{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NZNH5O6UMS7D64ABCXJMOGCH3N","short_pith_number":"pith:NZNH5O6U","schema_version":"1.0","canonical_sha256":"6e5a7ebbd464be3f700115d2c71847db6a1857587a28fe427149554a5b2d7900","source":{"kind":"arxiv","id":"2112.01021","version":2},"attestation_state":"computed","paper":{"title":"Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eunho Yang, Hajin Shim, June Yong Yang, Yeonsung Jung","submitted_at":"2021-12-02T07:16:06Z","abstract_excerpt":"Deep neural networks (DNNs), despite their impressive ability to generalize over-capacity networks, often rely heavily on malignant bias as shortcuts instead of task-related information for discriminative tasks. To address this problem, recent studies utilize auxiliary information related to the bias, which is rarely obtainable in practice, or sift through a handful of bias-free samples for debiasing. However, the success of these methods is not always guaranteed due to the unfulfilled presumptions. In this paper, we propose a novel method, Contrastive Debiasing via Generative Bias-transformat"},"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":"2112.01021","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-02T07:16:06Z","cross_cats_sorted":[],"title_canon_sha256":"4c3f0ae2be9f97b5ca911424c99e4d91ce5bdf40ce80fa34aa8cfa94380d98b7","abstract_canon_sha256":"9450fae5bb1430738ec3565f6ed8a228376bd162676c3f989224868d422b56fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:38.207147Z","signature_b64":"mrCoGO6R+lO0eL/UI16J7b2q7mFjmpbchz9SOTRns0rR6bm4ZCrofssD3er/dlQQkb3g3PHwTemf139Uy753Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e5a7ebbd464be3f700115d2c71847db6a1857587a28fe427149554a5b2d7900","last_reissued_at":"2026-07-05T06:27:38.206653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:38.206653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eunho Yang, Hajin Shim, June Yong Yang, Yeonsung Jung","submitted_at":"2021-12-02T07:16:06Z","abstract_excerpt":"Deep neural networks (DNNs), despite their impressive ability to generalize over-capacity networks, often rely heavily on malignant bias as shortcuts instead of task-related information for discriminative tasks. To address this problem, recent studies utilize auxiliary information related to the bias, which is rarely obtainable in practice, or sift through a handful of bias-free samples for debiasing. However, the success of these methods is not always guaranteed due to the unfulfilled presumptions. In this paper, we propose a novel method, Contrastive Debiasing via Generative Bias-transformat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01021","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/2112.01021/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":"2112.01021","created_at":"2026-07-05T06:27:38.206714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.01021v2","created_at":"2026-07-05T06:27:38.206714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01021","created_at":"2026-07-05T06:27:38.206714+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZNH5O6UMS7D","created_at":"2026-07-05T06:27:38.206714+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZNH5O6UMS7D64AB","created_at":"2026-07-05T06:27:38.206714+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZNH5O6U","created_at":"2026-07-05T06:27:38.206714+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/NZNH5O6UMS7D64ABCXJMOGCH3N","json":"https://pith.science/pith/NZNH5O6UMS7D64ABCXJMOGCH3N.json","graph_json":"https://pith.science/api/pith-number/NZNH5O6UMS7D64ABCXJMOGCH3N/graph.json","events_json":"https://pith.science/api/pith-number/NZNH5O6UMS7D64ABCXJMOGCH3N/events.json","paper":"https://pith.science/paper/NZNH5O6U"},"agent_actions":{"view_html":"https://pith.science/pith/NZNH5O6UMS7D64ABCXJMOGCH3N","download_json":"https://pith.science/pith/NZNH5O6UMS7D64ABCXJMOGCH3N.json","view_paper":"https://pith.science/paper/NZNH5O6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.01021&json=true","fetch_graph":"https://pith.science/api/pith-number/NZNH5O6UMS7D64ABCXJMOGCH3N/graph.json","fetch_events":"https://pith.science/api/pith-number/NZNH5O6UMS7D64ABCXJMOGCH3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZNH5O6UMS7D64ABCXJMOGCH3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZNH5O6UMS7D64ABCXJMOGCH3N/action/storage_attestation","attest_author":"https://pith.science/pith/NZNH5O6UMS7D64ABCXJMOGCH3N/action/author_attestation","sign_citation":"https://pith.science/pith/NZNH5O6UMS7D64ABCXJMOGCH3N/action/citation_signature","submit_replication":"https://pith.science/pith/NZNH5O6UMS7D64ABCXJMOGCH3N/action/replication_record"}},"created_at":"2026-07-05T06:27:38.206714+00:00","updated_at":"2026-07-05T06:27:38.206714+00:00"}