{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:M6SVLXJNRNVNVYLY2QE3BY5W65","short_pith_number":"pith:M6SVLXJN","canonical_record":{"source":{"id":"2203.06317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-12T02:22:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f9070cb302412aeac0d5cfce6f1108a3f8a429ad5022a3289d7f6be00ba8e23","abstract_canon_sha256":"5f83a12ad691c0488808303b44a42dc26cd5958ec0f05865e01f1534953ec402"},"schema_version":"1.0"},"canonical_sha256":"67a555dd2d8b6adae178d409b0e3b6f744edfca6b6d913f91dfdfab38ddef213","source":{"kind":"arxiv","id":"2203.06317","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06317","created_at":"2026-07-05T04:23:25Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06317v2","created_at":"2026-07-05T04:23:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06317","created_at":"2026-07-05T04:23:25Z"},{"alias_kind":"pith_short_12","alias_value":"M6SVLXJNRNVN","created_at":"2026-07-05T04:23:25Z"},{"alias_kind":"pith_short_16","alias_value":"M6SVLXJNRNVNVYLY","created_at":"2026-07-05T04:23:25Z"},{"alias_kind":"pith_short_8","alias_value":"M6SVLXJN","created_at":"2026-07-05T04:23:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:M6SVLXJNRNVNVYLY2QE3BY5W65","target":"record","payload":{"canonical_record":{"source":{"id":"2203.06317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-12T02:22:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f9070cb302412aeac0d5cfce6f1108a3f8a429ad5022a3289d7f6be00ba8e23","abstract_canon_sha256":"5f83a12ad691c0488808303b44a42dc26cd5958ec0f05865e01f1534953ec402"},"schema_version":"1.0"},"canonical_sha256":"67a555dd2d8b6adae178d409b0e3b6f744edfca6b6d913f91dfdfab38ddef213","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:25.777329Z","signature_b64":"x2Z3CsHWD9RacCrvGctwurvb9dRs8xei5Ybvce38Tx38775rFIcc8X/N4uL8I721pv8D5hVt22hWltQ57UHtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67a555dd2d8b6adae178d409b0e3b6f744edfca6b6d913f91dfdfab38ddef213","last_reissued_at":"2026-07-05T04:23:25.776903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:25.776903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.06317","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":"2026-07-05T04:23:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x+RySrqHDHOtzRmc4B5GgCdBczdaPVF6lqUJroVslwVIeDy7XXbd4QpfSOHXaxROc7LVZRSMUUGBSDyCmzE5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:09:31.686379Z"},"content_sha256":"bd29796fa868637437cc7ab96b498e455e805b45dd68453b7e41dac5c52cd323","schema_version":"1.0","event_id":"sha256:bd29796fa868637437cc7ab96b498e455e805b45dd68453b7e41dac5c52cd323"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:M6SVLXJNRNVNVYLY2QE3BY5W65","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Equal Opportunity Fairness through Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Timothy Baldwin, Trevor Cohn, Xudong Han","submitted_at":"2022-03-12T02:22:58Z","abstract_excerpt":"Adversarial training is a common approach for bias mitigation in natural language processing. Although most work on debiasing is motivated by equal opportunity, it is not explicitly captured in standard adversarial training. In this paper, we propose an augmented discriminator for adversarial training, which takes the target class as input to create richer features and more explicitly model equal opportunity. Experimental results over two datasets show that our method substantially improves over standard adversarial debiasing methods, in terms of the performance--fairness trade-off."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06317","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.06317/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":"2026-07-05T04:23:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ZL7Qt9UWPkpQLaYKwTXudcAMYcBUuNAoQXRooSztQlqXBeASGcx7AiOx6jopf8qGIS7+7Kp5Qh3GICYooWJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:09:31.686961Z"},"content_sha256":"af747720d12d3fef3411d6191d0c488b90dc68ebd260dee3daade9eb2e603c2b","schema_version":"1.0","event_id":"sha256:af747720d12d3fef3411d6191d0c488b90dc68ebd260dee3daade9eb2e603c2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6SVLXJNRNVNVYLY2QE3BY5W65/bundle.json","state_url":"https://pith.science/pith/