{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7NI6XQTLA3XPJNDWR7EFK2RQXO","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":"54f9b0769f57728cf9ab4e4faf9d81e0f2b6c1f69de0b320257c8ab8db3f956a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T02:51:33Z","title_canon_sha256":"c392bddbfecc7e2261220da0ec4369d4cc21d110eb346336549388b61696f96a"},"schema_version":"1.0","source":{"id":"2410.17519","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17519","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17519v3","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17519","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"7NI6XQTLA3XP","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"7NI6XQTLA3XPJNDW","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"7NI6XQTL","created_at":"2026-07-05T11:49:47Z"}],"graph_snapshots":[{"event_id":"sha256:929514e8f888d863974a4469cb19b85717409c04603eae0caa1d487e00e981a5","target":"graph","created_at":"2026-07-05T11:49:47Z","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/2410.17519/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing fairness benchmarks for large language models (LLMs) primarily focus on simple tasks, such as multiple-choice questions, overlooking biases that may arise in more complex scenarios like long-text generation. To address this gap, we introduce the Long Text Fairness Test (LTF-TEST), a framework that evaluates biases in LLMs through essay-style prompts. LTF-TEST covers 14 topics and 10 demographic axes, including gender and race, resulting in 11,948 samples. By assessing both model responses and the reasoning behind them, LTF-TEST uncovers subtle biases that are difficult to detect in si","authors_text":"Ashkan Yousefpour, Dongjae Jeon, Jonghyun Choi, Wonje Jeung","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T02:51:33Z","title":"Large Language Models Still Exhibit Bias in Long Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17519","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:bb7ff5339ff6b58be6a59c1e9f491855592f1630605bbfb3db90f058cd3c498d","target":"record","created_at":"2026-07-05T11:49:47Z","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":"54f9b0769f57728cf9ab4e4faf9d81e0f2b6c1f69de0b320257c8ab8db3f956a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T02:51:33Z","title_canon_sha256":"c392bddbfecc7e2261220da0ec4369d4cc21d110eb346336549388b61696f96a"},"schema_version":"1.0","source":{"id":"2410.17519","kind":"arxiv","version":3}},"canonical_sha256":"fb51ebc26b06eef4b4768fc8556a30bb8a6cacd239693c51948d2235de67f6f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb51ebc26b06eef4b4768fc8556a30bb8a6cacd239693c51948d2235de67f6f5","first_computed_at":"2026-07-05T11:49:47.707148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:47.707148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tllql2AOOEu9p4/TZsYM5FT06XcH2MrWYT/mOJQ8FlGDZbWzAfzPrE1QKIMfJnaLlNBZxtfsj+bqWWwXxqpLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:47.707579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17519","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb7ff5339ff6b58be6a59c1e9f491855592f1630605bbfb3db90f058cd3c498d","sha256:929514e8f888d863974a4469cb19b85717409c04603eae0caa1d487e00e981a5"],"state_sha256":"32e6697712c8851d36f4b48c6142e78fda212870fa121f3a032742c5151f9973"}