{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DBQZWB7HSFLMUNH42UOMI4CYUV","short_pith_number":"pith:DBQZWB7H","schema_version":"1.0","canonical_sha256":"18619b07e79156ca34fcd51cc47058a5711b4d92d203df5b17296e50060b474c","source":{"kind":"arxiv","id":"2503.24310","version":1},"attestation_state":"computed","paper":{"title":"BEATS: Bias Evaluation and Assessment Test Suite for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alok Abhishek, Lisa Erickson, Tushar Bandopadhyay","submitted_at":"2025-03-31T16:56:52Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.24310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T16:56:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"66d73d0e873875cef197add721727fcd4d7f05c04f31ae54dc719639e7830501","abstract_canon_sha256":"57fbbbbdef87795a359de94df90f3b86392cb8a858157dafcae353218da647fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:08.073232Z","signature_b64":"nhmGNgDdj2ytf8Ch87hcAW0GPwXDRV/JoGBrD2tO4QeVwkAmUdPRrcjrQMgOrebcQ7J/ST8oWomL+YQnlkhOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18619b07e79156ca34fcd51cc47058a5711b4d92d203df5b17296e50060b474c","last_reissued_at":"2026-07-05T10:42:08.072794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:08.072794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEATS: Bias Evaluation and Assessment Test Suite for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alok Abhishek, Lisa Erickson, Tushar Bandopadhyay","submitted_at":"2025-03-31T16:56:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.24310","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.24310/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.24310","created_at":"2026-07-05T10:42:08.072851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.24310v1","created_at":"2026-07-05T10:42:08.072851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.24310","created_at":"2026-07-05T10:42:08.072851+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBQZWB7HSFLM","created_at":"2026-07-05T10:42:08.072851+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBQZWB7HSFLMUNH4","created_at":"2026-07-05T10:42:08.072851+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBQZWB7H","created_at":"2026-07-05T10:42:08.072851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03970","citing_title":"Data and AI governance: Promoting equity, ethics, and fairness in large language models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBQZWB7HSFLMUNH42UOMI4CYUV","json":"https://pith.science/pith/DBQZWB7HSFLMUNH42UOMI4CYUV.json","graph_json":"https://pith.science/api/pith-number/DBQZWB7HSFLMUNH42UOMI4CYUV/graph.json","events_json":"https://pith.science/api/pith-number/DBQZWB7HSFLMUNH42UOMI4CYUV/events.json","paper":"https://pith.science/paper/DBQZWB7H"},"agent_actions":{"view_html":"https://pith.science/pith/DBQZWB7HSFLMUNH42UOMI4CYUV","download_json":"https://pith.science/pith/DBQZWB7HSFLMUNH42UOMI4CYUV.json","view_paper":"https://pith.science/paper/DBQZWB7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.24310&json=true","fetch_graph":"https://pith.science/api/pith-number/DBQZWB7HSFLMUNH42UOMI4CYUV/graph.json","fetch_events":"https://pith.science/api/pith-number/DBQZWB7HSFLMUNH42UOMI4CYUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBQZWB7HSFLMUNH42UOMI4CYUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBQZWB7HSFLMUNH42UOMI4CYUV/action/storage_attestation","attest_author":"https://pith.science/pith/DBQZWB7HSFLMUNH42UOMI4CYUV/action/author_attestation","sign_citation":"https://pith.science/pith/DBQZWB7HSFLMUNH42UOMI4CYUV/action/citation_signature","submit_replication":"https://pith.science/pith/DBQZWB7HSFLMUNH42UOMI4CYUV/action/replication_record"}},"created_at":"2026-07-05T10:42:08.072851+00:00","updated_at":"2026-07-05T10:42:08.072851+00:00"}