{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5DOJW3O62AUIPFDMCSQS24KCVU","short_pith_number":"pith:5DOJW3O6","schema_version":"1.0","canonical_sha256":"e8dc9b6dded02887946c14a12d7142ad0e600fbd2bb55dd04651ae9f838b3d10","source":{"kind":"arxiv","id":"2305.15377","version":1},"attestation_state":"computed","paper":{"title":"Uncovering and Quantifying Social Biases in Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daoguang Zan, Fengji Zhang, Jian-Guang Lou, Pin-Yu Chen, Tsung-Yi Ho, Xiaokang Chen, Yan Gao, Yan Liu, Zhe Su","submitted_at":"2023-05-24T17:37:33Z","abstract_excerpt":"With the popularity of automatic code generation tools, such as Copilot, the study of the potential hazards of these tools is gaining importance. In this work, we explore the social bias problem in pre-trained code generation models. We propose a new paradigm to construct code prompts and successfully uncover social biases in code generation models. To quantify the severity of social biases in generated code, we develop a dataset along with three metrics to evaluate the overall social bias and fine-grained unfairness across different demographics. Experimental results on three pre-trained code"},"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":"2305.15377","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"5386a9735b2c2e81b720e57aeeca62d8c7fcdf625bff5cac04c316590850a8d7","abstract_canon_sha256":"63ccb337f957f5066eb78145b76706fbd918b2b7a238bfdaee0016103a37e1f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:34.544238Z","signature_b64":"RirKnpvinOQjBNNr4tShC/xtizeS9zAcUCD8dfcrJtDpur/CGXXOTDvahRBM3SQTctkumavQJsAAHfWVENDIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8dc9b6dded02887946c14a12d7142ad0e600fbd2bb55dd04651ae9f838b3d10","last_reissued_at":"2026-07-05T06:13:34.543869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:34.543869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncovering and Quantifying Social Biases in Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daoguang Zan, Fengji Zhang, Jian-Guang Lou, Pin-Yu Chen, Tsung-Yi Ho, Xiaokang Chen, Yan Gao, Yan Liu, Zhe Su","submitted_at":"2023-05-24T17:37:33Z","abstract_excerpt":"With the popularity of automatic code generation tools, such as Copilot, the study of the potential hazards of these tools is gaining importance. In this work, we explore the social bias problem in pre-trained code generation models. We propose a new paradigm to construct code prompts and successfully uncover social biases in code generation models. To quantify the severity of social biases in generated code, we develop a dataset along with three metrics to evaluate the overall social bias and fine-grained unfairness across different demographics. Experimental results on three pre-trained code"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15377","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/2305.15377/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":"2305.15377","created_at":"2026-07-05T06:13:34.543923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15377v1","created_at":"2026-07-05T06:13:34.543923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15377","created_at":"2026-07-05T06:13:34.543923+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DOJW3O62AUI","created_at":"2026-07-05T06:13:34.543923+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DOJW3O62AUIPFDM","created_at":"2026-07-05T06:13:34.543923+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DOJW3O6","created_at":"2026-07-05T06:13:34.543923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.17181","citing_title":"A Study of LLMs' Preferences for Libraries and Programming Languages","ref_index":49,"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":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DOJW3O62AUIPFDMCSQS24KCVU","json":"https://pith.science/pith/5DOJW3O62AUIPFDMCSQS24KCVU.json","graph_json":"https://pith.science/api/pith-number/5DOJW3O62AUIPFDMCSQS24KCVU/graph.json","events_json":"https://pith.science/api/pith-number/5DOJW3O62AUIPFDMCSQS24KCVU/events.json","paper":"https://pith.science/paper/5DOJW3O6"},"agent_actions":{"view_html":"https://pith.science/pith/5DOJW3O62AUIPFDMCSQS24KCVU","download_json":"https://pith.science/pith/5DOJW3O62AUIPFDMCSQS24KCVU.json","view_paper":"https://pith.science/paper/5DOJW3O6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15377&json=true","fetch_graph":"https://pith.science/api/pith-number/5DOJW3O62AUIPFDMCSQS24KCVU/graph.json","fetch_events":"https://pith.science/api/pith-number/5DOJW3O62AUIPFDMCSQS24KCVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DOJW3O62AUIPFDMCSQS24KCVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DOJW3O62AUIPFDMCSQS24KCVU/action/storage_attestation","attest_author":"https://pith.science/pith/5DOJW3O62AUIPFDMCSQS24KCVU/action/author_attestation","sign_citation":"https://pith.science/pith/5DOJW3O62AUIPFDMCSQS24KCVU/action/citation_signature","submit_replication":"https://pith.science/pith/5DOJW3O62AUIPFDMCSQS24KCVU/action/replication_record"}},"created_at":"2026-07-05T06:13:34.543923+00:00","updated_at":"2026-07-05T06:13:34.543923+00:00"}