{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CMI7GA6BHVIJ7CQEEN2OS3U5EC","short_pith_number":"pith:CMI7GA6B","schema_version":"1.0","canonical_sha256":"1311f303c13d509f8a042374e96e9d2098c00a8978f6e3613882987d5e76d0b7","source":{"kind":"arxiv","id":"2209.05104","version":2},"attestation_state":"computed","paper":{"title":"Bias Challenges in Counterfactual Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Ribeiro, S Chandra Mouli, Yangze Zhou","submitted_at":"2022-09-12T09:17:49Z","abstract_excerpt":"Deep learning models tend not to be out-of-distribution robust primarily due to their reliance on spurious features to solve the task. Counterfactual data augmentations provide a general way of (approximately) achieving representations that are counterfactual-invariant to spurious features, a requirement for out-of-distribution (OOD) robustness. In this work, we show that counterfactual data augmentations may not achieve the desired counterfactual-invariance if the augmentation is performed by a context-guessing machine, an abstract machine that guesses the most-likely context of a given input"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.05104","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-12T09:17:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f6e5765d60416514c553f36590ece76dce3db4bc965351ab89b75352c28ea41a","abstract_canon_sha256":"570120c2eff0c6ca1d17f141f5e027df651be92cd0a9d511c008317d36e905d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:27.551778Z","signature_b64":"8I8Qvof+WBiKdd74x3vSK6ITqysEA13+EpFDQG/6/KJH1dwLK756iV8FHts+/q0AeHOziLe9wekkQHbo5wUhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1311f303c13d509f8a042374e96e9d2098c00a8978f6e3613882987d5e76d0b7","last_reissued_at":"2026-07-05T04:57:27.551236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:27.551236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bias Challenges in Counterfactual Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Ribeiro, S Chandra Mouli, Yangze Zhou","submitted_at":"2022-09-12T09:17:49Z","abstract_excerpt":"Deep learning models tend not to be out-of-distribution robust primarily due to their reliance on spurious features to solve the task. Counterfactual data augmentations provide a general way of (approximately) achieving representations that are counterfactual-invariant to spurious features, a requirement for out-of-distribution (OOD) robustness. In this work, we show that counterfactual data augmentations may not achieve the desired counterfactual-invariance if the augmentation is performed by a context-guessing machine, an abstract machine that guesses the most-likely context of a given input"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05104","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/2209.05104/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.05104","created_at":"2026-07-05T04:57:27.551292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.05104v2","created_at":"2026-07-05T04:57:27.551292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05104","created_at":"2026-07-05T04:57:27.551292+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMI7GA6BHVIJ","created_at":"2026-07-05T04:57:27.551292+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMI7GA6BHVIJ7CQE","created_at":"2026-07-05T04:57:27.551292+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMI7GA6B","created_at":"2026-07-05T04:57:27.551292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMI7GA6BHVIJ7CQEEN2OS3U5EC","json":"https://pith.science/pith/CMI7GA6BHVIJ7CQEEN2OS3U5EC.json","graph_json":"https://pith.science/api/pith-number/CMI7GA6BHVIJ7CQEEN2OS3U5EC/graph.json","events_json":"https://pith.science/api/pith-number/CMI7GA6BHVIJ7CQEEN2OS3U5EC/events.json","paper":"https://pith.science/paper/CMI7GA6B"},"agent_actions":{"view_html":"https://pith.science/pith/CMI7GA6BHVIJ7CQEEN2OS3U5EC","download_json":"https://pith.science/pith/CMI7GA6BHVIJ7CQEEN2OS3U5EC.json","view_paper":"https://pith.science/paper/CMI7GA6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.05104&json=true","fetch_graph":"https://pith.science/api/pith-number/CMI7GA6BHVIJ7CQEEN2OS3U5EC/graph.json","fetch_events":"https://pith.science/api/pith-number/CMI7GA6BHVIJ7CQEEN2OS3U5EC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMI7GA6BHVIJ7CQEEN2OS3U5EC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMI7GA6BHVIJ7CQEEN2OS3U5EC/action/storage_attestation","attest_author":"https://pith.science/pith/CMI7GA6BHVIJ7CQEEN2OS3U5EC/action/author_attestation","sign_citation":"https://pith.science/pith/CMI7GA6BHVIJ7CQEEN2OS3U5EC/action/citation_signature","submit_replication":"https://pith.science/pith/CMI7GA6BHVIJ7CQEEN2OS3U5EC/action/replication_record"}},"created_at":"2026-07-05T04:57:27.551292+00:00","updated_at":"2026-07-05T04:57:27.551292+00:00"}