{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:OFD745CGMIXN2VAVXKYJSXITMX","short_pith_number":"pith:OFD745CG","canonical_record":{"source":{"id":"2006.08669","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-15T18:17:44Z","cross_cats_sorted":["cs.CR","cs.CY","cs.LG"],"title_canon_sha256":"9571b3a3edba20e53b6f40ed146c8286c39b05ccaa4d3b696e0472864c2f8e2c","abstract_canon_sha256":"4cad64cca63adb38215747bce07ec8322c576ccf72cd4b206b3ef87e7248a9fa"},"schema_version":"1.0"},"canonical_sha256":"7147fe7446622edd5415bab0995d1365c3344a3f6f35a9adae42fe5303f09c69","source":{"kind":"arxiv","id":"2006.08669","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.08669","created_at":"2026-07-05T01:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2006.08669v1","created_at":"2026-07-05T01:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08669","created_at":"2026-07-05T01:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"OFD745CGMIXN","created_at":"2026-07-05T01:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"OFD745CGMIXN2VAV","created_at":"2026-07-05T01:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"OFD745CG","created_at":"2026-07-05T01:10:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:OFD745CGMIXN2VAVXKYJSXITMX","target":"record","payload":{"canonical_record":{"source":{"id":"2006.08669","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-15T18:17:44Z","cross_cats_sorted":["cs.CR","cs.CY","cs.LG"],"title_canon_sha256":"9571b3a3edba20e53b6f40ed146c8286c39b05ccaa4d3b696e0472864c2f8e2c","abstract_canon_sha256":"4cad64cca63adb38215747bce07ec8322c576ccf72cd4b206b3ef87e7248a9fa"},"schema_version":"1.0"},"canonical_sha256":"7147fe7446622edd5415bab0995d1365c3344a3f6f35a9adae42fe5303f09c69","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:41.860576Z","signature_b64":"TpNItYNHCdQKC4VFTpox1OV6FudJuK8jpQ26um3D5hWjtttNPiPG6CBZvDUkiOsk0m19B1U1vyJvjlBf3BP8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7147fe7446622edd5415bab0995d1365c3344a3f6f35a9adae42fe5303f09c69","last_reissued_at":"2026-07-05T01:10:41.860075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:41.860075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.08669","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":"2026-07-05T01:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lS4huWdphA3HaGz57C5evgo016dr/cHuPmsh0REKSh8At2rPtns1HF7ItROElRBcnNp9S0fAGn6iEQq65rGcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:50:33.614666Z"},"content_sha256":"c27ae99d84e9f9eb180c78234bc5d157f8d71f5d2ab67caef57f643809e93386","schema_version":"1.0","event_id":"sha256:c27ae99d84e9f9eb180c78234bc5d157f8d71f5d2ab67caef57f643809e93386"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:OFD745CGMIXN2VAVXKYJSXITMX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Adversarial Bias and the Robustness of Fair Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CY","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ehsan Kazemi, Hongyan Chang, Reza Shokri, Sasi Kumar Murakonda, Ta Duy Nguyen","submitted_at":"2020-06-15T18:17:44Z","abstract_excerpt":"Optimizing prediction accuracy can come at the expense of fairness. Towards minimizing discrimination against a group, fair machine learning algorithms strive to equalize the behavior of a model across different groups, by imposing a fairness constraint on models. However, we show that giving the same importance to groups of different sizes and distributions, to counteract the effect of bias in training data, can be in conflict with robustness. We analyze data poisoning attacks against group-based fair machine learning, with the focus on equalized odds. An adversary who can control sampling or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08669","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/2006.08669/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":"2026-07-05T01:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3sWG65d4mhV1697b22P7zQ86GJslTEKwZ4x3Y9fJ6PpYF5LbFpfEZ84WH3YSEMpW+CvvvXCsQrrGas7Ccf0hDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:50:33.615607Z"},"content_sha256":"264284ff77368e79ccecdd82728d0a5bb2fc6a38fe6ccb93655965bfdbc21450","schema_version":"1.0","event_id":"sha256:264284ff77368e79ccecdd82728d0a5bb2fc6a38fe6ccb93655965bfdbc21450"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OFD745CGMIXN2VAVXKYJSXITMX/bundle.json","state_url":"https://pith