{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GWHX5H2RK36ZY7JF3SLYMP2GEU","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":"133af41fdf31227757f3632f807def60cf544422c0824072786b73b12ff83dee","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T22:41:24Z","title_canon_sha256":"a5408d1c6a9caf46e4423b26a2203ad28cf70b89501fd36f211aa2c01477074a"},"schema_version":"1.0","source":{"id":"2212.10678","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10678","created_at":"2026-07-05T11:42:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10678v4","created_at":"2026-07-05T11:42:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10678","created_at":"2026-07-05T11:42:19Z"},{"alias_kind":"pith_short_12","alias_value":"GWHX5H2RK36Z","created_at":"2026-07-05T11:42:19Z"},{"alias_kind":"pith_short_16","alias_value":"GWHX5H2RK36ZY7JF","created_at":"2026-07-05T11:42:19Z"},{"alias_kind":"pith_short_8","alias_value":"GWHX5H2R","created_at":"2026-07-05T11:42:19Z"}],"graph_snapshots":[{"event_id":"sha256:0d99c4d23313d9989a3e8d2264a8c2892dd4e787d6b9fe690464dcfdd0522f78","target":"graph","created_at":"2026-07-05T11:42:19Z","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/2212.10678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generated texts from large language models (LLMs) have been shown to exhibit a variety of harmful, human-like biases against various demographics. These findings motivate research efforts aiming to understand and measure such effects. This paper introduces a causal formulation for bias measurement in generative language models. Based on this theoretical foundation, we outline a list of desiderata for designing robust bias benchmarks. We then propose a benchmark called OccuGender, with a bias-measuring procedure to investigate occupational gender bias. We test several state-of-the-art open-sour","authors_text":"Justus Mattern, Rada Mihalcea, Vethavikashini Chithrra Raghuram, Yuen Chen, Zhijing Jin","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T22:41:24Z","title":"Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10678","kind":"arxiv","version":4},"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:d5e277a1e19649d1fbeae44ee81aee3772e5f10e570438254dfbb38512898498","target":"record","created_at":"2026-07-05T11:42:19Z","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":"133af41fdf31227757f3632f807def60cf544422c0824072786b73b12ff83dee","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T22:41:24Z","title_canon_sha256":"a5408d1c6a9caf46e4423b26a2203ad28cf70b89501fd36f211aa2c01477074a"},"schema_version":"1.0","source":{"id":"2212.10678","kind":"arxiv","version":4}},"canonical_sha256":"358f7e9f5156fd9c7d25dc97863f4625322291bf1af6f738c86624028d1370ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"358f7e9f5156fd9c7d25dc97863f4625322291bf1af6f738c86624028d1370ef","first_computed_at":"2026-07-05T11:42:19.308199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:19.308199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ABq6Bhu5tpJs0mNMQAiZSWuDGhxMwcloIzpy0kiVMTcwcAoUw7ahW0gYk6uNqZHf55COKmw4CZ/3GtmG37mLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:19.308645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10678","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5e277a1e19649d1fbeae44ee81aee3772e5f10e570438254dfbb38512898498","sha256:0d99c4d23313d9989a3e8d2264a8c2892dd4e787d6b9fe690464dcfdd0522f78"],"state_sha256":"3f0538ee514b35981a1df076c91fe2e653aa3156cee392578e33b118b86d7424"}