{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7VUYSJGY2GCFVDEBJDRVYDZMEH","short_pith_number":"pith:7VUYSJGY","canonical_record":{"source":{"id":"2212.06254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-12T21:42:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"559297ac7320a2dcf1e4fb0d132b5ec096d1ce2318e9410a84261613e52f1123","abstract_canon_sha256":"83c1e63a4a279d5f95e682889c98892017d47be6e52885388011d21b0d4e7fa6"},"schema_version":"1.0"},"canonical_sha256":"fd698924d8d1845a8c8148e35c0f2c21d2305dfaa4e7b256cb134f6951a38bf1","source":{"kind":"arxiv","id":"2212.06254","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.06254","created_at":"2026-07-05T05:24:48Z"},{"alias_kind":"arxiv_version","alias_value":"2212.06254v1","created_at":"2026-07-05T05:24:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06254","created_at":"2026-07-05T05:24:48Z"},{"alias_kind":"pith_short_12","alias_value":"7VUYSJGY2GCF","created_at":"2026-07-05T05:24:48Z"},{"alias_kind":"pith_short_16","alias_value":"7VUYSJGY2GCFVDEB","created_at":"2026-07-05T05:24:48Z"},{"alias_kind":"pith_short_8","alias_value":"7VUYSJGY","created_at":"2026-07-05T05:24:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7VUYSJGY2GCFVDEBJDRVYDZMEH","target":"record","payload":{"canonical_record":{"source":{"id":"2212.06254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-12T21:42:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"559297ac7320a2dcf1e4fb0d132b5ec096d1ce2318e9410a84261613e52f1123","abstract_canon_sha256":"83c1e63a4a279d5f95e682889c98892017d47be6e52885388011d21b0d4e7fa6"},"schema_version":"1.0"},"canonical_sha256":"fd698924d8d1845a8c8148e35c0f2c21d2305dfaa4e7b256cb134f6951a38bf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:48.194293Z","signature_b64":"lUQZiisS9GhQiq+VLoJ6pzaovFQBwHUDLJ92ncpxyJ88eNj/ej+jTMNm72cgOyndeZXyOFWwTW2YPkJkDLUiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd698924d8d1845a8c8148e35c0f2c21d2305dfaa4e7b256cb134f6951a38bf1","last_reissued_at":"2026-07-05T05:24:48.193825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:48.193825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.06254","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:24:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OBwJrWv/4qFrBwku7XhvPQSeMRbcTMrq3pb2umdym//eDPNilBIcP0WGS+FiLcbPgSumPgP1kGSlRwCfQWisDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:16:19.330026Z"},"content_sha256":"820b6a6a803ec348a6cc9915d47a37eba50a94e62641e88c760da8a5004079e9","schema_version":"1.0","event_id":"sha256:820b6a6a803ec348a6cc9915d47a37eba50a94e62641e88c760da8a5004079e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7VUYSJGY2GCFVDEBJDRVYDZMEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"You Only Need a Good Embeddings Extractor to Fix Spurious Correlations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ivan Evtimov, Li Chen, Raghav Mehta, Tal Hassner, Tamar Glaser, V\\'itor Albiero, Zhiheng Li","submitted_at":"2022-12-12T21:42:33Z","abstract_excerpt":"Spurious correlations in training data often lead to robustness issues since models learn to use them as shortcuts. For example, when predicting whether an object is a cow, a model might learn to rely on its green background, so it would do poorly on a cow on a sandy background. A standard dataset for measuring state-of-the-art on methods mitigating this problem is Waterbirds. The best method (Group Distributionally Robust Optimization - GroupDRO) currently achieves 89\\% worst group accuracy and standard training from scratch on raw images only gets 72\\%. GroupDRO requires training a model in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06254","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/2212.06254/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:24:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VBxvoc+lJjE0zi+r2oDX5RvWV8vS2FT2QOxTz18SJkFEHMjScNDr2AdTLYRMp9GgaN0UNPk1vbfp84vguJTdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:16:19.330973Z"},"content_sha256":"56f98d9bb77b77f5039a218243e45a3fb29708974639012cd5cdff8800b44204","schema_version":"1.0","event_id":"sha256:56f98d9bb77b77f5039a218243e45a3fb29708974639012cd5cdff8800b44204"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7VUYSJGY2GCFVDEBJDRVYDZMEH/bundle.json","state_url":"https://pith.science/pith/7VUYSJGY2GCFVDEBJDRVYDZMEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7VUYSJGY2GCFVDEBJDRVYDZMEH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T04:16:19Z","links":{"resolver":"https://pith.science/pith/7VUYSJGY2GCFVDEBJDRVYDZMEH","bundle":"https://pith.science/pith/7VUYSJGY2GCFVDEBJDRVYDZMEH/bundle.json","state":"https://pith.science/pith/7VUYSJGY2GCFVDEBJDRVYDZMEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7VUYSJGY2GCFVDEBJDRVYDZMEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7VUYSJGY2GCFVDEBJDRVYDZMEH","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":"83c1e63a4a279d5f95e682889c98892017d47be6e52885388011d21b0d4e7fa6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-12T21:42:33Z","title_canon_sha256":"559297ac7320a2dcf1e4fb0d132b5ec096d1ce2318e9410a84261613e52f1123"},"schema_version":"1.0","source":{"id":"2212.06254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.06254","created_at":"2026-07-05T05:24:48Z"},{"alias_kind":"arxiv_version","alias_value":"2212.06254v1","created_at":"2026-07-05T05:24:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06254","created_at":"2026-07-05T05:24:48Z"},{"alias_kind":"pith_short_12","alias_value":"7VUYSJGY2GCF","created_at":"2026-07-05T05:24:48Z"},{"alias_kind":"pith_short_16","alias_value":"7VUYSJGY2GCFVDEB","created_at":"2026-07-05T05:24:48Z"},{"alias_kind":"pith_short_8","alias_value":"7VUYSJGY","created_at":"2026-07-05T05:24:48Z"}],"graph_snapshots":[{"event_id":"sha256:56f98d9bb77b77f5039a218243e45a3fb29708974639012cd5cdff8800b44204","target":"graph","created_at":"2026-07-05T05:24:48Z","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/2212.06254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spurious correlations in training data often lead to robustness issues since models learn to use them as shortcuts. For example, when predicting whether an object is a cow, a model might learn to rely on its green background, so it would do poorly on a cow on a sandy background. A standard dataset for measuring state-of-the-art on methods mitigating this problem is Waterbirds. The best method (Group Distributionally Robust Optimization - GroupDRO) currently achieves 89\\% worst group accuracy and standard training from scratch on raw images only gets 72\\%. GroupDRO requires training a model in ","authors_text":"Ivan Evtimov, Li Chen, Raghav Mehta, Tal Hassner, Tamar Glaser, V\\'itor Albiero, Zhiheng Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-12T21:42:33Z","title":"You Only Need a Good Embeddings Extractor to Fix Spurious Correlations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06254","kind":"arxiv","version":1},"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":"sha256:820b6a6a803ec348a6cc9915d47a37eba50a94e62641e88c760da8a5004079e9","target":"record","created_at":"2026-07-05T05:24:48Z","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":"83c1e63a4a279d5f95e682889c98892017d47be6e52885388011d21b0d4e7fa6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-12T21:42:33Z","title_canon_sha256":"559297ac7320a2dcf1e4fb0d132b5ec096d1ce2318e9410a84261613e52f1123"},"schema_version":"1.0","source":{"id":"2212.06254","kind":"arxiv","version":1}},"canonical_sha256":"fd698924d8d1845a8c8148e35c0f2c21d2305dfaa4e7b256cb134f6951a38bf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd698924d8d1845a8c8148e35c0f2c21d2305dfaa4e7b256cb134f6951a38bf1","first_computed_at":"2026-07-05T05:24:48.193825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:24:48.193825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lUQZiisS9GhQiq+VLoJ6pzaovFQBwHUDLJ92ncpxyJ88eNj/ej+jTMNm72cgOyndeZXyOFWwTW2YPkJkDLUiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:24:48.194293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.06254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:820b6a6a803ec348a6cc9915d47a37eba50a94e62641e88c760da8a5004079e9","sha256:56f98d9bb77b77f5039a218243e45a3fb29708974639012cd5cdff8800b44204"],"state_sha256":"5be2b5f6d1f5710a7b05aa9491f9060599c45bb7fb330adc72d17886fbda0204"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BXjvypsrZsyYRWMhdNeo9R5ydmCzrtWnCHIKmqUjIOrJ+A5kED6onak7GvvurGHmxQfKh4FqmcPmSs4XJEonDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:16:19.339896Z","bundle_sha256":"aa3c954561000979e55afb2e5c781275a935b3974799330ef4bfd1dfa05891a2"}}