{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BEHFEWHBNPY42YLFBM64345U5S","short_pith_number":"pith:BEHFEWHB","canonical_record":{"source":{"id":"1703.06856","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-20T17:18:57Z","cross_cats_sorted":["cs.CY","cs.LG"],"title_canon_sha256":"620636742d10eab2b46e7277dcd710a4f45533dc83898ad11c21db5bbe0016f4","abstract_canon_sha256":"70362e74bc249adfebc304309164c5f214831ffc0b7ad04ef4837b7f3e2f704a"},"schema_version":"1.0"},"canonical_sha256":"090e5258e16bf1cd61650b3dcdf3b4ec9c55cb5f4533134886f38c10f545a81c","source":{"kind":"arxiv","id":"1703.06856","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06856","created_at":"2026-05-18T00:21:46Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06856v3","created_at":"2026-05-18T00:21:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06856","created_at":"2026-05-18T00:21:46Z"},{"alias_kind":"pith_short_12","alias_value":"BEHFEWHBNPY4","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BEHFEWHBNPY42YLF","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BEHFEWHB","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BEHFEWHBNPY42YLFBM64345U5S","target":"record","payload":{"canonical_record":{"source":{"id":"1703.06856","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-20T17:18:57Z","cross_cats_sorted":["cs.CY","cs.LG"],"title_canon_sha256":"620636742d10eab2b46e7277dcd710a4f45533dc83898ad11c21db5bbe0016f4","abstract_canon_sha256":"70362e74bc249adfebc304309164c5f214831ffc0b7ad04ef4837b7f3e2f704a"},"schema_version":"1.0"},"canonical_sha256":"090e5258e16bf1cd61650b3dcdf3b4ec9c55cb5f4533134886f38c10f545a81c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:46.497877Z","signature_b64":"76Y4oSyfy9+1OfREWFuia9j5AX8RDaE0hYQKhvDLkl/Z4kK8QBw2oHN1/At5HfiIg3gf4s6fNVh7GygOcTdiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"090e5258e16bf1cd61650b3dcdf3b4ec9c55cb5f4533134886f38c10f545a81c","last_reissued_at":"2026-05-18T00:21:46.497193Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:46.497193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.06856","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":"2026-05-18T00:21:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3mUwx4Tyrc33i/D6YJh3h4BOf+j6aSGqyC30T6wvEbBU2gX4zoxEzDbzcQqiDYd1lCdpXvQ3h27+ZWNd9X62DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:41:35.287184Z"},"content_sha256":"9ec9602636eaf034469df108d85f38db9853dc7c37e1d070f25fc7b9d318f943","schema_version":"1.0","event_id":"sha256:9ec9602636eaf034469df108d85f38db9853dc7c37e1d070f25fc7b9d318f943"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BEHFEWHBNPY42YLFBM64345U5S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Counterfactual Fairness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris Russell, Joshua R. Loftus, Matt J. Kusner, Ricardo Silva","submitted_at":"2017-03-20T17:18:57Z","abstract_excerpt":"Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06856","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":""},"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":"2026-05-18T00:21:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RiNc/Rr1/zX7M4eKxLWqKel6/MomAEsOph8L/yX1D43fvs3asWy151Qf6EZ55wzoJpKq3lrVqbvg7a7dJb8vDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:41:35.287862Z"},"content_sha256":"7c727830edfa424194fc0ebf6638e52d661f2d74e34673226fc3fcc5503cda9e","schema_version":"1.0","event_id":"sha256:7c727830edfa424194fc0ebf6638e52d661f2d74e34673226fc3fcc5503cda9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BEHFEWHBNPY42YLFBM64345U5S/bundle.json","state_url":"https://pith.science/pith/BEHFEWHBNPY42YLFBM64345U5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BEHFEWHBNPY42YLFBM64345U5S/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":"2026-05-27T14:41:35Z","links":{"resolver":"https://pith.science/pith/BEHFEWHBNPY42YLFBM64345U5S","bundle":"https://pith.science/pith/BEHFEWHBNPY42YLFBM64345U5S/bundle.json","state":"https://pith.science/pith/BEHFEWHBNPY42YLFBM64345U5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BEHFEWHBNPY42YLFBM64345U5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BEHFEWHBNPY42YLFBM64345U5S","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":"70362e74bc249adfebc304309164c5f214831ffc0b7ad04ef4837b7f3e2f704a","cross_cats_sorted":["cs.CY","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-20T17:18:57Z","title_canon_sha256":"620636742d10eab2b46e7277dcd710a4f45533dc83898ad11c21db5bbe0016f4"},"schema_version":"1.0","source":{"id":"1703.06856","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06856","created_at":"2026-05-18T00:21:46Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06856v3","created_at":"2026-05-18T00:21:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06856","created_at":"2026-05-18T00:21:46Z"},{"alias_kind":"pith_short_12","alias_value":"BEHFEWHBNPY4","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BEHFEWHBNPY42YLF","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BEHFEWHB","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:7c727830edfa424194fc0ebf6638e52d661f2d74e34673226fc3fcc5503cda9e","target":"graph","created_at":"2026-05-18T00:21:46Z","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"},"paper":{"abstract_excerpt":"Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal in","authors_text":"Chris Russell, Joshua R. Loftus, Matt J. Kusner, Ricardo Silva","cross_cats":["cs.CY","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-20T17:18:57Z","title":"Counterfactual Fairness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06856","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":"sha256:9ec9602636eaf034469df108d85f38db9853dc7c37e1d070f25fc7b9d318f943","target":"record","created_at":"2026-05-18T00:21:46Z","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":"70362e74bc249adfebc304309164c5f214831ffc0b7ad04ef4837b7f3e2f704a","cross_cats_sorted":["cs.CY","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-20T17:18:57Z","title_canon_sha256":"620636742d10eab2b46e7277dcd710a4f45533dc83898ad11c21db5bbe0016f4"},"schema_version":"1.0","source":{"id":"1703.06856","kind":"arxiv","version":3}},"canonical_sha256":"090e5258e16bf1cd61650b3dcdf3b4ec9c55cb5f4533134886f38c10f545a81c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"090e5258e16bf1cd61650b3dcdf3b4ec9c55cb5f4533134886f38c10f545a81c","first_computed_at":"2026-05-18T00:21:46.497193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:46.497193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"76Y4oSyfy9+1OfREWFuia9j5AX8RDaE0hYQKhvDLkl/Z4kK8QBw2oHN1/At5HfiIg3gf4s6fNVh7GygOcTdiBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:46.497877Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.06856","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ec9602636eaf034469df108d85f38db9853dc7c37e1d070f25fc7b9d318f943","sha256:7c727830edfa424194fc0ebf6638e52d661f2d74e34673226fc3fcc5503cda9e"],"state_sha256":"60aabda8ec72800c6341543cdf40d191318386c810011e067c6742fe3c142b13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6U4tdZMQ3p95vLTEz7hpBWy+0ewtcl7GKvB9ZlpiMrHKAvN+ui4m6pxKywBAlBzifkzAPCePGCVw6cbFt/3FCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:41:35.291232Z","bundle_sha256":"6fc60aace88d5e3e0d591f2eb8def79ca86dd67f08bfca811486686ce07895b2"}}