{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZSNXQC2ETZ4YOBHUSCQHPU367Z","short_pith_number":"pith:ZSNXQC2E","schema_version":"1.0","canonical_sha256":"cc9b780b449e798704f490a077d37efe6c82ef22e15dc6f4e3f1776c6425e4a2","source":{"kind":"arxiv","id":"2503.19540","version":1},"attestation_state":"computed","paper":{"title":"FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chanjun Park, Dahyun Jung, Heuiseok Lim, Hyeonseok Moon, Seungyoon Lee","submitted_at":"2025-03-25T10:48:33Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have significantly enhanced interactions between users and models. These advancements concurrently underscore the need for rigorous safety evaluations due to the manifestation of social biases, which can lead to harmful societal impacts. Despite these concerns, existing benchmarks may overlook the intrinsic weaknesses of LLMs, which can generate biased responses even with simple adversarial instructions. To address this critical gap, we introduce a new benchmark, Fairness Benchmark in LLM under Extreme Scenarios (FLEX), designed to test wheth"},"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":"2503.19540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-25T10:48:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea0a3a96ace235ff858b200b5f9924a98ca387ebbb95192141e57463bcd7eb9e","abstract_canon_sha256":"b4421ec7c05e13fcee0e5538e3fbaf7eed99477fac3c9af313718c58c585a089"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:56.808920Z","signature_b64":"S59DGTsFR6WH4slStpyWJml1RuirATxHYtAJl8GFqZITXi1cMEchlVPMBaYaM5idrzD4+tR9pB5HZdSMCK9PDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc9b780b449e798704f490a077d37efe6c82ef22e15dc6f4e3f1776c6425e4a2","last_reissued_at":"2026-07-05T10:38:56.808487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:56.808487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chanjun Park, Dahyun Jung, Heuiseok Lim, Hyeonseok Moon, Seungyoon Lee","submitted_at":"2025-03-25T10:48:33Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have significantly enhanced interactions between users and models. These advancements concurrently underscore the need for rigorous safety evaluations due to the manifestation of social biases, which can lead to harmful societal impacts. Despite these concerns, existing benchmarks may overlook the intrinsic weaknesses of LLMs, which can generate biased responses even with simple adversarial instructions. To address this critical gap, we introduce a new benchmark, Fairness Benchmark in LLM under Extreme Scenarios (FLEX), designed to test wheth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19540","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/2503.19540/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":"2503.19540","created_at":"2026-07-05T10:38:56.808538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19540v1","created_at":"2026-07-05T10:38:56.808538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19540","created_at":"2026-07-05T10:38:56.808538+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSNXQC2ETZ4Y","created_at":"2026-07-05T10:38:56.808538+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSNXQC2ETZ4YOBHU","created_at":"2026-07-05T10:38:56.808538+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSNXQC2E","created_at":"2026-07-05T10:38:56.808538+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14922","citing_title":"FORTRESS: Frontier Risk Evaluation for National Security and Public Safety","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSNXQC2ETZ4YOBHUSCQHPU367Z","json":"https://pith.science/pith/ZSNXQC2ETZ4YOBHUSCQHPU367Z.json","graph_json":"https://pith.science/api/pith-number/ZSNXQC2ETZ4YOBHUSCQHPU367Z/graph.json","events_json":"https://pith.science/api/pith-number/ZSNXQC2ETZ4YOBHUSCQHPU367Z/events.json","paper":"https://pith.science/paper/ZSNXQC2E"},"agent_actions":{"view_html":"https://pith.science/pith/ZSNXQC2ETZ4YOBHUSCQHPU367Z","download_json":"https://pith.science/pith/ZSNXQC2ETZ4YOBHUSCQHPU367Z.json","view_paper":"https://pith.science/paper/ZSNXQC2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19540&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSNXQC2ETZ4YOBHUSCQHPU367Z/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSNXQC2ETZ4YOBHUSCQHPU367Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSNXQC2ETZ4YOBHUSCQHPU367Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSNXQC2ETZ4YOBHUSCQHPU367Z/action/storage_attestation","attest_author":"https://pith.science/pith/ZSNXQC2ETZ4YOBHUSCQHPU367Z/action/author_attestation","sign_citation":"https://pith.science/pith/ZSNXQC2ETZ4YOBHUSCQHPU367Z/action/citation_signature","submit_replication":"https://pith.science/pith/ZSNXQC2ETZ4YOBHUSCQHPU367Z/action/replication_record"}},"created_at":"2026-07-05T10:38:56.808538+00:00","updated_at":"2026-07-05T10:38:56.808538+00:00"}