{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QWHQPIXNI3QHLBFOYPH3VVTLA2","short_pith_number":"pith:QWHQPIXN","schema_version":"1.0","canonical_sha256":"858f07a2ed46e07584aec3cfbad66b069a934925e6526eaa5ddecf4de4313216","source":{"kind":"arxiv","id":"2405.04412","version":3},"attestation_state":"computed","paper":{"title":"The Silicon Ceiling: Auditing GPT's Race and Gender Biases in Hiring","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Abbey Liu, Dana\\\"e Metaxa, Lena Armstrong, Stephen MacNeil","submitted_at":"2024-05-07T15:39:45Z","abstract_excerpt":"Large language models (LLMs) are increasingly being introduced in workplace settings, with the goals of improving efficiency and fairness. However, concerns have arisen regarding these models' potential to reflect or exacerbate social biases and stereotypes. This study explores the potential impact of LLMs on hiring practices. To do so, we conduct an AI audit of race and gender biases in one commonly-used LLM, OpenAI's GPT-3.5, taking inspiration from the history of traditional offline resume audits. We conduct two studies using names with varied race and gender connotations: resume assessment"},"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":"2405.04412","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2024-05-07T15:39:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8f7304a6ab218384c80f33e13d83d2b5acb663726fd813c9c869558f3e11207d","abstract_canon_sha256":"04a61a5891ad4c36100572e6d4830a1ce1f327bf90074c4fe83b08f34bf25b26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:48.974631Z","signature_b64":"xLGNVQSv7GYiyMlIBkOzImzKmLVAlwuG59+voVn8v9hVZZeLWQBKTkfMWq1Y9iXqaC7kOVX+SUH0GnLw2b0+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"858f07a2ed46e07584aec3cfbad66b069a934925e6526eaa5ddecf4de4313216","last_reissued_at":"2026-07-05T09:35:48.974100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:48.974100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Silicon Ceiling: Auditing GPT's Race and Gender Biases in Hiring","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Abbey Liu, Dana\\\"e Metaxa, Lena Armstrong, Stephen MacNeil","submitted_at":"2024-05-07T15:39:45Z","abstract_excerpt":"Large language models (LLMs) are increasingly being introduced in workplace settings, with the goals of improving efficiency and fairness. However, concerns have arisen regarding these models' potential to reflect or exacerbate social biases and stereotypes. This study explores the potential impact of LLMs on hiring practices. To do so, we conduct an AI audit of race and gender biases in one commonly-used LLM, OpenAI's GPT-3.5, taking inspiration from the history of traditional offline resume audits. We conduct two studies using names with varied race and gender connotations: resume assessment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04412","kind":"arxiv","version":3},"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/2405.04412/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":"2405.04412","created_at":"2026-07-05T09:35:48.974155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04412v3","created_at":"2026-07-05T09:35:48.974155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04412","created_at":"2026-07-05T09:35:48.974155+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWHQPIXNI3QH","created_at":"2026-07-05T09:35:48.974155+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWHQPIXNI3QHLBFO","created_at":"2026-07-05T09:35:48.974155+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWHQPIXN","created_at":"2026-07-05T09:35:48.974155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWHQPIXNI3QHLBFOYPH3VVTLA2","json":"https://pith.science/pith/QWHQPIXNI3QHLBFOYPH3VVTLA2.json","graph_json":"https://pith.science/api/pith-number/QWHQPIXNI3QHLBFOYPH3VVTLA2/graph.json","events_json":"https://pith.science/api/pith-number/QWHQPIXNI3QHLBFOYPH3VVTLA2/events.json","paper":"https://pith.science/paper/QWHQPIXN"},"agent_actions":{"view_html":"https://pith.science/pith/QWHQPIXNI3QHLBFOYPH3VVTLA2","download_json":"https://pith.science/pith/QWHQPIXNI3QHLBFOYPH3VVTLA2.json","view_paper":"https://pith.science/paper/QWHQPIXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04412&json=true","fetch_graph":"https://pith.science/api/pith-number/QWHQPIXNI3QHLBFOYPH3VVTLA2/graph.json","fetch_events":"https://pith.science/api/pith-number/QWHQPIXNI3QHLBFOYPH3VVTLA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWHQPIXNI3QHLBFOYPH3VVTLA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWHQPIXNI3QHLBFOYPH3VVTLA2/action/storage_attestation","attest_author":"https://pith.science/pith/QWHQPIXNI3QHLBFOYPH3VVTLA2/action/author_attestation","sign_citation":"https://pith.science/pith/QWHQPIXNI3QHLBFOYPH3VVTLA2/action/citation_signature","submit_replication":"https://pith.science/pith/QWHQPIXNI3QHLBFOYPH3VVTLA2/action/replication_record"}},"created_at":"2026-07-05T09:35:48.974155+00:00","updated_at":"2026-07-05T09:35:48.974155+00:00"}