{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:M7Z66FFOKZROVF5QVAUSCE6NNK","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":"245442439f79046ce22af95ffc458be35add74c33aab417f86960c6b1a29efba","cross_cats_sorted":["cs.CL","cs.CV","eess.IV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-02T20:30:59Z","title_canon_sha256":"54aa50207388996dda3fca872d9799e9956a9f3925c0d4ac2d1231a7bd9ec310"},"schema_version":"1.0","source":{"id":"2212.01433","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01433","created_at":"2026-07-05T05:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01433v2","created_at":"2026-07-05T05:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01433","created_at":"2026-07-05T05:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"M7Z66FFOKZRO","created_at":"2026-07-05T05:46:52Z"},{"alias_kind":"pith_short_16","alias_value":"M7Z66FFOKZROVF5Q","created_at":"2026-07-05T05:46:52Z"},{"alias_kind":"pith_short_8","alias_value":"M7Z66FFO","created_at":"2026-07-05T05:46:52Z"}],"graph_snapshots":[{"event_id":"sha256:568e9923ecfcdca6f9b82dc582de4ddb03d1762933edeb3af714a1df60510f21","target":"graph","created_at":"2026-07-05T05:46:52Z","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/2212.01433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Empirical studies suggest that machine learning models trained with empirical risk minimization (ERM) often rely on attributes that may be spuriously correlated with the class labels. Such models typically lead to poor performance during inference for data lacking such correlations. In this work, we explicitly consider a situation where potential spurious correlations are present in the majority of training data. In contrast with existing approaches, which use the ERM model outputs to detect the samples without spurious correlations and either heuristically upweight or upsample those samples, ","authors_text":"Carlos Fernandez-Granda, Nitesh Sekhar, Prateek Singhal, Sheng Liu, Xu Zhang, Yue Wu","cross_cats":["cs.CL","cs.CV","eess.IV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-02T20:30:59Z","title":"Avoiding spurious correlations via logit correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01433","kind":"arxiv","version":2},"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":"sha256:9c95e3b6f650e9cdbbece4b44bd4cd672d9ff08c56190f393cf281357a0bf04c","target":"record","created_at":"2026-07-05T05:46:52Z","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":"245442439f79046ce22af95ffc458be35add74c33aab417f86960c6b1a29efba","cross_cats_sorted":["cs.CL","cs.CV","eess.IV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-02T20:30:59Z","title_canon_sha256":"54aa50207388996dda3fca872d9799e9956a9f3925c0d4ac2d1231a7bd9ec310"},"schema_version":"1.0","source":{"id":"2212.01433","kind":"arxiv","version":2}},"canonical_sha256":"67f3ef14ae5662ea97b0a8292113cd6abedeb3c080dd8294b19e22ae4e058e20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67f3ef14ae5662ea97b0a8292113cd6abedeb3c080dd8294b19e22ae4e058e20","first_computed_at":"2026-07-05T05:46:52.838809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:46:52.838809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Eyo4oYLqkwCk6VjvL9RQwkz+1pSoh1r6nIir3wlDx4COqkvwI6MWem+yrkwJfi6DrFA+z5Ui6j8MmAkHv+4Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:46:52.839159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.01433","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c95e3b6f650e9cdbbece4b44bd4cd672d9ff08c56190f393cf281357a0bf04c","sha256:568e9923ecfcdca6f9b82dc582de4ddb03d1762933edeb3af714a1df60510f21"],"state_sha256":"f3c4677e3e428386d6ba8c426cb1ef57cff164e4348ceab6c8fa385620f5960e"}