{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:F6FNGFBFZYPHXMMF2OTUB7PYEM","short_pith_number":"pith:F6FNGFBF","schema_version":"1.0","canonical_sha256":"2f8ad31425ce1e7bb185d3a740fdf82336abc5175520339d77b5723750a3105f","source":{"kind":"arxiv","id":"2209.09592","version":1},"attestation_state":"computed","paper":{"title":"Closing the Gender Wage Gap: Adversarial Fairness in Job Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Clara Rus, Gido H. Schoenmacker, Harrie Oosterhuis, Jeffrey Luppes","submitted_at":"2022-09-20T10:11:40Z","abstract_excerpt":"The goal of this work is to help mitigate the already existing gender wage gap by supplying unbiased job recommendations based on resumes from job seekers. We employ a generative adversarial network to remove gender bias from word2vec representations of 12M job vacancy texts and 900k resumes. Our results show that representations created from recruitment texts contain algorithmic bias and that this bias results in real-world consequences for recommendation systems. Without controlling for bias, women are recommended jobs with significantly lower salary in our data. With adversarially fair repr"},"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":"2209.09592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-20T10:11:40Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"3eb202d95a8a65f5a926e3fe47864f618fbd19815501b034a2e47545e5ec2a3e","abstract_canon_sha256":"cb26a768c04abbdf795b37b8099b9a8c398107d92c3dc2574d5a177800ed450a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:59:42.604031Z","signature_b64":"CdCa3yMxO2xwg/zqsYamhPSfQX0z0L8SIO7KkfkfHaGF2o9ocaBaoM3ebozcZ2MW6STpiM2wjCFD64IGvAL1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f8ad31425ce1e7bb185d3a740fdf82336abc5175520339d77b5723750a3105f","last_reissued_at":"2026-07-05T04:59:42.603311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:59:42.603311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Closing the Gender Wage Gap: Adversarial Fairness in Job Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Clara Rus, Gido H. Schoenmacker, Harrie Oosterhuis, Jeffrey Luppes","submitted_at":"2022-09-20T10:11:40Z","abstract_excerpt":"The goal of this work is to help mitigate the already existing gender wage gap by supplying unbiased job recommendations based on resumes from job seekers. We employ a generative adversarial network to remove gender bias from word2vec representations of 12M job vacancy texts and 900k resumes. Our results show that representations created from recruitment texts contain algorithmic bias and that this bias results in real-world consequences for recommendation systems. Without controlling for bias, women are recommended jobs with significantly lower salary in our data. With adversarially fair repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09592","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/2209.09592/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":"2209.09592","created_at":"2026-07-05T04:59:42.603419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.09592v1","created_at":"2026-07-05T04:59:42.603419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09592","created_at":"2026-07-05T04:59:42.603419+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6FNGFBFZYPH","created_at":"2026-07-05T04:59:42.603419+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6FNGFBFZYPHXMMF","created_at":"2026-07-05T04:59:42.603419+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6FNGFBF","created_at":"2026-07-05T04:59:42.603419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.14110","citing_title":"Value Sensitive Design for Fair Online Recruitment: A Conceptual Framework Informed by Job Seekers' Fairness Concerns","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F6FNGFBFZYPHXMMF2OTUB7PYEM","json":"https://pith.science/pith/F6FNGFBFZYPHXMMF2OTUB7PYEM.json","graph_json":"https://pith.science/api/pith-number/F6FNGFBFZYPHXMMF2OTUB7PYEM/graph.json","events_json":"https://pith.science/api/pith-number/F6FNGFBFZYPHXMMF2OTUB7PYEM/events.json","paper":"https://pith.science/paper/F6FNGFBF"},"agent_actions":{"view_html":"https://pith.science/pith/F6FNGFBFZYPHXMMF2OTUB7PYEM","download_json":"https://pith.science/pith/F6FNGFBFZYPHXMMF2OTUB7PYEM.json","view_paper":"https://pith.science/paper/F6FNGFBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.09592&json=true","fetch_graph":"https://pith.science/api/pith-number/F6FNGFBFZYPHXMMF2OTUB7PYEM/graph.json","fetch_events":"https://pith.science/api/pith-number/F6FNGFBFZYPHXMMF2OTUB7PYEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6FNGFBFZYPHXMMF2OTUB7PYEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6FNGFBFZYPHXMMF2OTUB7PYEM/action/storage_attestation","attest_author":"https://pith.science/pith/F6FNGFBFZYPHXMMF2OTUB7PYEM/action/author_attestation","sign_citation":"https://pith.science/pith/F6FNGFBFZYPHXMMF2OTUB7PYEM/action/citation_signature","submit_replication":"https://pith.science/pith/F6FNGFBFZYPHXMMF2OTUB7PYEM/action/replication_record"}},"created_at":"2026-07-05T04:59:42.603419+00:00","updated_at":"2026-07-05T04:59:42.603419+00:00"}