{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JRZRKXK24H67FRR2GGW2XY6IHJ","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":"1e2dab671fa82225c3c4480058efbc0834ed4d14901c9a8daee3d1f5aecb1346","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-08T18:14:11Z","title_canon_sha256":"42834cfc951e9fb03e3d39d7b831c70f4e659ddaa9d769091fb1caefcbcb2fa8"},"schema_version":"1.0","source":{"id":"2109.03858","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.03858","created_at":"2026-07-05T03:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2109.03858v2","created_at":"2026-07-05T03:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03858","created_at":"2026-07-05T03:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"JRZRKXK24H67","created_at":"2026-07-05T03:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"JRZRKXK24H67FRR2","created_at":"2026-07-05T03:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"JRZRKXK2","created_at":"2026-07-05T03:13:06Z"}],"graph_snapshots":[{"event_id":"sha256:9839b6b4d97112a4555a8bfae8d4fcd4b83f6fe117f6f7464ffa645c5b615a68","target":"graph","created_at":"2026-07-05T03:13:06Z","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/2109.03858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale and consist mostly of artificial, out-of-distribution sentences. In this work, we find grammatical patterns indicating stereotypical and non-stereotypical gender-role assignments (e.g., female nurses versus male dancers) in corpora from three domains, resulting in a first large-scale gender bias dataset of 108K diverse real-world English sentences. We manual","authors_text":"Gabriel Stanovsky, Koren Lazar, Shahar Levy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-08T18:14:11Z","title":"Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03858","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:cca1e3540dd3fc6fae515201adef2249cfbda3a1c30415f8262c2416364cd31b","target":"record","created_at":"2026-07-05T03:13:06Z","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":"1e2dab671fa82225c3c4480058efbc0834ed4d14901c9a8daee3d1f5aecb1346","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-08T18:14:11Z","title_canon_sha256":"42834cfc951e9fb03e3d39d7b831c70f4e659ddaa9d769091fb1caefcbcb2fa8"},"schema_version":"1.0","source":{"id":"2109.03858","kind":"arxiv","version":2}},"canonical_sha256":"4c73155d5ae1fdf2c63a31adabe3c83a7d2a5aa7838d7680f01948a2c2f3e8f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c73155d5ae1fdf2c63a31adabe3c83a7d2a5aa7838d7680f01948a2c2f3e8f1","first_computed_at":"2026-07-05T03:13:06.119034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:06.119034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SHPbHEhXSvzWqm9LmVl5I4bMXMm1j6mZeFJL5H40mpGYo0/zyl1V3AFIz+iJHJKC8vk8q29YRS+eSa5z8z2qCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:06.119500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.03858","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cca1e3540dd3fc6fae515201adef2249cfbda3a1c30415f8262c2416364cd31b","sha256:9839b6b4d97112a4555a8bfae8d4fcd4b83f6fe117f6f7464ffa645c5b615a68"],"state_sha256":"1dcea9dceae284f767491d82d919776f54f59bf9166964f4d7023c34104b55a4"}