{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WMDOKKDFXLA2XSFSEYYK3BH42A","short_pith_number":"pith:WMDOKKDF","canonical_record":{"source":{"id":"2006.13114","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T16:06:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"28d45890f423fcf086817996db6baa52246014edc4f098728b74e96bc13625e9","abstract_canon_sha256":"8cc953f9273e1ba66b187c5b5d51ceb636fffa3f9ac22a2366e8092c504b872f"},"schema_version":"1.0"},"canonical_sha256":"b306e52865bac1abc8b22630ad84fcd01418b9c9a73d0a2a2cf9a68cd8262be7","source":{"kind":"arxiv","id":"2006.13114","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13114","created_at":"2026-07-05T01:48:47Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13114v3","created_at":"2026-07-05T01:48:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13114","created_at":"2026-07-05T01:48:47Z"},{"alias_kind":"pith_short_12","alias_value":"WMDOKKDFXLA2","created_at":"2026-07-05T01:48:47Z"},{"alias_kind":"pith_short_16","alias_value":"WMDOKKDFXLA2XSFS","created_at":"2026-07-05T01:48:47Z"},{"alias_kind":"pith_short_8","alias_value":"WMDOKKDF","created_at":"2026-07-05T01:48:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WMDOKKDFXLA2XSFSEYYK3BH42A","target":"record","payload":{"canonical_record":{"source":{"id":"2006.13114","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T16:06:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"28d45890f423fcf086817996db6baa52246014edc4f098728b74e96bc13625e9","abstract_canon_sha256":"8cc953f9273e1ba66b187c5b5d51ceb636fffa3f9ac22a2366e8092c504b872f"},"schema_version":"1.0"},"canonical_sha256":"b306e52865bac1abc8b22630ad84fcd01418b9c9a73d0a2a2cf9a68cd8262be7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:47.580123Z","signature_b64":"QbvpCJ3q17kXWgQGscVMCUGVhdB1ttPw21dCXXJIfmZdSp+Ijy6diyZLYUo3hAX3hdLF83ydirOHPDk9a51PCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b306e52865bac1abc8b22630ad84fcd01418b9c9a73d0a2a2cf9a68cd8262be7","last_reissued_at":"2026-07-05T01:48:47.579594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:47.579594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.13114","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:48:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hGdup10pJ2I0W/ioAlFygrejrm/No6bolmAHkLpyCCHgXJJoD3iVUWtjIICyInMeCDOrqm1pcttS0cCPMH6qDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:21:49.317716Z"},"content_sha256":"e9bce14d098fd7f0b7b5af6a4b376370c01d404e97e43a692f6face1bbc52be6","schema_version":"1.0","event_id":"sha256:e9bce14d098fd7f0b7b5af6a4b376370c01d404e97e43a692f6face1bbc52be6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WMDOKKDFXLA2XSFSEYYK3BH42A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fairness without Demographics through Adversarially Reweighted Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Beutel, Ed H. Chi, Flavien Prost, Jilin Chen, Kang Lee, Nithum Thain, Preethi Lahoti, Xuezhi Wang","submitted_at":"2020-06-23T16:06:52Z","abstract_excerpt":"Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fairness concerns. However, in practice factors like privacy and regulation often preclude the collection of protected features, or their use for training or inference, severely limiting the applicability of traditional fairness research. Therefore we ask: How can we train an ML model to improve fairness when we do not even know the protected group memberships? In this work we address this problem by proposing Adversari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13114","kind":"arxiv","version":3},"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/2006.13114/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":"2026-07-05T01:48:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+80RTenhvH+PVvdEKncuku4KlDphglubpc8qVuGEvfpNk0aUxY8D16i5D32LLli5AmtmKWYf5jRIVlygeve+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:21:49.318135Z"},"content_sha256":"11cf3b44b8a84b8aabc7cc8cb6b7a5e9fdc57c27f2a01dfaed57fa4d6ba748df","schema_version":"1.0","event_id":"sha256:11cf3b44b8a84b8aabc7cc8cb6b7a5e9fdc57c27f2a01dfaed57fa4d6ba748df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMDOKKDFXLA2XSFSEYYK3BH42A/bundle.json","