{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OPVCDKGJZ3V4ADKCV3QCJZ65MD","short_pith_number":"pith:OPVCDKGJ","schema_version":"1.0","canonical_sha256":"73ea21a8c9ceebc00d42aee024e7dd60cad4d781f2450ef0ad418e9fdc5990fc","source":{"kind":"arxiv","id":"2605.21341","version":1},"attestation_state":"computed","paper":{"title":"Semiparametric Efficient Bilevel Gradient Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aur\\'elien Bibaut, Fares El Khoury, Houssam Zenati, Michael Arbel, Nathan Kallus","submitted_at":"2026-05-20T16:07:55Z","abstract_excerpt":"Functional bilevel methods estimate a lower-level function and plug it into a hypergradient, but this plug-in gradient can retain first-order bias when the lower-level problem is learned nonparametrically. To remove this bias, we develop a semiparametric debiasing theory for population bilevel gradients based on the efficient influence function. This perspective leads to a cross-fitted orthogonal hypergradient estimator for which we establish asymptotic normality together with uniform control over the outer parameter. Under quadratic losses, the estimator reduces to a simple doubly robust scor"},"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":"2605.21341","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-20T16:07:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c384c1aa9724458cf25197a2f93caa15dd555ed594250c4e5f5830261991ebd","abstract_canon_sha256":"8b1355355ca1a5e80f6c6b829071277c42073cb3d7cb9fecc9d54bc3badb708e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:30.068054Z","signature_b64":"eSHkkuj74Ve6N3YWUk+olTi6V4k7nS7SeCxFA1qC5Pde3vxP9A6vVOSUi7gj/ozZQK205zo5VgAJdA/K7WXABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73ea21a8c9ceebc00d42aee024e7dd60cad4d781f2450ef0ad418e9fdc5990fc","last_reissued_at":"2026-05-21T02:05:30.067370Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:30.067370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semiparametric Efficient Bilevel Gradient Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aur\\'elien Bibaut, Fares El Khoury, Houssam Zenati, Michael Arbel, Nathan Kallus","submitted_at":"2026-05-20T16:07:55Z","abstract_excerpt":"Functional bilevel methods estimate a lower-level function and plug it into a hypergradient, but this plug-in gradient can retain first-order bias when the lower-level problem is learned nonparametrically. To remove this bias, we develop a semiparametric debiasing theory for population bilevel gradients based on the efficient influence function. This perspective leads to a cross-fitted orthogonal hypergradient estimator for which we establish asymptotic normality together with uniform control over the outer parameter. Under quadratic losses, the estimator reduces to a simple doubly robust scor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21341","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/2605.21341/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":"2605.21341","created_at":"2026-05-21T02:05:30.067476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21341v1","created_at":"2026-05-21T02:05:30.067476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21341","created_at":"2026-05-21T02:05:30.067476+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPVCDKGJZ3V4","created_at":"2026-05-21T02:05:30.067476+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPVCDKGJZ3V4ADKC","created_at":"2026-05-21T02:05:30.067476+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPVCDKGJ","created_at":"2026-05-21T02:05:30.067476+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/OPVCDKGJZ3V4ADKCV3QCJZ65MD","json":"https://pith.science/pith/OPVCDKGJZ3V4ADKCV3QCJZ65MD.json","graph_json":"https://pith.science/api/pith-number/OPVCDKGJZ3V4ADKCV3QCJZ65MD/graph.json","events_json":"https://pith.science/api/pith-number/OPVCDKGJZ3V4ADKCV3QCJZ65MD/events.json","paper":"https://pith.science/paper/OPVCDKGJ"},"agent_actions":{"view_html":"https://pith.science/pith/OPVCDKGJZ3V4ADKCV3QCJZ65MD","download_json":"https://pith.science/pith/OPVCDKGJZ3V4ADKCV3QCJZ65MD.json","view_paper":"https://pith.science/paper/OPVCDKGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21341&json=true","fetch_graph":"https://pith.science/api/pith-number/OPVCDKGJZ3V4ADKCV3QCJZ65MD/graph.json","fetch_events":"https://pith.science/api/pith-number/OPVCDKGJZ3V4ADKCV3QCJZ65MD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPVCDKGJZ3V4ADKCV3QCJZ65MD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPVCDKGJZ3V4ADKCV3QCJZ65MD/action/storage_attestation","attest_author":"https://pith.science/pith/OPVCDKGJZ3V4ADKCV3QCJZ65MD/action/author_attestation","sign_citation":"https://pith.science/pith/OPVCDKGJZ3V4ADKCV3QCJZ65MD/action/citation_signature","submit_replication":"https://pith.science/pith/OPVCDKGJZ3V4ADKCV3QCJZ65MD/action/replication_record"}},"created_at":"2026-05-21T02:05:30.067476+00:00","updated_at":"2026-05-21T02:05:30.067476+00:00"}