{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AYAB4MESJXPUWADJHMBCMS6BCB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e22792742e5c20e6fdc993de14f05127b4ef1bdda986e06b72e6c484c52dd91d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T19:50:04Z","title_canon_sha256":"1c1fa17acd04f14b2cdaca55dbb4a997034602349b9e6f8a4a443c6385a69f28"},"schema_version":"1.0","source":{"id":"2504.00186","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00186","created_at":"2026-07-05T11:47:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00186v3","created_at":"2026-07-05T11:47:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00186","created_at":"2026-07-05T11:47:20Z"},{"alias_kind":"pith_short_12","alias_value":"AYAB4MESJXPU","created_at":"2026-07-05T11:47:20Z"},{"alias_kind":"pith_short_16","alias_value":"AYAB4MESJXPUWADJ","created_at":"2026-07-05T11:47:20Z"},{"alias_kind":"pith_short_8","alias_value":"AYAB4MES","created_at":"2026-07-05T11:47:20Z"}],"graph_snapshots":[{"event_id":"sha256:f0578113cf945655238fe6f084e8deb8b7db471a375d15f8a8895edbf96f1cf1","target":"graph","created_at":"2026-07-05T11:47:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.00186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spurious correlations, unstable statistical shortcuts a model can exploit, are expected to degrade performance out-of-distribution (OOD). However, across many popular OOD generalization benchmarks, vanilla empirical risk minimization (ERM) often achieves the highest OOD accuracy. Moreover, gains in in-distribution accuracy generally improve OOD accuracy, a phenomenon termed accuracy on the line, which contradicts the expected harm of spurious correlations. We show that these observations are an artifact of misspecified OOD datasets that do not include shifts in spurious correlations that harm ","authors_text":"Nicole Chiou, Olawale Salaudeen, Sanmi Koyejo, Shiny Weng","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T19:50:04Z","title":"Are Domain Generalization Benchmarks with Accuracy on the Line Misspecified?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00186","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:40c2111dc3fbbf05804e5e5921dbbacb2dfb27bede076548835d2e60ea1ce2b0","target":"record","created_at":"2026-07-05T11:47:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e22792742e5c20e6fdc993de14f05127b4ef1bdda986e06b72e6c484c52dd91d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T19:50:04Z","title_canon_sha256":"1c1fa17acd04f14b2cdaca55dbb4a997034602349b9e6f8a4a443c6385a69f28"},"schema_version":"1.0","source":{"id":"2504.00186","kind":"arxiv","version":3}},"canonical_sha256":"06001e30924ddf4b00693b02264bc110593cab2ef12c9b380affc346e2b3fa71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06001e30924ddf4b00693b02264bc110593cab2ef12c9b380affc346e2b3fa71","first_computed_at":"2026-07-05T11:47:20.969224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:20.969224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rYqLNGmnXOesdfCEka5FdVK83oLY/LjJLZvqCvwUV2SdH5CChWhQhTlIeMQ+/jAet0o+EPJJlMGOXzLRAVW7AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:20.969750Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00186","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40c2111dc3fbbf05804e5e5921dbbacb2dfb27bede076548835d2e60ea1ce2b0","sha256:f0578113cf945655238fe6f084e8deb8b7db471a375d15f8a8895edbf96f1cf1"],"state_sha256":"a885a7b47733404046e303ef3569c8e862dde0e208281d1d52278e3b22c28f64"}