{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:H4MFNPR7PLNZIUDBCYOHMWVS6T","short_pith_number":"pith:H4MFNPR7","canonical_record":{"source":{"id":"2110.00813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-02T14:32:51Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"8e0531ad6bbc9bcaaf9d2f8441ec8a0587e9f064c979f1568f826324adb9f730","abstract_canon_sha256":"d44286d013cbe61144085d84cd5fb2ed2b2b5c7fc7aaa2d4d90b0330e578d383"},"schema_version":"1.0"},"canonical_sha256":"3f1856be3f7adb945061161c765ab2f4c74b092f93578b88689eaeb7b2cdefa7","source":{"kind":"arxiv","id":"2110.00813","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00813","created_at":"2026-07-05T03:19:48Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00813v1","created_at":"2026-07-05T03:19:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00813","created_at":"2026-07-05T03:19:48Z"},{"alias_kind":"pith_short_12","alias_value":"H4MFNPR7PLNZ","created_at":"2026-07-05T03:19:48Z"},{"alias_kind":"pith_short_16","alias_value":"H4MFNPR7PLNZIUDB","created_at":"2026-07-05T03:19:48Z"},{"alias_kind":"pith_short_8","alias_value":"H4MFNPR7","created_at":"2026-07-05T03:19:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:H4MFNPR7PLNZIUDBCYOHMWVS6T","target":"record","payload":{"canonical_record":{"source":{"id":"2110.00813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-02T14:32:51Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"8e0531ad6bbc9bcaaf9d2f8441ec8a0587e9f064c979f1568f826324adb9f730","abstract_canon_sha256":"d44286d013cbe61144085d84cd5fb2ed2b2b5c7fc7aaa2d4d90b0330e578d383"},"schema_version":"1.0"},"canonical_sha256":"3f1856be3f7adb945061161c765ab2f4c74b092f93578b88689eaeb7b2cdefa7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:48.787105Z","signature_b64":"2SM/WGlTP6MV3pRVXH+ILnG7mdbClydebkLrnbnZlkC7nyPU7iW1wB7gm5UpEwl+bs1jIs1Sf/JqYQFpHGdrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f1856be3f7adb945061161c765ab2f4c74b092f93578b88689eaeb7b2cdefa7","last_reissued_at":"2026-07-05T03:19:48.786678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:48.786678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.00813","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:19:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UTrEc5Rb5NoOg3HrFwtDOG8fUr6XoulveHjMVAwrvvqvaORZd/OP+5KiTDrGP16wtC7Z2MbB0jqYzq945ZxPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:39:57.833858Z"},"content_sha256":"a8f1648796b21b555cc272a5be633611eda5ec382d4482179b58c45e4fa4df02","schema_version":"1.0","event_id":"sha256:a8f1648796b21b555cc272a5be633611eda5ec382d4482179b58c45e4fa4df02"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:H4MFNPR7PLNZIUDBCYOHMWVS6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Consider the Alternatives: Navigating Fairness-Accuracy Tradeoffs via Disqualification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"Gal Yona, Guy N. Rothblum","submitted_at":"2021-10-02T14:32:51Z","abstract_excerpt":"In many machine learning settings there is an inherent tension between fairness and accuracy desiderata. How should one proceed in light of such trade-offs? In this work we introduce and study $\\gamma$-disqualification, a new framework for reasoning about fairness-accuracy tradeoffs w.r.t a benchmark class $H$ in the context of supervised learning. Our requirement stipulates that a classifier should be disqualified if it is possible to improve its fairness by switching to another classifier from $H$ without paying \"too much\" in accuracy. The notion of \"too much\" is quantified via a parameter $"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00813","kind":"arxiv","version":1},"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/2110.00813/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":"2026-07-05T03:19:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ACPqOVHrTt0BU0VSWoq5C3D4fChKEEjok7qoHRBH2tytvZSHKunU2MmW0m+/AN7x2Ct6OYfBPmV7sAlqcWNvBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:39:57.837210Z"},"content_sha256":"fa161bf5dbedb77b10b0dfb9cda5519d34afbe57b4e326b588d4d9454dcb6a80","schema_version":"1.0","event_id":"sha256:fa161bf5dbedb77b10b0dfb9cda5519d34afbe57b4e326b588d4d9454dcb6a80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H4MFNPR7PLNZIUDBCYOHMWVS6T/bundle.json","state_url":"https://pith.