{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OT2IMRQHX7JOB4UDEYSPY42BA2","short_pith_number":"pith:OT2IMRQH","schema_version":"1.0","canonical_sha256":"74f4864607bfd2e0f2832624fc734106a36e105681c1473ed5cb9ec9f0987d43","source":{"kind":"arxiv","id":"2406.15484","version":2},"attestation_state":"computed","paper":{"title":"JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Adriano Koshiyama, Ediz Ertekin Jr., Maria Perez-Ortiz, Michael Thaler, Sachin Beepath, Skylar Lu, Xin Guan, Zekun Wu, Ze Wang","submitted_at":"2024-06-17T09:15:57Z","abstract_excerpt":"The use of Large Language Models (LLMs) in hiring has led to legislative actions to protect vulnerable demographic groups. This paper presents a novel framework for benchmarking hierarchical gender hiring bias in Large Language Models (LLMs) for resume scoring, revealing significant issues of reverse gender hiring bias and overdebiasing. Our contributions are fourfold: Firstly, we introduce a new construct grounded in labour economics, legal principles, and critiques of current bias benchmarks: hiring bias can be categorized into two types: Level bias (difference in the average outcomes betwee"},"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":"2406.15484","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T09:15:57Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"8b1b9980980caf001beabf58ecb672be09aa0b78dca1162ca2c057f6ba34b4be","abstract_canon_sha256":"1c9e0bdd78f9bb16550de02634d0c1599bb824b8d623015e1d270556f0938d75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:04.534164Z","signature_b64":"9NLwD4nLjTNaSVH0t/Am8fqEk6a1iP+cSw2vBlEc/i/5gqBQOJD3OLp49mDxYDXvSDXp8gh4YCyLadJxo515BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74f4864607bfd2e0f2832624fc734106a36e105681c1473ed5cb9ec9f0987d43","last_reissued_at":"2026-07-05T10:02:04.533692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:04.533692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Adriano Koshiyama, Ediz Ertekin Jr., Maria Perez-Ortiz, Michael Thaler, Sachin Beepath, Skylar Lu, Xin Guan, Zekun Wu, Ze Wang","submitted_at":"2024-06-17T09:15:57Z","abstract_excerpt":"The use of Large Language Models (LLMs) in hiring has led to legislative actions to protect vulnerable demographic groups. This paper presents a novel framework for benchmarking hierarchical gender hiring bias in Large Language Models (LLMs) for resume scoring, revealing significant issues of reverse gender hiring bias and overdebiasing. Our contributions are fourfold: Firstly, we introduce a new construct grounded in labour economics, legal principles, and critiques of current bias benchmarks: hiring bias can be categorized into two types: Level bias (difference in the average outcomes betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15484","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/2406.15484/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":"2406.15484","created_at":"2026-07-05T10:02:04.533750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15484v2","created_at":"2026-07-05T10:02:04.533750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15484","created_at":"2026-07-05T10:02:04.533750+00:00"},{"alias_kind":"pith_short_12","alias_value":"OT2IMRQHX7JO","created_at":"2026-07-05T10:02:04.533750+00:00"},{"alias_kind":"pith_short_16","alias_value":"OT2IMRQHX7JOB4UD","created_at":"2026-07-05T10:02:04.533750+00:00"},{"alias_kind":"pith_short_8","alias_value":"OT2IMRQH","created_at":"2026-07-05T10:02:04.533750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.14092","citing_title":"Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OT2IMRQHX7JOB4UDEYSPY42BA2","json":"https://pith.science/pith/OT2IMRQHX7JOB4UDEYSPY42BA2.json","graph_json":"https://pith.science/api/pith-number/OT2IMRQHX7JOB4UDEYSPY42BA2/graph.json","events_json":"https://pith.science/api/pith-number/OT2IMRQHX7JOB4UDEYSPY42BA2/events.json","paper":"https://pith.science/paper/OT2IMRQH"},"agent_actions":{"view_html":"https://pith.science/pith/OT2IMRQHX7JOB4UDEYSPY42BA2","download_json":"https://pith.science/pith/OT2IMRQHX7JOB4UDEYSPY42BA2.json","view_paper":"https://pith.science/paper/OT2IMRQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15484&json=true","fetch_graph":"https://pith.science/api/pith-number/OT2IMRQHX7JOB4UDEYSPY42BA2/graph.json","fetch_events":"https://pith.science/api/pith-number/OT2IMRQHX7JOB4UDEYSPY42BA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OT2IMRQHX7JOB4UDEYSPY42BA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OT2IMRQHX7JOB4UDEYSPY42BA2/action/storage_attestation","attest_author":"https://pith.science/pith/OT2IMRQHX7JOB4UDEYSPY42BA2/action/author_attestation","sign_citation":"https://pith.science/pith/OT2IMRQHX7JOB4UDEYSPY42BA2/action/citation_signature","submit_replication":"https://pith.science/pith/OT2IMRQHX7JOB4UDEYSPY42BA2/action/replication_record"}},"created_at":"2026-07-05T10:02:04.533750+00:00","updated_at":"2026-07-05T10:02:04.533750+00:00"}