{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ASEYMYS4YTRSEQ6TIFJV7KBNGE","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":"808913e57fd4e50f31239400af61e08232dd492f00cda808f9ca259d4a78a1e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-31T09:27:27Z","title_canon_sha256":"a86a7c281a044c1f72bafb3b4dd3c7a673a347ccfde90944bb6aec5b866d9895"},"schema_version":"1.0","source":{"id":"1807.11714","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11714","created_at":"2026-05-17T23:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11714v2","created_at":"2026-05-17T23:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11714","created_at":"2026-05-17T23:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"ASEYMYS4YTRS","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ASEYMYS4YTRSEQ6T","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ASEYMYS4","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:d7163a37293e46d8cd8f305d70ab8c89dae3affd7d19a5bc1b5fc68ad270c6b9","target":"graph","created_at":"2026-05-17T23:44:38Z","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":"We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with state-of-the-art neural coreference resolution and textbook RNN-based language models trained on benchmark datasets finds significant gender bias in how models view occupations. We then mitigate bias with CDA: a generic methodology for corpus augmentation via causal interventions that breaks associations between gendered and gender-neutral words. We empirically show t","authors_text":"Anupam Datta, Fangjing Wu, Kaiji Lu, Piotr Mardziel, Preetam Amancharla","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-31T09:27:27Z","title":"Gender Bias in Neural Natural Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11714","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:b0ce5858bc51a675d9038140b382cfbcc02435a842265321565c472ec62e20db","target":"record","created_at":"2026-05-17T23:44:38Z","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":"808913e57fd4e50f31239400af61e08232dd492f00cda808f9ca259d4a78a1e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-31T09:27:27Z","title_canon_sha256":"a86a7c281a044c1f72bafb3b4dd3c7a673a347ccfde90944bb6aec5b866d9895"},"schema_version":"1.0","source":{"id":"1807.11714","kind":"arxiv","version":2}},"canonical_sha256":"048986625cc4e32243d341535fa82d3107718d04edbdbac6ad441f7cbde69f2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"048986625cc4e32243d341535fa82d3107718d04edbdbac6ad441f7cbde69f2b","first_computed_at":"2026-05-17T23:44:38.134254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:38.134254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+wwZ8ouGxERo39v0KYjH7iSLvoLpwArnDn8ylYuY1K4faTF+nX35+CFV10HLQN+9H5CkaxkI6Ff5AZnCDqKdCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:38.134779Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.11714","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0ce5858bc51a675d9038140b382cfbcc02435a842265321565c472ec62e20db","sha256:d7163a37293e46d8cd8f305d70ab8c89dae3affd7d19a5bc1b5fc68ad270c6b9"],"state_sha256":"78b6caf2e917b64a048656041145df10061aabaf19f5a1c00f41f6fa055c68a9"}