science/pith/H4MFNPR7PLNZIUDBCYOHMWVS6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H4MFNPR7PLNZIUDBCYOHMWVS6T/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":"2026-08-16T07:39:57Z","links":{"resolver":"https://pith.science/pith/H4MFNPR7PLNZIUDBCYOHMWVS6T","bundle":"https://pith.science/pith/H4MFNPR7PLNZIUDBCYOHMWVS6T/bundle.json","state":"https://pith.science/pith/H4MFNPR7PLNZIUDBCYOHMWVS6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H4MFNPR7PLNZIUDBCYOHMWVS6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H4MFNPR7PLNZIUDBCYOHMWVS6T","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":"d44286d013cbe61144085d84cd5fb2ed2b2b5c7fc7aaa2d4d90b0330e578d383","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-02T14:32:51Z","title_canon_sha256":"8e0531ad6bbc9bcaaf9d2f8441ec8a0587e9f064c979f1568f826324adb9f730"},"schema_version":"1.0","source":{"id":"2110.00813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00813","created_at":"2026-07-05T03:19:48Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00813v1","created_at":"2026-07-05T03:19:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00813","created_at":"2026-07-05T03:19:48Z"},{"alias_kind":"pith_short_12","alias_value":"H4MFNPR7PLNZ","created_at":"2026-07-05T03:19:48Z"},{"alias_kind":"pith_short_16","alias_value":"H4MFNPR7PLNZIUDB","created_at":"2026-07-05T03:19:48Z"},{"alias_kind":"pith_short_8","alias_value":"H4MFNPR7","created_at":"2026-07-05T03:19:48Z"}],"graph_snapshots":[{"event_id":"sha256:fa161bf5dbedb77b10b0dfb9cda5519d34afbe57b4e326b588d4d9454dcb6a80","target":"graph","created_at":"2026-07-05T03:19:48Z","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/2110.00813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many machine learning settings there is an inherent tension between fairness and accuracy desiderata. How should one proceed in light of such trade-offs? In this work we introduce and study $\\gamma$-disqualification, a new framework for reasoning about fairness-accuracy tradeoffs w.r.t a benchmark class $H$ in the context of supervised learning. Our requirement stipulates that a classifier should be disqualified if it is possible to improve its fairness by switching to another classifier from $H$ without paying \"too much\" in accuracy. The notion of \"too much\" is quantified via a parameter $","authors_text":"Gal Yona, Guy N. Rothblum","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-02T14:32:51Z","title":"Consider the Alternatives: Navigating Fairness-Accuracy Tradeoffs via Disqualification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00813","kind":"arxiv","version":1},"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:a8f1648796b21b555cc272a5be633611eda5ec382d4482179b58c45e4fa4df02","target":"record","created_at":"2026-07-05T03:19:48Z","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":"d44286d013cbe61144085d84cd5fb2ed2b2b5c7fc7aaa2d4d90b0330e578d383","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-02T14:32:51Z","title_canon_sha256":"8e0531ad6bbc9bcaaf9d2f8441ec8a0587e9f064c979f1568f826324adb9f730"},"schema_version":"1.0","source":{"id":"2110.00813","kind":"arxiv","version":1}},"canonical_sha256":"3f1856be3f7adb945061161c765ab2f4c74b092f93578b88689eaeb7b2cdefa7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f1856be3f7adb945061161c765ab2f4c74b092f93578b88689eaeb7b2cdefa7","first_computed_at":"2026-07-05T03:19:48.786678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:19:48.786678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2SM/WGlTP6MV3pRVXH+ILnG7mdbClydebkLrnbnZlkC7nyPU7iW1wB7gm5UpEwl+bs1jIs1Sf/JqYQFpHGdrCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:19:48.787105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.00813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8f1648796b21b555cc272a5be633611eda5ec382d4482179b58c45e4fa4df02","sha256:fa161bf5dbedb77b10b0dfb9cda5519d34afbe57b4e326b588d4d9454dcb6a80"],"state_sha256":"e36580dcff100038182f610fcdcf186f220810b7ecaad33a26d659362e22e290"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ydF7zrnglSmOXnNOVBtJ7ws4xDChZ/FRLtfY73z7373NjfPYszOtAfbcIakTndZJk8NspV0C/HUTjW3oG8X9CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:39:57.843881Z","bundle_sha256":"c7fae704349139fb605d97c30e29d433d286b0e2314f389ee2fb7f47ecaaf51c"}}