{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FCAQ62337P6XS4GKDQGPWCQKH3","short_pith_number":"pith:FCAQ6233","canonical_record":{"source":{"id":"1902.00375","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T14:47:01Z","cross_cats_sorted":["cs.CY","stat.ML"],"title_canon_sha256":"b82965e79a5f0e8aebd8b2462685306527460f012e9e9b7dd8572b7e0c00913c","abstract_canon_sha256":"0c26c80527e184f0257530858167e60d32c51868d424fd610f0ed4284ffd85be"},"schema_version":"1.0"},"canonical_sha256":"28810f6b7bfbfd7970ca1c0cfb0a0a3ec1c7e9ce0e3e8db8324522507b58fb6f","source":{"kind":"arxiv","id":"1902.00375","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00375","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00375v2","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00375","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"FCAQ62337P6X","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FCAQ62337P6XS4GK","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FCAQ6233","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FCAQ62337P6XS4GKDQGPWCQKH3","target":"record","payload":{"canonical_record":{"source":{"id":"1902.00375","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T14:47:01Z","cross_cats_sorted":["cs.CY","stat.ML"],"title_canon_sha256":"b82965e79a5f0e8aebd8b2462685306527460f012e9e9b7dd8572b7e0c00913c","abstract_canon_sha256":"0c26c80527e184f0257530858167e60d32c51868d424fd610f0ed4284ffd85be"},"schema_version":"1.0"},"canonical_sha256":"28810f6b7bfbfd7970ca1c0cfb0a0a3ec1c7e9ce0e3e8db8324522507b58fb6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:09.183195Z","signature_b64":"RasA8XwiKC7ftGH0yE9em7S7NHao317IsfIaOU3r2xMyUFctN8hmwdrijm4UT/L6gRfcUWETFRCN61DWzFJkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28810f6b7bfbfd7970ca1c0cfb0a0a3ec1c7e9ce0e3e8db8324522507b58fb6f","last_reissued_at":"2026-05-17T23:46:09.182658Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:09.182658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.00375","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ie+bkpLkAgNWvqQKBGPHf0JCs2E4w1beCu+52TTB7rbJpfUt7vEvCf5Uc9ELppaRFXZkIe/oQfFazCMg48m0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T13:53:55.693685Z"},"content_sha256":"686458c494e0672738f34655d7cd2bc6211dc5b137a59b93bb25b1d9622b6da1","schema_version":"1.0","event_id":"sha256:686458c494e0672738f34655d7cd2bc6211dc5b137a59b93bb25b1d9622b6da1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FCAQ62337P6XS4GKDQGPWCQKH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic fairness - Breaking vicious cycles in automatic decision making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Astrid Bunge, Benjamin Paa{\\ss}en, Carolin Hainke, Leon Sindelar, Matthias Vogelsang","submitted_at":"2019-02-01T14:47:01Z","abstract_excerpt":"In recent years, machine learning techniques have been increasingly applied in sensitive decision making processes, raising fairness concerns. Past research has shown that machine learning may reproduce and even exacerbate human bias due to biased training data or flawed model assumptions, and thus may lead to discriminatory actions. To counteract such biased models, researchers have proposed multiple mathematical definitions of fairness according to which classifiers can be optimized. However, it has also been shown that the outcomes generated by some fairness notions may be unsatisfactory.\n "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00375","kind":"arxiv","version":2},"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":"2026-05-17T23:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9wJk6TldJuVjlNbEpOQSWHrezDH4liMIViyQoCoVFnsnj7DiHc8yVDcC2PNN98Rd8Xoyf2ZFvKpgObl7ZS45BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T13:53:55.694025Z"},"content_sha256":"86455df4c25b1280ed43e496f99fcb346e7b0d5d2de4ad52f8f3e8cd028bbf74","schema_version":"1.0","event_id":"sha256:86455df4c25b1280ed43e496f99fcb346e7b0d5d2de4ad52f8f3e8cd028bbf74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FCAQ62337P6XS4GKDQGPWCQKH3/bundle.json","state_url":"https://pith.science/pith/FCAQ62337P6XS4GKDQGPWCQKH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