.science/pith/OFD745CGMIXN2VAVXKYJSXITMX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OFD745CGMIXN2VAVXKYJSXITMX/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":"2026-08-10T05:50:33Z","links":{"resolver":"https://pith.science/pith/OFD745CGMIXN2VAVXKYJSXITMX","bundle":"https://pith.science/pith/OFD745CGMIXN2VAVXKYJSXITMX/bundle.json","state":"https://pith.science/pith/OFD745CGMIXN2VAVXKYJSXITMX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OFD745CGMIXN2VAVXKYJSXITMX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OFD745CGMIXN2VAVXKYJSXITMX","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":"4cad64cca63adb38215747bce07ec8322c576ccf72cd4b206b3ef87e7248a9fa","cross_cats_sorted":["cs.CR","cs.CY","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-15T18:17:44Z","title_canon_sha256":"9571b3a3edba20e53b6f40ed146c8286c39b05ccaa4d3b696e0472864c2f8e2c"},"schema_version":"1.0","source":{"id":"2006.08669","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.08669","created_at":"2026-07-05T01:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2006.08669v1","created_at":"2026-07-05T01:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08669","created_at":"2026-07-05T01:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"OFD745CGMIXN","created_at":"2026-07-05T01:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"OFD745CGMIXN2VAV","created_at":"2026-07-05T01:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"OFD745CG","created_at":"2026-07-05T01:10:41Z"}],"graph_snapshots":[{"event_id":"sha256:264284ff77368e79ccecdd82728d0a5bb2fc6a38fe6ccb93655965bfdbc21450","target":"graph","created_at":"2026-07-05T01:10:41Z","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/2006.08669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimizing prediction accuracy can come at the expense of fairness. Towards minimizing discrimination against a group, fair machine learning algorithms strive to equalize the behavior of a model across different groups, by imposing a fairness constraint on models. However, we show that giving the same importance to groups of different sizes and distributions, to counteract the effect of bias in training data, can be in conflict with robustness. We analyze data poisoning attacks against group-based fair machine learning, with the focus on equalized odds. An adversary who can control sampling or","authors_text":"Ehsan Kazemi, Hongyan Chang, Reza Shokri, Sasi Kumar Murakonda, Ta Duy Nguyen","cross_cats":["cs.CR","cs.CY","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-15T18:17:44Z","title":"On Adversarial Bias and the Robustness of Fair Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08669","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:c27ae99d84e9f9eb180c78234bc5d157f8d71f5d2ab67caef57f643809e93386","target":"record","created_at":"2026-07-05T01:10:41Z","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":"4cad64cca63adb38215747bce07ec8322c576ccf72cd4b206b3ef87e7248a9fa","cross_cats_sorted":["cs.CR","cs.CY","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-15T18:17:44Z","title_canon_sha256":"9571b3a3edba20e53b6f40ed146c8286c39b05ccaa4d3b696e0472864c2f8e2c"},"schema_version":"1.0","source":{"id":"2006.08669","kind":"arxiv","version":1}},"canonical_sha256":"7147fe7446622edd5415bab0995d1365c3344a3f6f35a9adae42fe5303f09c69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7147fe7446622edd5415bab0995d1365c3344a3f6f35a9adae42fe5303f09c69","first_computed_at":"2026-07-05T01:10:41.860075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:41.860075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TpNItYNHCdQKC4VFTpox1OV6FudJuK8jpQ26um3D5hWjtttNPiPG6CBZvDUkiOsk0m19B1U1vyJvjlBf3BP8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:41.860576Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.08669","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c27ae99d84e9f9eb180c78234bc5d157f8d71f5d2ab67caef57f643809e93386","sha256:264284ff77368e79ccecdd82728d0a5bb2fc6a38fe6ccb93655965bfdbc21450"],"state_sha256":"03c902f12afedac8683c2b5da597bf8af4d8757d1dd703ff6d628f94cc6cd6e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+1ATLSUzOMPztvilbQu4dnnuL4eQ+0pHKIAVVE7ooaXlfSky4gaB+yavNeO+edNASnq2iWsE3kvRDq56NjNMCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:50:33.637557Z","bundle_sha256":"59492e0ce66c7581ad670a5ba05fc67d4136a8891a35fee7fe8954047365e3ed"}}