{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DCGKAJ7LVO7PCRZQ6WUMM3J2AS","short_pith_number":"pith:DCGKAJ7L","schema_version":"1.0","canonical_sha256":"188ca027ebabbef14730f5a8c66d3a04aba96cf693597f2697664568a388b028","source":{"kind":"arxiv","id":"2501.05396","version":2},"attestation_state":"computed","paper":{"title":"FairCoder: Evaluating Social Bias of LLMs in Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Jen-tse Huang, Jieyu Zhao, Lu Lin, Yongkang Du","submitted_at":"2025-01-09T17:42:23Z","abstract_excerpt":"Large language models (LLMs) have been widely deployed in coding tasks, drawing increasing attention to the evaluation of the quality and safety of LLMs' outputs. However, research on bias in code generation remains limited. Existing studies typically identify bias by applying malicious prompts or reusing tasks and dataset originally designed for discriminative models. Given that prior datasets are not fully optimized for code-related tasks, there is a pressing need for benchmarks specifically designed for evaluating code models. In this study, we introduce FairCoder, a novel benchmark for eva"},"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":"2501.05396","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T17:42:23Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"27bf4b2f2ccb93ae5098b29d9360d740f8c9cfbc3356afa15cdb23dbfc44fa7a","abstract_canon_sha256":"4c049cf375c669606b11010563c9ea84512b3df04dad53f03c98dad481bd0e8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:04.325261Z","signature_b64":"+24QISh12LtgSUDrhUtM0iicNhHsDHxmvz/ZY0qveZQSKXuqIFlc/k3AHIe9o1j1SSs67eo82f394DbiaiAcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"188ca027ebabbef14730f5a8c66d3a04aba96cf693597f2697664568a388b028","last_reissued_at":"2026-07-05T10:43:04.324797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:04.324797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FairCoder: Evaluating Social Bias of LLMs in Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Jen-tse Huang, Jieyu Zhao, Lu Lin, Yongkang Du","submitted_at":"2025-01-09T17:42:23Z","abstract_excerpt":"Large language models (LLMs) have been widely deployed in coding tasks, drawing increasing attention to the evaluation of the quality and safety of LLMs' outputs. However, research on bias in code generation remains limited. Existing studies typically identify bias by applying malicious prompts or reusing tasks and dataset originally designed for discriminative models. Given that prior datasets are not fully optimized for code-related tasks, there is a pressing need for benchmarks specifically designed for evaluating code models. In this study, we introduce FairCoder, a novel benchmark for eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05396","kind":"arxiv","version":2},"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/2501.05396/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":"2501.05396","created_at":"2026-07-05T10:43:04.324852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05396v2","created_at":"2026-07-05T10:43:04.324852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05396","created_at":"2026-07-05T10:43:04.324852+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCGKAJ7LVO7P","created_at":"2026-07-05T10:43:04.324852+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCGKAJ7LVO7PCRZQ","created_at":"2026-07-05T10:43:04.324852+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCGKAJ7L","created_at":"2026-07-05T10:43:04.324852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07480","citing_title":"Biased or Personalized? The Impact of Personal Information on AI-driven Development","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCGKAJ7LVO7PCRZQ6WUMM3J2AS","json":"https://pith.science/pith/DCGKAJ7LVO7PCRZQ6WUMM3J2AS.json","graph_json":"https://pith.science/api/pith-number/DCGKAJ7LVO7PCRZQ6WUMM3J2AS/graph.json","events_json":"https://pith.science/api/pith-number/DCGKAJ7LVO7PCRZQ6WUMM3J2AS/events.json","paper":"https://pith.science/paper/DCGKAJ7L"},"agent_actions":{"view_html":"https://pith.science/pith/DCGKAJ7LVO7PCRZQ6WUMM3J2AS","download_json":"https://pith.science/pith/DCGKAJ7LVO7PCRZQ6WUMM3J2AS.json","view_paper":"https://pith.science/paper/DCGKAJ7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05396&json=true","fetch_graph":"https://pith.science/api/pith-number/DCGKAJ7LVO7PCRZQ6WUMM3J2AS/graph.json","fetch_events":"https://pith.science/api/pith-number/DCGKAJ7LVO7PCRZQ6WUMM3J2AS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCGKAJ7LVO7PCRZQ6WUMM3J2AS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCGKAJ7LVO7PCRZQ6WUMM3J2AS/action/storage_attestation","attest_author":"https://pith.science/pith/DCGKAJ7LVO7PCRZQ6WUMM3J2AS/action/author_attestation","sign_citation":"https://pith.science/pith/DCGKAJ7LVO7PCRZQ6WUMM3J2AS/action/citation_signature","submit_replication":"https://pith.science/pith/DCGKAJ7LVO7PCRZQ6WUMM3J2AS/action/replication_record"}},"created_at":"2026-07-05T10:43:04.324852+00:00","updated_at":"2026-07-05T10:43:04.324852+00:00"}