{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KOD5HPG653O6CQSMTRYBZFRLFF","short_pith_number":"pith:KOD5HPG6","schema_version":"1.0","canonical_sha256":"5387d3bcdeeedde1424c9c701c962b297bd4db2f3fd408bbc1a8223ef08accfc","source":{"kind":"arxiv","id":"2306.10081","version":4},"attestation_state":"computed","paper":{"title":"Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Garud Iyengar, Henry Lam, Tianyu Wang","submitted_at":"2023-06-16T07:07:58Z","abstract_excerpt":"In data-driven optimization, the sample performance of the obtained decision typically incurs an optimistic bias against the true performance, a phenomenon commonly known as the Optimizer's Curse and intimately related to overfitting in machine learning. Common techniques to correct this bias, such as cross-validation, require repeatedly solving additional optimization problems and are therefore computationally expensive. We develop a general bias correction approach, building on what we call Optimizer's Information Criterion (OIC), that directly approximates the first-order bias and does not "},"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":"2306.10081","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-16T07:07:58Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"787d3725db0ad06b56fa91c839a3a9aff2231532e47a90cb6555824bea67e791","abstract_canon_sha256":"70e9a5af10ea635b94879836039544b6e8eab040878af53bea28206d98dd4dc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:29.257139Z","signature_b64":"BWekSTim975jnkrxWy3+gs0Elrhq2Rv6O8qWeGbZ8joypPjhqKLeliT+QV8D+q1XN5x3jwPOJCWTtin6CuE9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5387d3bcdeeedde1424c9c701c962b297bd4db2f3fd408bbc1a8223ef08accfc","last_reissued_at":"2026-07-05T11:40:29.256624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:29.256624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Garud Iyengar, Henry Lam, Tianyu Wang","submitted_at":"2023-06-16T07:07:58Z","abstract_excerpt":"In data-driven optimization, the sample performance of the obtained decision typically incurs an optimistic bias against the true performance, a phenomenon commonly known as the Optimizer's Curse and intimately related to overfitting in machine learning. Common techniques to correct this bias, such as cross-validation, require repeatedly solving additional optimization problems and are therefore computationally expensive. We develop a general bias correction approach, building on what we call Optimizer's Information Criterion (OIC), that directly approximates the first-order bias and does not "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10081","kind":"arxiv","version":4},"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/2306.10081/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":"2306.10081","created_at":"2026-07-05T11:40:29.256687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10081v4","created_at":"2026-07-05T11:40:29.256687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10081","created_at":"2026-07-05T11:40:29.256687+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOD5HPG653O6","created_at":"2026-07-05T11:40:29.256687+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOD5HPG653O6CQSM","created_at":"2026-07-05T11:40:29.256687+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOD5HPG6","created_at":"2026-07-05T11:40:29.256687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.16607","citing_title":"Risk-averse Decision Making with Contextual Information: Model, Sample Average Approximation, and Kernelization","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOD5HPG653O6CQSMTRYBZFRLFF","json":"https://pith.science/pith/KOD5HPG653O6CQSMTRYBZFRLFF.json","graph_json":"https://pith.science/api/pith-number/KOD5HPG653O6CQSMTRYBZFRLFF/graph.json","events_json":"https://pith.science/api/pith-number/KOD5HPG653O6CQSMTRYBZFRLFF/events.json","paper":"https://pith.science/paper/KOD5HPG6"},"agent_actions":{"view_html":"https://pith.science/pith/KOD5HPG653O6CQSMTRYBZFRLFF","download_json":"https://pith.science/pith/KOD5HPG653O6CQSMTRYBZFRLFF.json","view_paper":"https://pith.science/paper/KOD5HPG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10081&json=true","fetch_graph":"https://pith.science/api/pith-number/KOD5HPG653O6CQSMTRYBZFRLFF/graph.json","fetch_events":"https://pith.science/api/pith-number/KOD5HPG653O6CQSMTRYBZFRLFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOD5HPG653O6CQSMTRYBZFRLFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOD5HPG653O6CQSMTRYBZFRLFF/action/storage_attestation","attest_author":"https://pith.science/pith/KOD5HPG653O6CQSMTRYBZFRLFF/action/author_attestation","sign_citation":"https://pith.science/pith/KOD5HPG653O6CQSMTRYBZFRLFF/action/citation_signature","submit_replication":"https://pith.science/pith/KOD5HPG653O6CQSMTRYBZFRLFF/action/replication_record"}},"created_at":"2026-07-05T11:40:29.256687+00:00","updated_at":"2026-07-05T11:40:29.256687+00:00"}