{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3BIY32JHCY5RHTDCVJOZXXE5ZK","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":"f870c44548d4472009f99da2d4c4b6a2ea013af7434fd0800ac0f2f32cb90963","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T01:49:15Z","title_canon_sha256":"77086fd9f59def51165a47d60fa888703a7d9b8a7b8001caf87515ecaca6ea34"},"schema_version":"1.0","source":{"id":"2402.12649","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12649","created_at":"2026-07-05T11:16:27Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12649v3","created_at":"2026-07-05T11:16:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12649","created_at":"2026-07-05T11:16:27Z"},{"alias_kind":"pith_short_12","alias_value":"3BIY32JHCY5R","created_at":"2026-07-05T11:16:27Z"},{"alias_kind":"pith_short_16","alias_value":"3BIY32JHCY5RHTDC","created_at":"2026-07-05T11:16:27Z"},{"alias_kind":"pith_short_8","alias_value":"3BIY32JH","created_at":"2026-07-05T11:16:27Z"}],"graph_snapshots":[{"event_id":"sha256:ac49dc8a17c598576c4b7fa7d62fc7030735d863e975151aff0ee4d2b1fd37d8","target":"graph","created_at":"2026-07-05T11:16:27Z","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/2402.12649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard benchmarks of bias and fairness in large language models (LLMs) measure the association between the user attributes stated or implied by a prompt and the LLM's short text response, but human-AI interaction increasingly requires long-form and context-specific system output to solve real-world tasks. In the commonly studied domain of gender-occupation bias, we test whether these benchmarks are robust to lengthening the LLM responses as a measure of Realistic Use and Tangible Effects (i.e., RUTEd evaluations). From the current literature, we adapt three standard bias metrics (neutrality,","authors_text":"Alexander D'Amour, Chirag Nagpal, Jacy Reese Anthis, Kevin Robinson, Kristian Lum","cross_cats":["stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T01:49:15Z","title":"Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12649","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":"sha256:6b0116a2b918558ef8dac669a5d920ef150a7c5dc3a3e35be3ec77c968b7622c","target":"record","created_at":"2026-07-05T11:16:27Z","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":"f870c44548d4472009f99da2d4c4b6a2ea013af7434fd0800ac0f2f32cb90963","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T01:49:15Z","title_canon_sha256":"77086fd9f59def51165a47d60fa888703a7d9b8a7b8001caf87515ecaca6ea34"},"schema_version":"1.0","source":{"id":"2402.12649","kind":"arxiv","version":3}},"canonical_sha256":"d8518de927163b13cc62aa5d9bdc9dcaa85b1c6ed2f0a0a16340e5ab1d7c7115","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8518de927163b13cc62aa5d9bdc9dcaa85b1c6ed2f0a0a16340e5ab1d7c7115","first_computed_at":"2026-07-05T11:16:27.601988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:27.601988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"em/EleOfhlw1MTyQCFnGolXjrj+qKwA2yR+pXqzOfCzPzfp9m7xtXYAUydaFpXRfNCxE004SRCMAtIxpTqSqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:27.602545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12649","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b0116a2b918558ef8dac669a5d920ef150a7c5dc3a3e35be3ec77c968b7622c","sha256:ac49dc8a17c598576c4b7fa7d62fc7030735d863e975151aff0ee4d2b1fd37d8"],"state_sha256":"4b0f850277fe8cad1fa36bce49f799010afd048a71bc6b21cc367f33fc0e10c5"}