{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A2PD6UOIXZPDECD36Y5N5MMBN3","short_pith_number":"pith:A2PD6UOI","schema_version":"1.0","canonical_sha256":"069e3f51c8be5e32087bf63adeb1816ee558ae2c54a668bba59be31f23ac5ebe","source":{"kind":"arxiv","id":"2101.07732","version":2},"attestation_state":"computed","paper":{"title":"Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fix","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emre Kiciman, Hao Liu, Pengchuan Zhang, Ruocheng Guo","submitted_at":"2021-01-16T01:35:06Z","abstract_excerpt":"This work considers the out-of-distribution (OOD) prediction problem where (1)~the training data are from multiple domains and (2)~the test domain is unseen in the training. DNNs fail in OOD prediction because they are prone to pick up spurious correlations. Recently, Invariant Risk Minimization (IRM) is proposed to address this issue. Its effectiveness has been demonstrated in the colored MNIST experiment. Nevertheless, we find that the performance of IRM can be dramatically degraded under \\emph{strong $\\Lambda$ spuriousness} -- when the spurious correlation between the spurious features 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":"2101.07732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-16T01:35:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"feff3754e0947aca3664e3505b513c904858f786dc8ce7d178edd463144b5714","abstract_canon_sha256":"b54ceca58cf27537dcd45fec5301944a86bbeee98028ef3801b9b67d885468bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:17:09.849958Z","signature_b64":"gV/KV43L341zh1C2WTqOuuy6lWyy7d6DkOKloHIXoQFeG9l/P0IQlnkUskgRd0KLhW8CoOYHbZp3hrP5pL+7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"069e3f51c8be5e32087bf63adeb1816ee558ae2c54a668bba59be31f23ac5ebe","last_reissued_at":"2026-07-05T02:17:09.849526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:17:09.849526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fix","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emre Kiciman, Hao Liu, Pengchuan Zhang, Ruocheng Guo","submitted_at":"2021-01-16T01:35:06Z","abstract_excerpt":"This work considers the out-of-distribution (OOD) prediction problem where (1)~the training data are from multiple domains and (2)~the test domain is unseen in the training. DNNs fail in OOD prediction because they are prone to pick up spurious correlations. Recently, Invariant Risk Minimization (IRM) is proposed to address this issue. Its effectiveness has been demonstrated in the colored MNIST experiment. Nevertheless, we find that the performance of IRM can be dramatically degraded under \\emph{strong $\\Lambda$ spuriousness} -- when the spurious correlation between the spurious features and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07732","kind":"arxiv","version":2},"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/2101.07732/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":"2101.07732","created_at":"2026-07-05T02:17:09.849585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.07732v2","created_at":"2026-07-05T02:17:09.849585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07732","created_at":"2026-07-05T02:17:09.849585+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2PD6UOIXZPD","created_at":"2026-07-05T02:17:09.849585+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2PD6UOIXZPDECD3","created_at":"2026-07-05T02:17:09.849585+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2PD6UOI","created_at":"2026-07-05T02:17:09.849585+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/A2PD6UOIXZPDECD36Y5N5MMBN3","json":"https://pith.science/pith/A2PD6UOIXZPDECD36Y5N5MMBN3.json","graph_json":"https://pith.science/api/pith-number/A2PD6UOIXZPDECD36Y5N5MMBN3/graph.json","events_json":"https://pith.science/api/pith-number/A2PD6UOIXZPDECD36Y5N5MMBN3/events.json","paper":"https://pith.science/paper/A2PD6UOI"},"agent_actions":{"view_html":"https://pith.science/pith/A2PD6UOIXZPDECD36Y5N5MMBN3","download_json":"https://pith.science/pith/A2PD6UOIXZPDECD36Y5N5MMBN3.json","view_paper":"https://pith.science/paper/A2PD6UOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.07732&json=true","fetch_graph":"https://pith.science/api/pith-number/A2PD6UOIXZPDECD36Y5N5MMBN3/graph.json","fetch_events":"https://pith.science/api/pith-number/A2PD6UOIXZPDECD36Y5N5MMBN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2PD6UOIXZPDECD36Y5N5MMBN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2PD6UOIXZPDECD36Y5N5MMBN3/action/storage_attestation","attest_author":"https://pith.science/pith/A2PD6UOIXZPDECD36Y5N5MMBN3/action/author_attestation","sign_citation":"https://pith.science/pith/A2PD6UOIXZPDECD36Y5N5MMBN3/action/citation_signature","submit_replication":"https://pith.science/pith/A2PD6UOIXZPDECD36Y5N5MMBN3/action/replication_record"}},"created_at":"2026-07-05T02:17:09.849585+00:00","updated_at":"2026-07-05T02:17:09.849585+00:00"}