{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3FQFDOHCSHK6YHTPGLAYFEE5RX","short_pith_number":"pith:3FQFDOHC","schema_version":"1.0","canonical_sha256":"d96051b8e291d5ec1e6f32c182909d8ddc5be24fb84076ee4871ac23d80338cd","source":{"kind":"arxiv","id":"2504.21400","version":1},"attestation_state":"computed","paper":{"title":"Who Gets the Callback? Generative AI and Gender Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","q-fin.EC"],"primary_cat":"econ.GN","authors_text":"Rochana Chaturvedi, Sugat Chaturvedi","submitted_at":"2025-04-30T07:55:52Z","abstract_excerpt":"Generative artificial intelligence (AI), particularly large language models (LLMs), is being rapidly deployed in recruitment and for candidate shortlisting. We audit several mid-sized open-source LLMs for gender bias using a dataset of 332,044 real-world online job postings. For each posting, we prompt the model to recommend whether an equally qualified male or female candidate should receive an interview callback. We find that most models tend to favor men, especially for higher-wage roles. Mapping job descriptions to the Standard Occupational Classification system, we find lower callback rat"},"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":"2504.21400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"econ.GN","submitted_at":"2025-04-30T07:55:52Z","cross_cats_sorted":["cs.CL","q-fin.EC"],"title_canon_sha256":"e2340c380d8f1a656a30f800bd14148e507444d62e26d2b9c9f7afac34eefd19","abstract_canon_sha256":"f2359a73078b420b18504233d368e7122ce0b3eed0723c11d96d7fe93c5534ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:23.296798Z","signature_b64":"vbTeLiYu3SqDBZnQFRg3tGZgDUyeYZ7z1VnIyt8TBT2kMx2BW0eDPqzyswKB+pVLCRYM9tPhCdbfSKBMI9zLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d96051b8e291d5ec1e6f32c182909d8ddc5be24fb84076ee4871ac23d80338cd","last_reissued_at":"2026-07-05T10:56:23.296458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:23.296458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Who Gets the Callback? Generative AI and Gender Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","q-fin.EC"],"primary_cat":"econ.GN","authors_text":"Rochana Chaturvedi, Sugat Chaturvedi","submitted_at":"2025-04-30T07:55:52Z","abstract_excerpt":"Generative artificial intelligence (AI), particularly large language models (LLMs), is being rapidly deployed in recruitment and for candidate shortlisting. We audit several mid-sized open-source LLMs for gender bias using a dataset of 332,044 real-world online job postings. For each posting, we prompt the model to recommend whether an equally qualified male or female candidate should receive an interview callback. We find that most models tend to favor men, especially for higher-wage roles. Mapping job descriptions to the Standard Occupational Classification system, we find lower callback rat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21400","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/2504.21400/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":"2504.21400","created_at":"2026-07-05T10:56:23.296516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21400v1","created_at":"2026-07-05T10:56:23.296516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21400","created_at":"2026-07-05T10:56:23.296516+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FQFDOHCSHK6","created_at":"2026-07-05T10:56:23.296516+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FQFDOHCSHK6YHTP","created_at":"2026-07-05T10:56:23.296516+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FQFDOHC","created_at":"2026-07-05T10:56:23.296516+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/3FQFDOHCSHK6YHTPGLAYFEE5RX","json":"https://pith.science/pith/3FQFDOHCSHK6YHTPGLAYFEE5RX.json","graph_json":"https://pith.science/api/pith-number/3FQFDOHCSHK6YHTPGLAYFEE5RX/graph.json","events_json":"https://pith.science/api/pith-number/3FQFDOHCSHK6YHTPGLAYFEE5RX/events.json","paper":"https://pith.science/paper/3FQFDOHC"},"agent_actions":{"view_html":"https://pith.science/pith/3FQFDOHCSHK6YHTPGLAYFEE5RX","download_json":"https://pith.science/pith/3FQFDOHCSHK6YHTPGLAYFEE5RX.json","view_paper":"https://pith.science/paper/3FQFDOHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21400&json=true","fetch_graph":"https://pith.science/api/pith-number/3FQFDOHCSHK6YHTPGLAYFEE5RX/graph.json","fetch_events":"https://pith.science/api/pith-number/3FQFDOHCSHK6YHTPGLAYFEE5RX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FQFDOHCSHK6YHTPGLAYFEE5RX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FQFDOHCSHK6YHTPGLAYFEE5RX/action/storage_attestation","attest_author":"https://pith.science/pith/3FQFDOHCSHK6YHTPGLAYFEE5RX/action/author_attestation","sign_citation":"https://pith.science/pith/3FQFDOHCSHK6YHTPGLAYFEE5RX/action/citation_signature","submit_replication":"https://pith.science/pith/3FQFDOHCSHK6YHTPGLAYFEE5RX/action/replication_record"}},"created_at":"2026-07-05T10:56:23.296516+00:00","updated_at":"2026-07-05T10:56:23.296516+00:00"}