state_url":"https://pith.science/pith/WMDOKKDFXLA2XSFSEYYK3BH42A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMDOKKDFXLA2XSFSEYYK3BH42A/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":"2026-07-07T07:21:49Z","links":{"resolver":"https://pith.science/pith/WMDOKKDFXLA2XSFSEYYK3BH42A","bundle":"https://pith.science/pith/WMDOKKDFXLA2XSFSEYYK3BH42A/bundle.json","state":"https://pith.science/pith/WMDOKKDFXLA2XSFSEYYK3BH42A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMDOKKDFXLA2XSFSEYYK3BH42A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WMDOKKDFXLA2XSFSEYYK3BH42A","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":"8cc953f9273e1ba66b187c5b5d51ceb636fffa3f9ac22a2366e8092c504b872f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T16:06:52Z","title_canon_sha256":"28d45890f423fcf086817996db6baa52246014edc4f098728b74e96bc13625e9"},"schema_version":"1.0","source":{"id":"2006.13114","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13114","created_at":"2026-07-05T01:48:47Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13114v3","created_at":"2026-07-05T01:48:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13114","created_at":"2026-07-05T01:48:47Z"},{"alias_kind":"pith_short_12","alias_value":"WMDOKKDFXLA2","created_at":"2026-07-05T01:48:47Z"},{"alias_kind":"pith_short_16","alias_value":"WMDOKKDFXLA2XSFS","created_at":"2026-07-05T01:48:47Z"},{"alias_kind":"pith_short_8","alias_value":"WMDOKKDF","created_at":"2026-07-05T01:48:47Z"}],"graph_snapshots":[{"event_id":"sha256:11cf3b44b8a84b8aabc7cc8cb6b7a5e9fdc57c27f2a01dfaed57fa4d6ba748df","target":"graph","created_at":"2026-07-05T01:48:47Z","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/2006.13114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fairness concerns. However, in practice factors like privacy and regulation often preclude the collection of protected features, or their use for training or inference, severely limiting the applicability of traditional fairness research. Therefore we ask: How can we train an ML model to improve fairness when we do not even know the protected group memberships? In this work we address this problem by proposing Adversari","authors_text":"Alex Beutel, Ed H. Chi, Flavien Prost, Jilin Chen, Kang Lee, Nithum Thain, Preethi Lahoti, Xuezhi Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T16:06:52Z","title":"Fairness without Demographics through Adversarially Reweighted Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13114","kind":"arxiv","version":3},"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:e9bce14d098fd7f0b7b5af6a4b376370c01d404e97e43a692f6face1bbc52be6","target":"record","created_at":"2026-07-05T01:48:47Z","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":"8cc953f9273e1ba66b187c5b5d51ceb636fffa3f9ac22a2366e8092c504b872f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T16:06:52Z","title_canon_sha256":"28d45890f423fcf086817996db6baa52246014edc4f098728b74e96bc13625e9"},"schema_version":"1.0","source":{"id":"2006.13114","kind":"arxiv","version":3}},"canonical_sha256":"b306e52865bac1abc8b22630ad84fcd01418b9c9a73d0a2a2cf9a68cd8262be7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b306e52865bac1abc8b22630ad84fcd01418b9c9a73d0a2a2cf9a68cd8262be7","first_computed_at":"2026-07-05T01:48:47.579594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:48:47.579594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QbvpCJ3q17kXWgQGscVMCUGVhdB1ttPw21dCXXJIfmZdSp+Ijy6diyZLYUo3hAX3hdLF83ydirOHPDk9a51PCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:48:47.580123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.13114","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9bce14d098fd7f0b7b5af6a4b376370c01d404e97e43a692f6face1bbc52be6","sha256:11cf3b44b8a84b8aabc7cc8cb6b7a5e9fdc57c27f2a01dfaed57fa4d6ba748df"],"state_sha256":"e545a0cf6e9dffb5a30a4c4c3e891ff43b73650a2fecab8b1fbe2fae28c0ced1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fYvX/ASzlC/+9jYatVyaTkSxcY8n8bTsCF/IrKz3efKAbOk76G5oywBiqBo62kADUDmyq13gyif19Eq217v8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:21:49.321360Z","bundle_sha256":"ce0582c670d078ecb14677352d09fcc0bdaf6c5b72e06d34734ccc6d9150bf87"}}