{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GNEOW7PKMC5DCSW3UJOYWF6ISY","short_pith_number":"pith:GNEOW7PK","schema_version":"1.0","canonical_sha256":"3348eb7dea60ba314adba25d8b17c8960b4293643de3497c56cb4a6d9098c41c","source":{"kind":"arxiv","id":"2212.10563","version":2},"attestation_state":"computed","paper":{"title":"BLIND: Bias Removal With No Demographics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hadas Orgad, Yonatan Belinkov","submitted_at":"2022-12-20T18:59:42Z","abstract_excerpt":"Models trained on real-world data tend to imitate and amplify social biases. Common methods to mitigate biases require prior information on the types of biases that should be mitigated (e.g., gender or racial bias) and the social groups associated with each data sample. In this work, we introduce BLIND, a method for bias removal with no prior knowledge of the demographics in the dataset. While training a model on a downstream task, BLIND detects biased samples using an auxiliary model that predicts the main model's success, and down-weights those samples during the training process. Experiment"},"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":"2212.10563","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T18:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"c4f162c64ef145fd549a7830f0564903b7246077fc4e41a2bc064579cf9e56a7","abstract_canon_sha256":"abea7d6a02e2675035595a33929dc1c24e031dfaf292d50b0e6389ef19d3aa35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:38.324523Z","signature_b64":"4QZcr0rlES0GFYFrJQTwSzZWV9AZCfuiX03W3kBqFlhgBdlbLgRtepfP8KsG55tN1RSgNLENk/kkUwewOkv8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3348eb7dea60ba314adba25d8b17c8960b4293643de3497c56cb4a6d9098c41c","last_reissued_at":"2026-07-05T06:19:38.324048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:38.324048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BLIND: Bias Removal With No Demographics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hadas Orgad, Yonatan Belinkov","submitted_at":"2022-12-20T18:59:42Z","abstract_excerpt":"Models trained on real-world data tend to imitate and amplify social biases. Common methods to mitigate biases require prior information on the types of biases that should be mitigated (e.g., gender or racial bias) and the social groups associated with each data sample. In this work, we introduce BLIND, a method for bias removal with no prior knowledge of the demographics in the dataset. While training a model on a downstream task, BLIND detects biased samples using an auxiliary model that predicts the main model's success, and down-weights those samples during the training process. Experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10563","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/2212.10563/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":"2212.10563","created_at":"2026-07-05T06:19:38.324111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10563v2","created_at":"2026-07-05T06:19:38.324111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10563","created_at":"2026-07-05T06:19:38.324111+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNEOW7PKMC5D","created_at":"2026-07-05T06:19:38.324111+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNEOW7PKMC5DCSW3","created_at":"2026-07-05T06:19:38.324111+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNEOW7PK","created_at":"2026-07-05T06:19:38.324111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15051","citing_title":"Fantastic Biases (What are They) and Where to Find Them","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY","json":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY.json","graph_json":"https://pith.science/api/pith-number/GNEOW7PKMC5DCSW3UJOYWF6ISY/graph.json","events_json":"https://pith.science/api/pith-number/GNEOW7PKMC5DCSW3UJOYWF6ISY/events.json","paper":"https://pith.science/paper/GNEOW7PK"},"agent_actions":{"view_html":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY","download_json":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY.json","view_paper":"https://pith.science/paper/GNEOW7PK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10563&json=true","fetch_graph":"https://pith.science/api/pith-number/GNEOW7PKMC5DCSW3UJOYWF6ISY/graph.json","fetch_events":"https://pith.science/api/pith-number/GNEOW7PKMC5DCSW3UJOYWF6ISY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/action/storage_attestation","attest_author":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/action/author_attestation","sign_citation":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/action/citation_signature","submit_replication":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/action/replication_record"}},"created_at":"2026-07-05T06:19:38.324111+00:00","updated_at":"2026-07-05T06:19:38.324111+00:00"}