW65TW3W45DV52GN/action/citation_signature","submit_replication":"https://pith.science/pith/WTMUFPP5TJFW65TW3W45DV52GN/action/replication_record"}},"created_at":"2026-08-04T01:56:10.402533+00:00","updated_at":"2026-08-04T01:56:10.402533+00:00"}