{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DMV3DMHKOPVTMSWP3SLW33NCJX","short_pith_number":"pith:DMV3DMHK","canonical_record":{"source":{"id":"2304.13431","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T10:36:40Z","cross_cats_sorted":[],"title_canon_sha256":"59752c1c53a169cb1690c3fcf86ec6bee086a38389e10a293da270ce5eea3579","abstract_canon_sha256":"85cb878f682a11da6e9200f797747a34df77f23c653d1beb8163f58c483c0a12"},"schema_version":"1.0"},"canonical_sha256":"1b2bb1b0ea73eb364acfdc976deda24df03ad5dbbd4244b2e16092cf09ac17ec","source":{"kind":"arxiv","id":"2304.13431","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13431","created_at":"2026-07-05T11:34:39Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13431v4","created_at":"2026-07-05T11:34:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13431","created_at":"2026-07-05T11:34:39Z"},{"alias_kind":"pith_short_12","alias_value":"DMV3DMHKOPVT","created_at":"2026-07-05T11:34:39Z"},{"alias_kind":"pith_short_16","alias_value":"DMV3DMHKOPVTMSWP","created_at":"2026-07-05T11:34:39Z"},{"alias_kind":"pith_short_8","alias_value":"DMV3DMHK","created_at":"2026-07-05T11:34:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DMV3DMHKOPVTMSWP3SLW33NCJX","target":"record","payload":{"canonical_record":{"source":{"id":"2304.13431","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T10:36:40Z","cross_cats_sorted":[],"title_canon_sha256":"59752c1c53a169cb1690c3fcf86ec6bee086a38389e10a293da270ce5eea3579","abstract_canon_sha256":"85cb878f682a11da6e9200f797747a34df77f23c653d1beb8163f58c483c0a12"},"schema_version":"1.0"},"canonical_sha256":"1b2bb1b0ea73eb364acfdc976deda24df03ad5dbbd4244b2e16092cf09ac17ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:39.825519Z","signature_b64":"sg0jN6T5KnmsrMNSKWRxSpPlCG61TlCGxIfwkRiWA6X0MPG1WXnCgWRZOkFYV+9BRD5Z0rbsT9xDqzesYsoDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b2bb1b0ea73eb364acfdc976deda24df03ad5dbbd4244b2e16092cf09ac17ec","last_reissued_at":"2026-07-05T11:34:39.825055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:39.825055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.13431","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MgBc19jqCPjDQJ3NN6KWTAIWw8L6mzOsdPddtSN8SkRdg9k0DGtr1/I2iBjt3V+CovqmjW5IfBhyFJXtyRP/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:33:27.212420Z"},"content_sha256":"b4836cba28c0e4bec5b4c61640634924ff8fab3b67c03d0f53627a2c2405a8df","schema_version":"1.0","event_id":"sha256:b4836cba28c0e4bec5b4c61640634924ff8fab3b67c03d0f53627a2c2405a8df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DMV3DMHKOPVTMSWP3SLW33NCJX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Counterfactual Data Augmentation for Robust Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Michael K. Ng, Ou Wu, Xiaoling Zhou","submitted_at":"2023-04-26T10:36:40Z","abstract_excerpt":"Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising direction for breaking these spurious associations. However, generating counterfactual data explicitly poses a challenge, and incorporating augmented data into the training process decreases training efficiency. This study proposes an Implicit Counterfactual Data Augmentation (ICDA) method to remove spurious correlations and make stable predictions. Specifically, first, a novel sample-wise augmentation strategy is developed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13431","kind":"arxiv","version":4},"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/2304.13431/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":"2026-07-05T11:34:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"na+Lw6ghE3k+X4iRYRu5fTJ3WXBN9B1OKCdGmKYE3H0K55vbvIBdmcFjUGcuTiPGFK9Ab21SsfZBFOLwZgvAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:33:27.213485Z"},"content_sha256":"5fe0243ddf54ef0ad2879837d3b087d95649ea005318527a15ae596ec4bba99c","schema_version":"1.0","event_id":"sha256:5fe0243ddf54ef0ad2879837d3b087d95649ea005318527a15ae596ec4bba99c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DMV3DMHKOPVTMSWP3SLW33NCJX/bundle.json","state_url":"https://pith.science/