{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2ZVBQWVXEKJSJBK47GWD6SO5LN","short_pith_number":"pith:2ZVBQWVX","canonical_record":{"source":{"id":"2212.08578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-16T16:54:37Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"eedfdb17b58febd6d5217d049f098489e4f72d992bbf19f1bb7a11aa14d08002","abstract_canon_sha256":"45301bd4d416e9f564492ab6b7a0c3118ff537ff52dd4768c4624f6101291bb0"},"schema_version":"1.0"},"canonical_sha256":"d66a185ab7229324855cf9ac3f49dd5b59a94d4ba17c73b95805207e7a3afbb5","source":{"kind":"arxiv","id":"2212.08578","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08578","created_at":"2026-07-05T05:25:59Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08578v1","created_at":"2026-07-05T05:25:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08578","created_at":"2026-07-05T05:25:59Z"},{"alias_kind":"pith_short_12","alias_value":"2ZVBQWVXEKJS","created_at":"2026-07-05T05:25:59Z"},{"alias_kind":"pith_short_16","alias_value":"2ZVBQWVXEKJSJBK4","created_at":"2026-07-05T05:25:59Z"},{"alias_kind":"pith_short_8","alias_value":"2ZVBQWVX","created_at":"2026-07-05T05:25:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2ZVBQWVXEKJSJBK47GWD6SO5LN","target":"record","payload":{"canonical_record":{"source":{"id":"2212.08578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-16T16:54:37Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"eedfdb17b58febd6d5217d049f098489e4f72d992bbf19f1bb7a11aa14d08002","abstract_canon_sha256":"45301bd4d416e9f564492ab6b7a0c3118ff537ff52dd4768c4624f6101291bb0"},"schema_version":"1.0"},"canonical_sha256":"d66a185ab7229324855cf9ac3f49dd5b59a94d4ba17c73b95805207e7a3afbb5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:59.101733Z","signature_b64":"lMSSxq8Uvo3CuS2lZR6Avt9LPs7iEvx0gR21YhXB1P/HsENQuHn62m9+YKcuo+eJL0UV5rXEEml7dCP6elrJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d66a185ab7229324855cf9ac3f49dd5b59a94d4ba17c73b95805207e7a3afbb5","last_reissued_at":"2026-07-05T05:25:59.101325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:59.101325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.08578","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":"2026-07-05T05:25:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mYgMoAzmuemwmEjRtpLTLlkUAMlNQn00FFBFhx0uq4WDDrHKamReEOxXRtuJQ1xAkiVHxx7ZW9lG3wjyPEXTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:00:35.250229Z"},"content_sha256":"4ca425e0795a21b689537d757ed22cf310299e94e9faccf50a9b3155625a0e16","schema_version":"1.0","event_id":"sha256:4ca425e0795a21b689537d757ed22cf310299e94e9faccf50a9b3155625a0e16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2ZVBQWVXEKJSJBK47GWD6SO5LN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provable Fairness for Neural Network Models using Formal Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"Giorgian Borca-Tasciuc, Stanley Bak, Steven Skiena, Xingzhi Guo","submitted_at":"2022-12-16T16:54:37Z","abstract_excerpt":"Machine learning models are increasingly deployed for critical decision-making tasks, making it important to verify that they do not contain gender or racial biases picked up from training data. Typical approaches to achieve fairness revolve around efforts to clean or curate training data, with post-hoc statistical evaluation of the fairness of the model on evaluation data. In contrast, we propose techniques to \\emph{prove} fairness using recently developed formal methods that verify properties of neural network models.Beyond the strength of guarantee implied by a formal proof, our methods hav"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08578","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/2212.08578/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":"2026-07-05T05:25:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pirOp5OTax7/bYuQng+7InoD5QfwtPDbSrkP014qalGqYWXU0h2HeD7W1B17YCChcn+EvKGb/qSZx6lAtIYxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:00:35.251069Z"},"content_sha256":"d0316937208a62b8cf7d765269c9c6950389ac06d73a44f49a2721264654e7f8","schema_version":"1.0","event_id":"sha256:d0316937208a62b8cf7d765269c9c6950389ac06d73a44f49a2721264654e7f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ZVBQWVXEKJSJBK47GWD6SO5LN/bundle.json","state_url":"https://pith.science