FCAQ62337P6XS4GKDQGPWCQKH3/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":"2026-06-28T13:53:55Z","links":{"resolver":"https://pith.science/pith/FCAQ62337P6XS4GKDQGPWCQKH3","bundle":"https://pith.science/pith/FCAQ62337P6XS4GKDQGPWCQKH3/bundle.json","state":"https://pith.science/pith/FCAQ62337P6XS4GKDQGPWCQKH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FCAQ62337P6XS4GKDQGPWCQKH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FCAQ62337P6XS4GKDQGPWCQKH3","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":"0c26c80527e184f0257530858167e60d32c51868d424fd610f0ed4284ffd85be","cross_cats_sorted":["cs.CY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T14:47:01Z","title_canon_sha256":"b82965e79a5f0e8aebd8b2462685306527460f012e9e9b7dd8572b7e0c00913c"},"schema_version":"1.0","source":{"id":"1902.00375","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00375","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00375v2","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00375","created_at":"2026-05-17T23:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"FCAQ62337P6X","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FCAQ62337P6XS4GK","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FCAQ6233","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:86455df4c25b1280ed43e496f99fcb346e7b0d5d2de4ad52f8f3e8cd028bbf74","target":"graph","created_at":"2026-05-17T23:46:09Z","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":"In recent years, machine learning techniques have been increasingly applied in sensitive decision making processes, raising fairness concerns. Past research has shown that machine learning may reproduce and even exacerbate human bias due to biased training data or flawed model assumptions, and thus may lead to discriminatory actions. To counteract such biased models, researchers have proposed multiple mathematical definitions of fairness according to which classifiers can be optimized. However, it has also been shown that the outcomes generated by some fairness notions may be unsatisfactory.\n ","authors_text":"Astrid Bunge, Benjamin Paa{\\ss}en, Carolin Hainke, Leon Sindelar, Matthias Vogelsang","cross_cats":["cs.CY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T14:47:01Z","title":"Dynamic fairness - Breaking vicious cycles in automatic decision making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00375","kind":"arxiv","version":2},"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":"sha256:686458c494e0672738f34655d7cd2bc6211dc5b137a59b93bb25b1d9622b6da1","target":"record","created_at":"2026-05-17T23:46:09Z","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":"0c26c80527e184f0257530858167e60d32c51868d424fd610f0ed4284ffd85be","cross_cats_sorted":["cs.CY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T14:47:01Z","title_canon_sha256":"b82965e79a5f0e8aebd8b2462685306527460f012e9e9b7dd8572b7e0c00913c"},"schema_version":"1.0","source":{"id":"1902.00375","kind":"arxiv","version":2}},"canonical_sha256":"28810f6b7bfbfd7970ca1c0cfb0a0a3ec1c7e9ce0e3e8db8324522507b58fb6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28810f6b7bfbfd7970ca1c0cfb0a0a3ec1c7e9ce0e3e8db8324522507b58fb6f","first_computed_at":"2026-05-17T23:46:09.182658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:09.182658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RasA8XwiKC7ftGH0yE9em7S7NHao317IsfIaOU3r2xMyUFctN8hmwdrijm4UT/L6gRfcUWETFRCN61DWzFJkBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:09.183195Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.00375","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:686458c494e0672738f34655d7cd2bc6211dc5b137a59b93bb25b1d9622b6da1","sha256:86455df4c25b1280ed43e496f99fcb346e7b0d5d2de4ad52f8f3e8cd028bbf74"],"state_sha256":"82cc25611313c48b8ee5faeeef7596da40c3b146bd1625cdfe33da39d9333d6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2/fWjHAYekV00xzHiOBSBlKfQr6CzxDRciw1aTeHCxNJGgIPQuR8d449RRmoeqf98W2g/ycUx6IkKaSt35eODg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T13:53:55.695827Z","bundle_sha256":"3f6368e1217bb1fa4e9847da32d8d6c9938e9c376f92ed27e7cbe97cdcf7984c"}}