pith/DMV3DMHKOPVTMSWP3SLW33NCJX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DMV3DMHKOPVTMSWP3SLW33NCJX/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":"2026-08-09T17:33:27Z","links":{"resolver":"https://pith.science/pith/DMV3DMHKOPVTMSWP3SLW33NCJX","bundle":"https://pith.science/pith/DMV3DMHKOPVTMSWP3SLW33NCJX/bundle.json","state":"https://pith.science/pith/DMV3DMHKOPVTMSWP3SLW33NCJX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DMV3DMHKOPVTMSWP3SLW33NCJX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DMV3DMHKOPVTMSWP3SLW33NCJX","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":"85cb878f682a11da6e9200f797747a34df77f23c653d1beb8163f58c483c0a12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T10:36:40Z","title_canon_sha256":"59752c1c53a169cb1690c3fcf86ec6bee086a38389e10a293da270ce5eea3579"},"schema_version":"1.0","source":{"id":"2304.13431","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13431","created_at":"2026-07-05T11:34:39Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13431v4","created_at":"2026-07-05T11:34:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13431","created_at":"2026-07-05T11:34:39Z"},{"alias_kind":"pith_short_12","alias_value":"DMV3DMHKOPVT","created_at":"2026-07-05T11:34:39Z"},{"alias_kind":"pith_short_16","alias_value":"DMV3DMHKOPVTMSWP","created_at":"2026-07-05T11:34:39Z"},{"alias_kind":"pith_short_8","alias_value":"DMV3DMHK","created_at":"2026-07-05T11:34:39Z"}],"graph_snapshots":[{"event_id":"sha256:5fe0243ddf54ef0ad2879837d3b087d95649ea005318527a15ae596ec4bba99c","target":"graph","created_at":"2026-07-05T11:34:39Z","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/2304.13431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising direction for breaking these spurious associations. However, generating counterfactual data explicitly poses a challenge, and incorporating augmented data into the training process decreases training efficiency. This study proposes an Implicit Counterfactual Data Augmentation (ICDA) method to remove spurious correlations and make stable predictions. Specifically, first, a novel sample-wise augmentation strategy is developed ","authors_text":"Michael K. Ng, Ou Wu, Xiaoling Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T10:36:40Z","title":"Implicit Counterfactual Data Augmentation for Robust Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13431","kind":"arxiv","version":4},"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:b4836cba28c0e4bec5b4c61640634924ff8fab3b67c03d0f53627a2c2405a8df","target":"record","created_at":"2026-07-05T11:34:39Z","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":"85cb878f682a11da6e9200f797747a34df77f23c653d1beb8163f58c483c0a12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T10:36:40Z","title_canon_sha256":"59752c1c53a169cb1690c3fcf86ec6bee086a38389e10a293da270ce5eea3579"},"schema_version":"1.0","source":{"id":"2304.13431","kind":"arxiv","version":4}},"canonical_sha256":"1b2bb1b0ea73eb364acfdc976deda24df03ad5dbbd4244b2e16092cf09ac17ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b2bb1b0ea73eb364acfdc976deda24df03ad5dbbd4244b2e16092cf09ac17ec","first_computed_at":"2026-07-05T11:34:39.825055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:39.825055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sg0jN6T5KnmsrMNSKWRxSpPlCG61TlCGxIfwkRiWA6X0MPG1WXnCgWRZOkFYV+9BRD5Z0rbsT9xDqzesYsoDAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:39.825519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.13431","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4836cba28c0e4bec5b4c61640634924ff8fab3b67c03d0f53627a2c2405a8df","sha256:5fe0243ddf54ef0ad2879837d3b087d95649ea005318527a15ae596ec4bba99c"],"state_sha256":"bd62ae2dbdba63ca1693941fdac4f164d6e435c7f772de03a2e4a3927fccd362"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7l4QFSMkqZ06VZWFGjgeYlNKCxtTKWGEeCrWD0s7iVCFOGUb/SnXt1HZ7T7A1j856ejbYQtEsHLYW5mN03bbAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:33:27.220959Z","bundle_sha256":"3fce60c128af21568dd5f0eade3014e7bfb3cf58227c0ff23ba23a301964bc98"}}