{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:D4ZVBPLDRBHLLTE2BGUJRQCMRZ","short_pith_number":"pith:D4ZVBPLD","canonical_record":{"source":{"id":"1908.05783","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-15T22:27:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9fa3bd0f33b6b903df944138c114a789f49239e88715cf7ccfc0f671e5eb7d3c","abstract_canon_sha256":"fef105e42bd19a5f03357867749dfe25939924d4f511b0b1b397c90e7053eb13"},"schema_version":"1.0"},"canonical_sha256":"1f3350bd63884eb5cc9a09a898c04c8e4071dc6e97cbdcd45741fbf9dc209911","source":{"kind":"arxiv","id":"1908.05783","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05783","created_at":"2026-07-05T03:31:11Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05783v3","created_at":"2026-07-05T03:31:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05783","created_at":"2026-07-05T03:31:11Z"},{"alias_kind":"pith_short_12","alias_value":"D4ZVBPLDRBHL","created_at":"2026-07-05T03:31:11Z"},{"alias_kind":"pith_short_16","alias_value":"D4ZVBPLDRBHLLTE2","created_at":"2026-07-05T03:31:11Z"},{"alias_kind":"pith_short_8","alias_value":"D4ZVBPLD","created_at":"2026-07-05T03:31:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:D4ZVBPLDRBHLLTE2BGUJRQCMRZ","target":"record","payload":{"canonical_record":{"source":{"id":"1908.05783","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-15T22:27:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9fa3bd0f33b6b903df944138c114a789f49239e88715cf7ccfc0f671e5eb7d3c","abstract_canon_sha256":"fef105e42bd19a5f03357867749dfe25939924d4f511b0b1b397c90e7053eb13"},"schema_version":"1.0"},"canonical_sha256":"1f3350bd63884eb5cc9a09a898c04c8e4071dc6e97cbdcd45741fbf9dc209911","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:11.807639Z","signature_b64":"UbOAL+C7tmGikc1S8qEvssUaXujANas36dNE1jOQjgmfFHwd6uld3cCznR8CsR0RGMUMLEurpneaMNtL7EHCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f3350bd63884eb5cc9a09a898c04c8e4071dc6e97cbdcd45741fbf9dc209911","last_reissued_at":"2026-07-05T03:31:11.807210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:11.807210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.05783","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":"2026-07-05T03:31:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CfYJyaMEn8JIz/bhJ21j3OGgRlUST2FAriuXkBe7lqfLCg7z1lzqhXLTSa9yzG4xwmp7nAgzMzgfiUWr+NprDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:05:57.509764Z"},"content_sha256":"21393dd73a6b6f29f3f614f850593625b926496a78fde74193cb20c467c363e0","schema_version":"1.0","event_id":"sha256:21393dd73a6b6f29f3f614f850593625b926496a78fde74193cb20c467c363e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:D4ZVBPLDRBHLLTE2BGUJRQCMRZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tackling Algorithmic Bias in Neural-Network Classifiers using Wasserstein-2 Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alberto Gonzalez Sanz, Jean-Michel Loubes, Laurent Risser, Quentin Vincenot","submitted_at":"2019-08-15T22:27:29Z","abstract_excerpt":"The increasingly common use of neural network classifiers in industrial and social applications of image analysis has allowed impressive progress these last years. Such methods are however sensitive to algorithmic bias, i.e. to an under- or an over-representation of positive predictions or to higher prediction errors in specific subgroups of images. We then introduce in this paper a new method to temper the algorithmic bias in Neural-Network based classifiers. Our method is Neural-Network architecture agnostic and scales well to massive training sets of images. It indeed only overloads the los"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05783","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.05783/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":"2026-07-05T03:31:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DMAAjiywFd7oMV3vOaNV3DNSV52sQ2vetA3pPGs6UiwK2Jp06XmruRMJ3/dEY4t9NoJokwlKILKi1GMJU4sNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:05:57.510282Z"},"content_sha256":"e97393aba86a4e8d8498ebb96806e5214f562b6a55be846c1b55149cbf179019","schema_version":"1.0","event_id":"sha256:e97393aba86a4e8d8498ebb96806e5214f562b6a55be846c1b55149cbf179019"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4ZVBPLDRBHLLTE2BGUJRQCMRZ/bundle.json","state_url":"https://pith.science