{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U4JDLAEDXFJDJQHXK22CTKZBNC","short_pith_number":"pith:U4JDLAED","schema_version":"1.0","canonical_sha256":"a712358083b95234c0f756b429ab216894ab9b53968f92f4c9a95607f11a2b03","source":{"kind":"arxiv","id":"2505.21422","version":1},"attestation_state":"computed","paper":{"title":"When Shift Happens - Confounding Is to Blame","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abbavaram Gowtham Reddy, Celia Rubio-Madrigal, Krikamol Muandet, Rebekka Burkholz","submitted_at":"2025-05-27T16:50:44Z","abstract_excerpt":"Distribution shifts introduce uncertainty that undermines the robustness and generalization capabilities of machine learning models. While conventional wisdom suggests that learning causal-invariant representations enhances robustness to such shifts, recent empirical studies present a counterintuitive finding: (i) empirical risk minimization (ERM) can rival or even outperform state-of-the-art out-of-distribution (OOD) generalization methods, and (ii) its OOD generalization performance improves when all available covariates, not just causal ones, are utilized. Drawing on both empirical and theo"},"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":"2505.21422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T16:50:44Z","cross_cats_sorted":[],"title_canon_sha256":"e14eb90340dafe4561b4d3a301bc6113096fc401b748bd2d128c6b1ac330773b","abstract_canon_sha256":"cdfd6a4ac748ffa8c7ee4918f87cffc6025fee3e7ff8f4bcb368b8c99baef12d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:41.750935Z","signature_b64":"QljdgVthJva3ahhtyv0n52wikcRk1sQ1il5PG1tT5KRKFVKFkeg4tCoub2c98OgclaDXwnJCdmwbluXQE5AvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a712358083b95234c0f756b429ab216894ab9b53968f92f4c9a95607f11a2b03","last_reissued_at":"2026-07-05T11:10:41.750311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:41.750311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Shift Happens - Confounding Is to Blame","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abbavaram Gowtham Reddy, Celia Rubio-Madrigal, Krikamol Muandet, Rebekka Burkholz","submitted_at":"2025-05-27T16:50:44Z","abstract_excerpt":"Distribution shifts introduce uncertainty that undermines the robustness and generalization capabilities of machine learning models. While conventional wisdom suggests that learning causal-invariant representations enhances robustness to such shifts, recent empirical studies present a counterintuitive finding: (i) empirical risk minimization (ERM) can rival or even outperform state-of-the-art out-of-distribution (OOD) generalization methods, and (ii) its OOD generalization performance improves when all available covariates, not just causal ones, are utilized. Drawing on both empirical and theo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21422","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/2505.21422/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":"2505.21422","created_at":"2026-07-05T11:10:41.750399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21422v1","created_at":"2026-07-05T11:10:41.750399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21422","created_at":"2026-07-05T11:10:41.750399+00:00"},{"alias_kind":"pith_short_12","alias_value":"U4JDLAEDXFJD","created_at":"2026-07-05T11:10:41.750399+00:00"},{"alias_kind":"pith_short_16","alias_value":"U4JDLAEDXFJDJQHX","created_at":"2026-07-05T11:10:41.750399+00:00"},{"alias_kind":"pith_short_8","alias_value":"U4JDLAED","created_at":"2026-07-05T11:10:41.750399+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/U4JDLAEDXFJDJQHXK22CTKZBNC","json":"https://pith.science/pith/U4JDLAEDXFJDJQHXK22CTKZBNC.json","graph_json":"https://pith.science/api/pith-number/U4JDLAEDXFJDJQHXK22CTKZBNC/graph.json","events_json":"https://pith.science/api/pith-number/U4JDLAEDXFJDJQHXK22CTKZBNC/events.json","paper":"https://pith.science/paper/U4JDLAED"},"agent_actions":{"view_html":"https://pith.science/pith/U4JDLAEDXFJDJQHXK22CTKZBNC","download_json":"https://pith.science/pith/U4JDLAEDXFJDJQHXK22CTKZBNC.json","view_paper":"https://pith.science/paper/U4JDLAED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21422&json=true","fetch_graph":"https://pith.science/api/pith-number/U4JDLAEDXFJDJQHXK22CTKZBNC/graph.json","fetch_events":"https://pith.science/api/pith-number/U4JDLAEDXFJDJQHXK22CTKZBNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U4JDLAEDXFJDJQHXK22CTKZBNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U4JDLAEDXFJDJQHXK22CTKZBNC/action/storage_attestation","attest_author":"https://pith.science/pith/U4JDLAEDXFJDJQHXK22CTKZBNC/action/author_attestation","sign_citation":"https://pith.science/pith/U4JDLAEDXFJDJQHXK22CTKZBNC/action/citation_signature","submit_replication":"https://pith.science/pith/U4JDLAEDXFJDJQHXK22CTKZBNC/action/replication_record"}},"created_at":"2026-07-05T11:10:41.750399+00:00","updated_at":"2026-07-05T11:10:41.750399+00:00"}