{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H2RZU3JXEWBR2LDGNBIMSOP4ML","short_pith_number":"pith:H2RZU3JX","schema_version":"1.0","canonical_sha256":"3ea39a6d3725831d2c666850c939fc62e0320c12d2e4ef6a99b0a0d00cd3e7c1","source":{"kind":"arxiv","id":"2207.09560","version":4},"attestation_state":"computed","paper":{"title":"Holistic Robust Data-Driven Decisions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Amine Bennouna, Bart Van Parys, Ryan Lucas","submitted_at":"2022-07-19T21:28:51Z","abstract_excerpt":"The design of data-driven formulations for machine learning and decision-making with good out-of-sample performance is a key challenge. The observation that good in-sample performance does not guarantee good out-of-sample performance is generally known as overfitting. Practical overfitting can typically not be attributed to a single cause but is caused by several factors simultaneously. We consider here three overfitting sources: (i) statistical error as a result of working with finite sample data, (ii) data noise, which occurs when the data points are measured only with finite precision, and "},"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":"2207.09560","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-19T21:28:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8ef0d8067d8e3cfce9accc01c55690dec3ae3305df5238d79a874ea07003fcf9","abstract_canon_sha256":"1fe78126e515f2d568c4fb23cd3f91b7bed91ce23c69d9e23c06b04b1d5b87e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:10.242862Z","signature_b64":"cYLvCxNVoOdGATKAweXt0yojWSLB5ubLXxhG4VHTpajrojC2frvikBlWGjoVFUs5r++5EqkaKznPLfQt6UNTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ea39a6d3725831d2c666850c939fc62e0320c12d2e4ef6a99b0a0d00cd3e7c1","last_reissued_at":"2026-07-05T10:08:10.242513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:10.242513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Holistic Robust Data-Driven Decisions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Amine Bennouna, Bart Van Parys, Ryan Lucas","submitted_at":"2022-07-19T21:28:51Z","abstract_excerpt":"The design of data-driven formulations for machine learning and decision-making with good out-of-sample performance is a key challenge. The observation that good in-sample performance does not guarantee good out-of-sample performance is generally known as overfitting. Practical overfitting can typically not be attributed to a single cause but is caused by several factors simultaneously. We consider here three overfitting sources: (i) statistical error as a result of working with finite sample data, (ii) data noise, which occurs when the data points are measured only with finite precision, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09560","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/2207.09560/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":"2207.09560","created_at":"2026-07-05T10:08:10.242569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.09560v4","created_at":"2026-07-05T10:08:10.242569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09560","created_at":"2026-07-05T10:08:10.242569+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2RZU3JXEWBR","created_at":"2026-07-05T10:08:10.242569+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2RZU3JXEWBR2LDG","created_at":"2026-07-05T10:08:10.242569+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2RZU3JX","created_at":"2026-07-05T10:08:10.242569+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23565","citing_title":"DRO: A Python Library for Distributionally Robust Optimization in Machine Learning","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2RZU3JXEWBR2LDGNBIMSOP4ML","json":"https://pith.science/pith/H2RZU3JXEWBR2LDGNBIMSOP4ML.json","graph_json":"https://pith.science/api/pith-number/H2RZU3JXEWBR2LDGNBIMSOP4ML/graph.json","events_json":"https://pith.science/api/pith-number/H2RZU3JXEWBR2LDGNBIMSOP4ML/events.json","paper":"https://pith.science/paper/H2RZU3JX"},"agent_actions":{"view_html":"https://pith.science/pith/H2RZU3JXEWBR2LDGNBIMSOP4ML","download_json":"https://pith.science/pith/H2RZU3JXEWBR2LDGNBIMSOP4ML.json","view_paper":"https://pith.science/paper/H2RZU3JX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.09560&json=true","fetch_graph":"https://pith.science/api/pith-number/H2RZU3JXEWBR2LDGNBIMSOP4ML/graph.json","fetch_events":"https://pith.science/api/pith-number/H2RZU3JXEWBR2LDGNBIMSOP4ML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2RZU3JXEWBR2LDGNBIMSOP4ML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2RZU3JXEWBR2LDGNBIMSOP4ML/action/storage_attestation","attest_author":"https://pith.science/pith/H2RZU3JXEWBR2LDGNBIMSOP4ML/action/author_attestation","sign_citation":"https://pith.science/pith/H2RZU3JXEWBR2LDGNBIMSOP4ML/action/citation_signature","submit_replication":"https://pith.science/pith/H2RZU3JXEWBR2LDGNBIMSOP4ML/action/replication_record"}},"created_at":"2026-07-05T10:08:10.242569+00:00","updated_at":"2026-07-05T10:08:10.242569+00:00"}