{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NSH4NOCME3CVVTWPFSSTBLP3X4","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":"9bd60b9a05d7324f468dc2a4d0074aef700580764dffb1dfe0a29376b667b718","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T16:31:37Z","title_canon_sha256":"2b5e23ecf91921231523d52f8db86a11db444c0088b317fa6d8bb7575ce46c64"},"schema_version":"1.0","source":{"id":"2407.02408","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02408","created_at":"2026-07-05T10:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02408v2","created_at":"2026-07-05T10:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02408","created_at":"2026-07-05T10:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"NSH4NOCME3CV","created_at":"2026-07-05T10:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"NSH4NOCME3CVVTWP","created_at":"2026-07-05T10:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"NSH4NOCM","created_at":"2026-07-05T10:18:09Z"}],"graph_snapshots":[{"event_id":"sha256:efcc2632a827d5030b4ac2b156714b58a5cfd900b19c4a5505e18e3f521fbf58","target":"graph","created_at":"2026-07-05T10:18:09Z","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/2407.02408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks, concerns regarding the potential negative societal impacts of LLM-generated content have also arisen. To evaluate the biases exhibited by LLMs, researchers have recently proposed a variety of datasets. However, existing bias evaluation efforts often focus on only a particular type of bias and employ inconsistent evaluation metrics, leading to difficulties in comparison across different datasets and LLMs. To address these limitations, we collect a variety of datasets designed for","authors_text":"Jundong Li, Peng Wang, Song Wang, Tong Zhou, Yushun Dong, Zhen Tan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T16:31:37Z","title":"CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02408","kind":"arxiv","version":2},"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":"sha256:89d9a39d617e59a651746ba1eaf365a91e53e77c11d45befc025fcbf9c71ac84","target":"record","created_at":"2026-07-05T10:18:09Z","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":"9bd60b9a05d7324f468dc2a4d0074aef700580764dffb1dfe0a29376b667b718","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T16:31:37Z","title_canon_sha256":"2b5e23ecf91921231523d52f8db86a11db444c0088b317fa6d8bb7575ce46c64"},"schema_version":"1.0","source":{"id":"2407.02408","kind":"arxiv","version":2}},"canonical_sha256":"6c8fc6b84c26c55acecf2ca530adfbbf12fd6586acdae2f4d99c0a474fc40e4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c8fc6b84c26c55acecf2ca530adfbbf12fd6586acdae2f4d99c0a474fc40e4d","first_computed_at":"2026-07-05T10:18:09.080591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:09.080591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kbkrQjopOq8/uOL3gJfcCqzhx+rrArVOVHBEB8uBN2YBb9in8HVCTyDXdL9oZAmIH8hE4COZX7o51gKm7fbZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:09.081054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02408","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89d9a39d617e59a651746ba1eaf365a91e53e77c11d45befc025fcbf9c71ac84","sha256:efcc2632a827d5030b4ac2b156714b58a5cfd900b19c4a5505e18e3f521fbf58"],"state_sha256":"12bc4888429e0588db787d3f2b4a7af3026a3e63105dbd057cf389893b7706ba"}