{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BGPUMWDOBUIUZNYJ6B6KSMY26H","short_pith_number":"pith:BGPUMWDO","schema_version":"1.0","canonical_sha256":"099f46586e0d114cb709f07ca9331af1f90fc37f0188b8caa8c05070b695df9c","source":{"kind":"arxiv","id":"2309.14345","version":4},"attestation_state":"computed","paper":{"title":"Bias Testing and Mitigation in LLM-based Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Dong Huang, Heming Cui, Jie M. Zhang, Junjie Chen, Qingwen Bu, Xiaofei Xie","submitted_at":"2023-09-03T07:14:49Z","abstract_excerpt":"As the adoption of LLMs becomes more widespread in software coding ecosystems, a pressing issue has emerged: does the generated code contain social bias and unfairness, such as those related to age, gender, and race? This issue concerns the integrity, fairness, and ethical foundation of software applications that depend on the code generated by these models but are underexplored in the literature. This paper presents a novel bias testing framework that is specifically designed for code generation tasks. Based on this framework, we conduct an extensive empirical study on the biases in code gene"},"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":"2309.14345","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-09-03T07:14:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68eaa2163e20e0810bd7b557d24e20550b8a96794f435ffc7a65aa8851674734","abstract_canon_sha256":"e9870bb205e039d78beda6125cb38746af6a905da665505084aa77950a45beff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:21.774349Z","signature_b64":"h5cEMpflu/G7SYSErhzL2vPvAu8eMA71BpGLja8ubfatEbjZLDPEA7nsyeBuA/ggbEzZTztAgOQa1OWWiA8CCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"099f46586e0d114cb709f07ca9331af1f90fc37f0188b8caa8c05070b695df9c","last_reissued_at":"2026-07-05T10:36:21.773752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:21.773752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bias Testing and Mitigation in LLM-based Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Dong Huang, Heming Cui, Jie M. Zhang, Junjie Chen, Qingwen Bu, Xiaofei Xie","submitted_at":"2023-09-03T07:14:49Z","abstract_excerpt":"As the adoption of LLMs becomes more widespread in software coding ecosystems, a pressing issue has emerged: does the generated code contain social bias and unfairness, such as those related to age, gender, and race? This issue concerns the integrity, fairness, and ethical foundation of software applications that depend on the code generated by these models but are underexplored in the literature. This paper presents a novel bias testing framework that is specifically designed for code generation tasks. Based on this framework, we conduct an extensive empirical study on the biases in code gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14345","kind":"arxiv","version":4},"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/2309.14345/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":"2309.14345","created_at":"2026-07-05T10:36:21.773818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.14345v4","created_at":"2026-07-05T10:36:21.773818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14345","created_at":"2026-07-05T10:36:21.773818+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGPUMWDOBUIU","created_at":"2026-07-05T10:36:21.773818+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGPUMWDOBUIUZNYJ","created_at":"2026-07-05T10:36:21.773818+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGPUMWDO","created_at":"2026-07-05T10:36:21.773818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.17181","citing_title":"A Study of LLMs' Preferences for Libraries and Programming Languages","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19353","citing_title":"Architectures of Error: A Philosophical Inquiry into AI and Human Code Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03860","citing_title":"LiquiLM: Bridging the Semantic Gap in Liquidity Flaw Audit via DCN and LLMs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19173","citing_title":"StarCoder 2 and The Stack v2: The Next Generation","ref_index":215,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13103","citing_title":"Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGPUMWDOBUIUZNYJ6B6KSMY26H","json":"https://pith.science/pith/BGPUMWDOBUIUZNYJ6B6KSMY26H.json","graph_json":"https://pith.science/api/pith-number/BGPUMWDOBUIUZNYJ6B6KSMY26H/graph.json","events_json":"https://pith.science/api/pith-number/BGPUMWDOBUIUZNYJ6B6KSMY26H/events.json","paper":"https://pith.science/paper/BGPUMWDO"},"agent_actions":{"view_html":"https://pith.science/pith/BGPUMWDOBUIUZNYJ6B6KSMY26H","download_json":"https://pith.science/pith/BGPUMWDOBUIUZNYJ6B6KSMY26H.json","view_paper":"https://pith.science/paper/BGPUMWDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.14345&json=true","fetch_graph":"https://pith.science/api/pith-number/BGPUMWDOBUIUZNYJ6B6KSMY26H/graph.json","fetch_events":"https://pith.science/api/pith-number/BGPUMWDOBUIUZNYJ6B6KSMY26H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGPUMWDOBUIUZNYJ6B6KSMY26H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGPUMWDOBUIUZNYJ6B6KSMY26H/action/storage_attestation","attest_author":"https://pith.science/pith/BGPUMWDOBUIUZNYJ6B6KSMY26H/action/author_attestation","sign_citation":"https://pith.science/pith/BGPUMWDOBUIUZNYJ6B6KSMY26H/action/citation_signature","submit_replication":"https://pith.science/pith/BGPUMWDOBUIUZNYJ6B6KSMY26H/action/replication_record"}},"created_at":"2026-07-05T10:36:21.773818+00:00","updated_at":"2026-07-05T10:36:21.773818+00:00"}