/pith/2ZVBQWVXEKJSJBK47GWD6SO5LN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ZVBQWVXEKJSJBK47GWD6SO5LN/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":"2026-08-21T22:00:35Z","links":{"resolver":"https://pith.science/pith/2ZVBQWVXEKJSJBK47GWD6SO5LN","bundle":"https://pith.science/pith/2ZVBQWVXEKJSJBK47GWD6SO5LN/bundle.json","state":"https://pith.science/pith/2ZVBQWVXEKJSJBK47GWD6SO5LN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ZVBQWVXEKJSJBK47GWD6SO5LN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2ZVBQWVXEKJSJBK47GWD6SO5LN","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":"45301bd4d416e9f564492ab6b7a0c3118ff537ff52dd4768c4624f6101291bb0","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-16T16:54:37Z","title_canon_sha256":"eedfdb17b58febd6d5217d049f098489e4f72d992bbf19f1bb7a11aa14d08002"},"schema_version":"1.0","source":{"id":"2212.08578","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08578","created_at":"2026-07-05T05:25:59Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08578v1","created_at":"2026-07-05T05:25:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08578","created_at":"2026-07-05T05:25:59Z"},{"alias_kind":"pith_short_12","alias_value":"2ZVBQWVXEKJS","created_at":"2026-07-05T05:25:59Z"},{"alias_kind":"pith_short_16","alias_value":"2ZVBQWVXEKJSJBK4","created_at":"2026-07-05T05:25:59Z"},{"alias_kind":"pith_short_8","alias_value":"2ZVBQWVX","created_at":"2026-07-05T05:25:59Z"}],"graph_snapshots":[{"event_id":"sha256:d0316937208a62b8cf7d765269c9c6950389ac06d73a44f49a2721264654e7f8","target":"graph","created_at":"2026-07-05T05:25:59Z","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/2212.08578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning models are increasingly deployed for critical decision-making tasks, making it important to verify that they do not contain gender or racial biases picked up from training data. Typical approaches to achieve fairness revolve around efforts to clean or curate training data, with post-hoc statistical evaluation of the fairness of the model on evaluation data. In contrast, we propose techniques to \\emph{prove} fairness using recently developed formal methods that verify properties of neural network models.Beyond the strength of guarantee implied by a formal proof, our methods hav","authors_text":"Giorgian Borca-Tasciuc, Stanley Bak, Steven Skiena, Xingzhi Guo","cross_cats":["cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-16T16:54:37Z","title":"Provable Fairness for Neural Network Models using Formal Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08578","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":"sha256:4ca425e0795a21b689537d757ed22cf310299e94e9faccf50a9b3155625a0e16","target":"record","created_at":"2026-07-05T05:25:59Z","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":"45301bd4d416e9f564492ab6b7a0c3118ff537ff52dd4768c4624f6101291bb0","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-16T16:54:37Z","title_canon_sha256":"eedfdb17b58febd6d5217d049f098489e4f72d992bbf19f1bb7a11aa14d08002"},"schema_version":"1.0","source":{"id":"2212.08578","kind":"arxiv","version":1}},"canonical_sha256":"d66a185ab7229324855cf9ac3f49dd5b59a94d4ba17c73b95805207e7a3afbb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d66a185ab7229324855cf9ac3f49dd5b59a94d4ba17c73b95805207e7a3afbb5","first_computed_at":"2026-07-05T05:25:59.101325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:25:59.101325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lMSSxq8Uvo3CuS2lZR6Avt9LPs7iEvx0gR21YhXB1P/HsENQuHn62m9+YKcuo+eJL0UV5rXEEml7dCP6elrJCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:25:59.101733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08578","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ca425e0795a21b689537d757ed22cf310299e94e9faccf50a9b3155625a0e16","sha256:d0316937208a62b8cf7d765269c9c6950389ac06d73a44f49a2721264654e7f8"],"state_sha256":"a44308ba8a0a41e55157d6384faca9b7f0ddb5b1cbe54a98a083f31b54b9cb7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hN7z5HV2+vgqo0Ceu6IMwysVf9BgRIMW64hzJOx3tAbzllU6gDS5S7Hmqx/INb7Ucb10DhbD0MOd1iL0EbbRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T22:00:35.256176Z","bundle_sha256":"a472ab88925cad9bed81349abafb95cae85dbc530a9c2e11a38ec7e1f8c0bcff"}}