{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DBQZWB7HSFLMUNH42UOMI4CYUV","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":"57fbbbbdef87795a359de94df90f3b86392cb8a858157dafcae353218da647fb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T16:56:52Z","title_canon_sha256":"66d73d0e873875cef197add721727fcd4d7f05c04f31ae54dc719639e7830501"},"schema_version":"1.0","source":{"id":"2503.24310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.24310","created_at":"2026-07-05T10:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"2503.24310v1","created_at":"2026-07-05T10:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.24310","created_at":"2026-07-05T10:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"DBQZWB7HSFLM","created_at":"2026-07-05T10:42:08Z"},{"alias_kind":"pith_short_16","alias_value":"DBQZWB7HSFLMUNH4","created_at":"2026-07-05T10:42:08Z"},{"alias_kind":"pith_short_8","alias_value":"DBQZWB7H","created_at":"2026-07-05T10:42:08Z"}],"graph_snapshots":[{"event_id":"sha256:92aa68a32f130989fe1846aefa7ea0394738457d80081e07fca2ac7d4b77814f","target":"graph","created_at":"2026-07-05T10:42:08Z","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/2503.24310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this research, we introduce BEATS, a novel framework for evaluating Bias, Ethics, Fairness, and Factuality in Large Language Models (LLMs). Building upon the BEATS framework, we present a bias benchmark for LLMs that measure performance across 29 distinct metrics. These metrics span a broad range of characteristics, including demographic, cognitive, and social biases, as well as measures of ethical reasoning, group fairness, and factuality related misinformation risk. These metrics enable a quantitative assessment of the extent to which LLM generated responses may perpetuate societal prejud","authors_text":"Alok Abhishek, Lisa Erickson, Tushar Bandopadhyay","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T16:56:52Z","title":"BEATS: Bias Evaluation and Assessment Test Suite for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.24310","kind":"arxiv","version":1},"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":"sha256:02c4e80826e333c351522637a2efb26b56c3b22181ca1eb0dcf1ec400ce62dd8","target":"record","created_at":"2026-07-05T10:42:08Z","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":"57fbbbbdef87795a359de94df90f3b86392cb8a858157dafcae353218da647fb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T16:56:52Z","title_canon_sha256":"66d73d0e873875cef197add721727fcd4d7f05c04f31ae54dc719639e7830501"},"schema_version":"1.0","source":{"id":"2503.24310","kind":"arxiv","version":1}},"canonical_sha256":"18619b07e79156ca34fcd51cc47058a5711b4d92d203df5b17296e50060b474c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18619b07e79156ca34fcd51cc47058a5711b4d92d203df5b17296e50060b474c","first_computed_at":"2026-07-05T10:42:08.072794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:08.072794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nhmGNgDdj2ytf8Ch87hcAW0GPwXDRV/JoGBrD2tO4QeVwkAmUdPRrcjrQMgOrebcQ7J/ST8oWomL+YQnlkhOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:08.073232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.24310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02c4e80826e333c351522637a2efb26b56c3b22181ca1eb0dcf1ec400ce62dd8","sha256:92aa68a32f130989fe1846aefa7ea0394738457d80081e07fca2ac7d4b77814f"],"state_sha256":"f8419116bed721e7a6332d1edca9524ff388498a90cdb452ccf4a55de0866fcc"}