{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GNEOW7PKMC5DCSW3UJOYWF6ISY","short_pith_number":"pith:GNEOW7PK","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"},"canonical_sha256":"3348eb7dea60ba314adba25d8b17c8960b4293643de3497c56cb4a6d9098c41c","source":{"kind":"arxiv","id":"2212.10563","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10563","created_at":"2026-07-05T06:19:38Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10563v2","created_at":"2026-07-05T06:19:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10563","created_at":"2026-07-05T06:19:38Z"},{"alias_kind":"pith_short_12","alias_value":"GNEOW7PKMC5D","created_at":"2026-07-05T06:19:38Z"},{"alias_kind":"pith_short_16","alias_value":"GNEOW7PKMC5DCSW3","created_at":"2026-07-05T06:19:38Z"},{"alias_kind":"pith_short_8","alias_value":"GNEOW7PK","created_at":"2026-07-05T06:19:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GNEOW7PKMC5DCSW3UJOYWF6ISY","target":"record","payload":{"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"},"canonical_sha256":"3348eb7dea60ba314adba25d8b17c8960b4293643de3497c56cb4a6d9098c41c","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"},"source_kind":"arxiv","source_id":"2212.10563","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":"2026-07-05T06:19:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PzuqVaf0JFqR6C68zCPR3cdZB5ckKSeBC9RP3DbtLbUy1UVAQZNa50RUqXG9FDMrRiy87rET4yvmun4M7dIcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:17:09.201801Z"},"content_sha256":"9d7b0dfc13583d44d0cbb61816a267bb0b463671dde428eb17dcd5c5f1f08f86","schema_version":"1.0","event_id":"sha256:9d7b0dfc13583d44d0cbb61816a267bb0b463671dde428eb17dcd5c5f1f08f86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GNEOW7PKMC5DCSW3UJOYWF6ISY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:19:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E03GQO/oe0Au2KpYWUFESsY9kNzL88xx03NXv92jfLnCo9wmZNVsiGueTYMf+erQ11AN5RV7MlWf1EdGxdnsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:17:09.202377Z"},"content_sha256":"b6aef5ef773ec680a938d0c9cf421556f37d7bb78beccd1c0b9883b84ec94c86","schema_version":"1.0","event_id":"sha256:b6aef5ef773ec680a938d0c9cf421556f37d7bb78beccd1c0b9883b84ec94c86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/bundle.json","state_url":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/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":"2026-08-13T19:17:09Z","links":{"resolver":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY","bundle":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/bundle.json","state":"https://pith.science/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GNEOW7PKMC5DCSW3UJOYWF6ISY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GNEOW7PKMC5DCSW3UJOYWF6ISY","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":"abea7d6a02e2675035595a33929dc1c24e031dfaf292d50b0e6389ef19d3aa35","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T18:59:42Z","title_canon_sha256":"c4f162c64ef145fd549a7830f0564903b7246077fc4e41a2bc064579cf9e56a7"},"schema_version":"1.0","source":{"id":"2212.10563","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10563","created_at":"2026-07-05T06:19:38Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10563v2","created_at":"2026-07-05T06:19:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10563","created_at":"2026-07-05T06:19:38Z"},{"alias_kind":"pith_short_12","alias_value":"GNEOW7PKMC5D","created_at":"2026-07-05T06:19:38Z"},{"alias_kind":"pith_short_16","alias_value":"GNEOW7PKMC5DCSW3","created_at":"2026-07-05T06:19:38Z"},{"alias_kind":"pith_short_8","alias_value":"GNEOW7PK","created_at":"2026-07-05T06:19:38Z"}],"graph_snapshots":[{"event_id":"sha256:b6aef5ef773ec680a938d0c9cf421556f37d7bb78beccd1c0b9883b84ec94c86","target":"graph","created_at":"2026-07-05T06:19:38Z","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/2212.10563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hadas Orgad, Yonatan Belinkov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T18:59:42Z","title":"BLIND: Bias Removal With No Demographics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10563","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":"sha256:9d7b0dfc13583d44d0cbb61816a267bb0b463671dde428eb17dcd5c5f1f08f86","target":"record","created_at":"2026-07-05T06:19:38Z","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":"abea7d6a02e2675035595a33929dc1c24e031dfaf292d50b0e6389ef19d3aa35","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T18:59:42Z","title_canon_sha256":"c4f162c64ef145fd549a7830f0564903b7246077fc4e41a2bc064579cf9e56a7"},"schema_version":"1.0","source":{"id":"2212.10563","kind":"arxiv","version":2}},"canonical_sha256":"3348eb7dea60ba314adba25d8b17c8960b4293643de3497c56cb4a6d9098c41c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3348eb7dea60ba314adba25d8b17c8960b4293643de3497c56cb4a6d9098c41c","first_computed_at":"2026-07-05T06:19:38.324048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:38.324048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4QZcr0rlES0GFYFrJQTwSzZWV9AZCfuiX03W3kBqFlhgBdlbLgRtepfP8KsG55tN1RSgNLENk/kkUwewOkv8CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:38.324523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10563","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d7b0dfc13583d44d0cbb61816a267bb0b463671dde428eb17dcd5c5f1f08f86","sha256:b6aef5ef773ec680a938d0c9cf421556f37d7bb78beccd1c0b9883b84ec94c86"],"state_sha256":"30589e3f4100765646696a4fa751c4ef56b99c9fdcc3fd6304c245661f1a5469"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2sVCgwkB7qDV8Bbwaw6FEolbgacxB2PxIHGLG4ji9/cyoxtOZ7Y1xPj8m7lgEWPMFPRc8pJ3jajN2LcczbkDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T19:17:09.260159Z","bundle_sha256":"01aa089368c500c8457e7f3462a08197ac7dacf860e2d44ee1bbaf639a17b586"}}