{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VNTOADWANBA7DKYCZKHRGQOGYO","short_pith_number":"pith:VNTOADWA","canonical_record":{"source":{"id":"2503.13236","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-17T14:48:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b686dc63cfb915b84facf0bca2b599174665d7944b002105f7dc369f4212d425","abstract_canon_sha256":"a109ea27b5220bd6c873bc550922407ebbea484cee26987ed25b3c3c44ba9dae"},"schema_version":"1.0"},"canonical_sha256":"ab66e00ec06841f1ab02ca8f1341c6c390e4010fcb32f1847d6cf20db0515760","source":{"kind":"arxiv","id":"2503.13236","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13236","created_at":"2026-07-05T11:51:24Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13236v2","created_at":"2026-07-05T11:51:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13236","created_at":"2026-07-05T11:51:24Z"},{"alias_kind":"pith_short_12","alias_value":"VNTOADWANBA7","created_at":"2026-07-05T11:51:24Z"},{"alias_kind":"pith_short_16","alias_value":"VNTOADWANBA7DKYC","created_at":"2026-07-05T11:51:24Z"},{"alias_kind":"pith_short_8","alias_value":"VNTOADWA","created_at":"2026-07-05T11:51:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VNTOADWANBA7DKYCZKHRGQOGYO","target":"record","payload":{"canonical_record":{"source":{"id":"2503.13236","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-17T14:48:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b686dc63cfb915b84facf0bca2b599174665d7944b002105f7dc369f4212d425","abstract_canon_sha256":"a109ea27b5220bd6c873bc550922407ebbea484cee26987ed25b3c3c44ba9dae"},"schema_version":"1.0"},"canonical_sha256":"ab66e00ec06841f1ab02ca8f1341c6c390e4010fcb32f1847d6cf20db0515760","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:24.014451Z","signature_b64":"X8HFY2gOQ38Rnhd4BjqvCGLuOdlBQPlRnl5kUezNH9HkR9/3d23otIFTqWTvYrObiViMVSjNa1pgk88Q6KJKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab66e00ec06841f1ab02ca8f1341c6c390e4010fcb32f1847d6cf20db0515760","last_reissued_at":"2026-07-05T11:51:24.013944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:24.013944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.13236","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xc6KMzxQU+V4jqrj0zl0z+YGb6SMYviP7nRwB4rOQfu0BFrtw3mvBgbojnfJ8HIEALM0hZU59312MH0Kg0hxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:39:07.505369Z"},"content_sha256":"c755792538a226a5e2e12b969cc7b7f8edecdccbf5fc69ab5e3d5b8be01dd737","schema_version":"1.0","event_id":"sha256:c755792538a226a5e2e12b969cc7b7f8edecdccbf5fc69ab5e3d5b8be01dd737"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VNTOADWANBA7DKYCZKHRGQOGYO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient Extrapolation for Debiased Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ihab Asaad, Joachim Denzler, Maha Shadaydeh","submitted_at":"2025-03-17T14:48:57Z","abstract_excerpt":"Machine learning classification models trained with empirical risk minimization (ERM) often inadvertently rely on spurious correlations. When absent in the test data, these unintended associations between non-target attributes and target labels lead to poor generalization. This paper addresses this problem from a model optimization perspective and proposes a novel method, Gradient Extrapolation for Debiased Representation Learning (GERNE), designed to learn debiased representations in both known and unknown attribute training cases. GERNE uses two distinct batches with different amounts of spu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13236","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/2503.13236/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":"2026-07-05T11:51:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+/nUiVs4m1WoiEzA5ujoifOybMqX66vyW02HBWig4gYTAHgUvyDDlGJdjwEdKrQ8Ug3GwTQtLlFMTPJBjqAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:39:07.505757Z"},"content_sha256":"dbb795bb63c28a70ac89a8613b1f1c3d7ba1d5bae629d132fc3d08fb425016f1","schema_version":"1.0","event_id":"sha256:dbb795bb63c28a70ac89a8613b1f1c3d7ba1d5bae629d132fc3d08fb425016f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VNTOADWANBA7DKYCZKHRGQOGYO/bundle.json","state_url":"https://pith.science/pith/VNTOADWANBA7DKYCZKHRGQOGYO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VNTOADWANBA7DKYCZKHRGQOGYO/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":"2026-07-06T18:39:07Z","links":{"resolver":"https://pith.science/pith/VNTOADWANBA7DKYCZKHRGQOGYO","bundle":"https://pith.science/pith/VNTOADWANBA7DKYCZKHRGQOGYO/bundle.json","state":"https://pith.science/pith/VNTOADWANBA7DKYCZKHRGQOGYO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VNTOADWANBA7DKYCZKHRGQOGYO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VNTOADWANBA7DKYCZKHRGQOGYO","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":"a109ea27b5220bd6c873bc550922407ebbea484cee26987ed25b3c3c44ba9dae","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-17T14:48:57Z","title_canon_sha256":"b686dc63cfb915b84facf0bca2b599174665d7944b002105f7dc369f4212d425"},"schema_version":"1.0","source":{"id":"2503.13236","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13236","created_at":"2026-07-05T11:51:24Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13236v2","created_at":"2026-07-05T11:51:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13236","created_at":"2026-07-05T11:51:24Z"},{"alias_kind":"pith_short_12","alias_value":"VNTOADWANBA7","created_at":"2026-07-05T11:51:24Z"},{"alias_kind":"pith_short_16","alias_value":"VNTOADWANBA7DKYC","created_at":"2026-07-05T11:51:24Z"},{"alias_kind":"pith_short_8","alias_value":"VNTOADWA","created_at":"2026-07-05T11:51:24Z"}],"graph_snapshots":[{"event_id":"sha256:dbb795bb63c28a70ac89a8613b1f1c3d7ba1d5bae629d132fc3d08fb425016f1","target":"graph","created_at":"2026-07-05T11:51:24Z","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/2503.13236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning classification models trained with empirical risk minimization (ERM) often inadvertently rely on spurious correlations. When absent in the test data, these unintended associations between non-target attributes and target labels lead to poor generalization. This paper addresses this problem from a model optimization perspective and proposes a novel method, Gradient Extrapolation for Debiased Representation Learning (GERNE), designed to learn debiased representations in both known and unknown attribute training cases. GERNE uses two distinct batches with different amounts of spu","authors_text":"Ihab Asaad, Joachim Denzler, Maha Shadaydeh","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-17T14:48:57Z","title":"Gradient Extrapolation for Debiased Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13236","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:c755792538a226a5e2e12b969cc7b7f8edecdccbf5fc69ab5e3d5b8be01dd737","target":"record","created_at":"2026-07-05T11:51:24Z","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":"a109ea27b5220bd6c873bc550922407ebbea484cee26987ed25b3c3c44ba9dae","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-17T14:48:57Z","title_canon_sha256":"b686dc63cfb915b84facf0bca2b599174665d7944b002105f7dc369f4212d425"},"schema_version":"1.0","source":{"id":"2503.13236","kind":"arxiv","version":2}},"canonical_sha256":"ab66e00ec06841f1ab02ca8f1341c6c390e4010fcb32f1847d6cf20db0515760","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab66e00ec06841f1ab02ca8f1341c6c390e4010fcb32f1847d6cf20db0515760","first_computed_at":"2026-07-05T11:51:24.013944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:24.013944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X8HFY2gOQ38Rnhd4BjqvCGLuOdlBQPlRnl5kUezNH9HkR9/3d23otIFTqWTvYrObiViMVSjNa1pgk88Q6KJKAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:24.014451Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13236","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c755792538a226a5e2e12b969cc7b7f8edecdccbf5fc69ab5e3d5b8be01dd737","sha256:dbb795bb63c28a70ac89a8613b1f1c3d7ba1d5bae629d132fc3d08fb425016f1"],"state_sha256":"3583b0a74bddf9d29eb0f675ad6634f88c208d4ca91775e2f977735eaf0a0ebd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZRRc4cfQj5l3LekK3xPKYqn9uPbxng3SRFJKwAfCK9+NMR3tvuH2XTRF5p9VobgnCgIMtxiHqdkbBsTY9CWDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:39:07.507732Z","bundle_sha256":"e587e95b64d6918a267ba47876ad9c0d51f95808f9e742e573dc683d68921deb"}}