{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FXJ26G4PXUCEY45QJJS5VE4DYH","short_pith_number":"pith:FXJ26G4P","schema_version":"1.0","canonical_sha256":"2dd3af1b8fbd044c73b04a65da9383c1d2e768d7722e88290cc9dc048a15470e","source":{"kind":"arxiv","id":"2312.16313","version":3},"attestation_state":"computed","paper":{"title":"Unraveling the Key Components of OOD Generalization via Diversification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Zamir, Andrei Atanov, Harold Benoit, Liangze Jiang, Mattia Rigotti, O\\u{g}uzhan Fatih Kar","submitted_at":"2023-12-26T19:47:53Z","abstract_excerpt":"Supervised learning datasets may contain multiple cues that explain the training set equally well, i.e., learning any of them would lead to the correct predictions on the training data. However, many of them can be spurious, i.e., lose their predictive power under a distribution shift and consequently fail to generalize to out-of-distribution (OOD) data. Recently developed \"diversification\" methods (Lee et al., 2023; Pagliardini et al., 2023) approach this problem by finding multiple diverse hypotheses that rely on different features. This paper aims to study this class of methods and identify"},"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":"2312.16313","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-26T19:47:53Z","cross_cats_sorted":[],"title_canon_sha256":"d60dde7cfac6fd9e6ca490d5dd9fd3dc726d252f442e4c13cd110ce75c51a2c9","abstract_canon_sha256":"dcdd3218e84b5058194ae0c9bf503457051526dea7e96aac7a8e284352423f70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:21.376335Z","signature_b64":"eTZMJdVpg6eXLQxNrUv5+xDwtdm9rQn0UKgKU02ZlimtdtJmvlj12J4TA9HQDjGM4KMAJSzJv5MjjKYsBV+9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dd3af1b8fbd044c73b04a65da9383c1d2e768d7722e88290cc9dc048a15470e","last_reissued_at":"2026-07-05T08:10:21.375834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:21.375834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unraveling the Key Components of OOD Generalization via Diversification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Zamir, Andrei Atanov, Harold Benoit, Liangze Jiang, Mattia Rigotti, O\\u{g}uzhan Fatih Kar","submitted_at":"2023-12-26T19:47:53Z","abstract_excerpt":"Supervised learning datasets may contain multiple cues that explain the training set equally well, i.e., learning any of them would lead to the correct predictions on the training data. However, many of them can be spurious, i.e., lose their predictive power under a distribution shift and consequently fail to generalize to out-of-distribution (OOD) data. Recently developed \"diversification\" methods (Lee et al., 2023; Pagliardini et al., 2023) approach this problem by finding multiple diverse hypotheses that rely on different features. This paper aims to study this class of methods and identify"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16313","kind":"arxiv","version":3},"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/2312.16313/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":"2312.16313","created_at":"2026-07-05T08:10:21.375896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16313v3","created_at":"2026-07-05T08:10:21.375896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16313","created_at":"2026-07-05T08:10:21.375896+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXJ26G4PXUCE","created_at":"2026-07-05T08:10:21.375896+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXJ26G4PXUCEY45Q","created_at":"2026-07-05T08:10:21.375896+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXJ26G4P","created_at":"2026-07-05T08:10:21.375896+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/FXJ26G4PXUCEY45QJJS5VE4DYH","json":"https://pith.science/pith/FXJ26G4PXUCEY45QJJS5VE4DYH.json","graph_json":"https://pith.science/api/pith-number/FXJ26G4PXUCEY45QJJS5VE4DYH/graph.json","events_json":"https://pith.science/api/pith-number/FXJ26G4PXUCEY45QJJS5VE4DYH/events.json","paper":"https://pith.science/paper/FXJ26G4P"},"agent_actions":{"view_html":"https://pith.science/pith/FXJ26G4PXUCEY45QJJS5VE4DYH","download_json":"https://pith.science/pith/FXJ26G4PXUCEY45QJJS5VE4DYH.json","view_paper":"https://pith.science/paper/FXJ26G4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16313&json=true","fetch_graph":"https://pith.science/api/pith-number/FXJ26G4PXUCEY45QJJS5VE4DYH/graph.json","fetch_events":"https://pith.science/api/pith-number/FXJ26G4PXUCEY45QJJS5VE4DYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXJ26G4PXUCEY45QJJS5VE4DYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXJ26G4PXUCEY45QJJS5VE4DYH/action/storage_attestation","attest_author":"https://pith.science/pith/FXJ26G4PXUCEY45QJJS5VE4DYH/action/author_attestation","sign_citation":"https://pith.science/pith/FXJ26G4PXUCEY45QJJS5VE4DYH/action/citation_signature","submit_replication":"https://pith.science/pith/FXJ26G4PXUCEY45QJJS5VE4DYH/action/replication_record"}},"created_at":"2026-07-05T08:10:21.375896+00:00","updated_at":"2026-07-05T08:10:21.375896+00:00"}