/pith/D4ZVBPLDRBHLLTE2BGUJRQCMRZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4ZVBPLDRBHLLTE2BGUJRQCMRZ/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":"2026-08-16T21:05:57Z","links":{"resolver":"https://pith.science/pith/D4ZVBPLDRBHLLTE2BGUJRQCMRZ","bundle":"https://pith.science/pith/D4ZVBPLDRBHLLTE2BGUJRQCMRZ/bundle.json","state":"https://pith.science/pith/D4ZVBPLDRBHLLTE2BGUJRQCMRZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4ZVBPLDRBHLLTE2BGUJRQCMRZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:D4ZVBPLDRBHLLTE2BGUJRQCMRZ","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":"fef105e42bd19a5f03357867749dfe25939924d4f511b0b1b397c90e7053eb13","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-15T22:27:29Z","title_canon_sha256":"9fa3bd0f33b6b903df944138c114a789f49239e88715cf7ccfc0f671e5eb7d3c"},"schema_version":"1.0","source":{"id":"1908.05783","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05783","created_at":"2026-07-05T03:31:11Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05783v3","created_at":"2026-07-05T03:31:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05783","created_at":"2026-07-05T03:31:11Z"},{"alias_kind":"pith_short_12","alias_value":"D4ZVBPLDRBHL","created_at":"2026-07-05T03:31:11Z"},{"alias_kind":"pith_short_16","alias_value":"D4ZVBPLDRBHLLTE2","created_at":"2026-07-05T03:31:11Z"},{"alias_kind":"pith_short_8","alias_value":"D4ZVBPLD","created_at":"2026-07-05T03:31:11Z"}],"graph_snapshots":[{"event_id":"sha256:e97393aba86a4e8d8498ebb96806e5214f562b6a55be846c1b55149cbf179019","target":"graph","created_at":"2026-07-05T03:31:11Z","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/1908.05783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasingly common use of neural network classifiers in industrial and social applications of image analysis has allowed impressive progress these last years. Such methods are however sensitive to algorithmic bias, i.e. to an under- or an over-representation of positive predictions or to higher prediction errors in specific subgroups of images. We then introduce in this paper a new method to temper the algorithmic bias in Neural-Network based classifiers. Our method is Neural-Network architecture agnostic and scales well to massive training sets of images. It indeed only overloads the los","authors_text":"Alberto Gonzalez Sanz, Jean-Michel Loubes, Laurent Risser, Quentin Vincenot","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-15T22:27:29Z","title":"Tackling Algorithmic Bias in Neural-Network Classifiers using Wasserstein-2 Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05783","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":"sha256:21393dd73a6b6f29f3f614f850593625b926496a78fde74193cb20c467c363e0","target":"record","created_at":"2026-07-05T03:31:11Z","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":"fef105e42bd19a5f03357867749dfe25939924d4f511b0b1b397c90e7053eb13","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-15T22:27:29Z","title_canon_sha256":"9fa3bd0f33b6b903df944138c114a789f49239e88715cf7ccfc0f671e5eb7d3c"},"schema_version":"1.0","source":{"id":"1908.05783","kind":"arxiv","version":3}},"canonical_sha256":"1f3350bd63884eb5cc9a09a898c04c8e4071dc6e97cbdcd45741fbf9dc209911","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f3350bd63884eb5cc9a09a898c04c8e4071dc6e97cbdcd45741fbf9dc209911","first_computed_at":"2026-07-05T03:31:11.807210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:31:11.807210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UbOAL+C7tmGikc1S8qEvssUaXujANas36dNE1jOQjgmfFHwd6uld3cCznR8CsR0RGMUMLEurpneaMNtL7EHCCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:31:11.807639Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05783","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21393dd73a6b6f29f3f614f850593625b926496a78fde74193cb20c467c363e0","sha256:e97393aba86a4e8d8498ebb96806e5214f562b6a55be846c1b55149cbf179019"],"state_sha256":"606d0abf325dae37061466cff0a9382589fe27b407ca03a9284b88aace481184"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4LzVM5Gi0ciFYSPWvaC6UY4g4p9/fm/9bs7wk9bS5pUzMwnUZNXfL3XUDI9zLSAvVCSKcJJH9hkiGwGu1FAXDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T21:05:57.515365Z","bundle_sha256":"f27b2eebb0b5070847664e583a023f2ad3d045cd229ec7a89d6058c6ed9d001d"}}