M6SVLXJNRNVNVYLY2QE3BY5W65/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6SVLXJNRNVNVYLY2QE3BY5W65/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":"2026-08-23T02:09:31Z","links":{"resolver":"https://pith.science/pith/M6SVLXJNRNVNVYLY2QE3BY5W65","bundle":"https://pith.science/pith/M6SVLXJNRNVNVYLY2QE3BY5W65/bundle.json","state":"https://pith.science/pith/M6SVLXJNRNVNVYLY2QE3BY5W65/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6SVLXJNRNVNVYLY2QE3BY5W65/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:M6SVLXJNRNVNVYLY2QE3BY5W65","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":"5f83a12ad691c0488808303b44a42dc26cd5958ec0f05865e01f1534953ec402","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-12T02:22:58Z","title_canon_sha256":"7f9070cb302412aeac0d5cfce6f1108a3f8a429ad5022a3289d7f6be00ba8e23"},"schema_version":"1.0","source":{"id":"2203.06317","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06317","created_at":"2026-07-05T04:23:25Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06317v2","created_at":"2026-07-05T04:23:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06317","created_at":"2026-07-05T04:23:25Z"},{"alias_kind":"pith_short_12","alias_value":"M6SVLXJNRNVN","created_at":"2026-07-05T04:23:25Z"},{"alias_kind":"pith_short_16","alias_value":"M6SVLXJNRNVNVYLY","created_at":"2026-07-05T04:23:25Z"},{"alias_kind":"pith_short_8","alias_value":"M6SVLXJN","created_at":"2026-07-05T04:23:25Z"}],"graph_snapshots":[{"event_id":"sha256:af747720d12d3fef3411d6191d0c488b90dc68ebd260dee3daade9eb2e603c2b","target":"graph","created_at":"2026-07-05T04:23:25Z","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/2203.06317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial training is a common approach for bias mitigation in natural language processing. Although most work on debiasing is motivated by equal opportunity, it is not explicitly captured in standard adversarial training. In this paper, we propose an augmented discriminator for adversarial training, which takes the target class as input to create richer features and more explicitly model equal opportunity. Experimental results over two datasets show that our method substantially improves over standard adversarial debiasing methods, in terms of the performance--fairness trade-off.","authors_text":"Timothy Baldwin, Trevor Cohn, Xudong Han","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-12T02:22:58Z","title":"Towards Equal Opportunity Fairness through Adversarial Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06317","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:bd29796fa868637437cc7ab96b498e455e805b45dd68453b7e41dac5c52cd323","target":"record","created_at":"2026-07-05T04:23:25Z","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":"5f83a12ad691c0488808303b44a42dc26cd5958ec0f05865e01f1534953ec402","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-12T02:22:58Z","title_canon_sha256":"7f9070cb302412aeac0d5cfce6f1108a3f8a429ad5022a3289d7f6be00ba8e23"},"schema_version":"1.0","source":{"id":"2203.06317","kind":"arxiv","version":2}},"canonical_sha256":"67a555dd2d8b6adae178d409b0e3b6f744edfca6b6d913f91dfdfab38ddef213","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67a555dd2d8b6adae178d409b0e3b6f744edfca6b6d913f91dfdfab38ddef213","first_computed_at":"2026-07-05T04:23:25.776903Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:23:25.776903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x2Z3CsHWD9RacCrvGctwurvb9dRs8xei5Ybvce38Tx38775rFIcc8X/N4uL8I721pv8D5hVt22hWltQ57UHtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:23:25.777329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.06317","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd29796fa868637437cc7ab96b498e455e805b45dd68453b7e41dac5c52cd323","sha256:af747720d12d3fef3411d6191d0c488b90dc68ebd260dee3daade9eb2e603c2b"],"state_sha256":"8947968dc700d5efda463d34ab506267c3c2bb3354a4f5fe0ac7d3ac61ede69e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f3qNRz/9sU5fp0DHSo4BSYDSxslQ2NXzV+0CHMQXdogVUP80ZRT2/CltL5VNUp1I0F6llEZP931+hlO8B1QyCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T02:09:31.691723Z","bundle_sha256":"095c1bb68902a4125932f4f1072fd500a7880a47c352b28200c7b3f0f64238e4"}}