{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PHXE4LEZ7GQJAVU3TIKYU22XQK","short_pith_number":"pith:PHXE4LEZ","schema_version":"1.0","canonical_sha256":"79ee4e2c99f9a090569b9a158a6b5782a2ebaddd8aad5eb8d2b4ce0b30a0282d","source":{"kind":"arxiv","id":"2401.15798","version":1},"attestation_state":"computed","paper":{"title":"UnMASKed: Quantifying Gender Biases in Masked Language Models through Linguistically Informed Job Market Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"I\\~nigo Parra","submitted_at":"2024-01-28T23:00:40Z","abstract_excerpt":"Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training. This research delves into the inherent biases present in masked language models (MLMs), with a specific focus on gender biases. This study evaluated six prominent models: BERT, RoBERTa, DistilBERT, BERT-multilingual, XLM-RoBERTa, and DistilBERT-multilingual. The methodology employed a novel dataset, bifurcated into two subsets: one containing prompts that enc"},"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":"2401.15798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-28T23:00:40Z","cross_cats_sorted":[],"title_canon_sha256":"3114ed0cc34c19cd3c296305262669c7cf75bdf5d24278859e5c51ae5c604690","abstract_canon_sha256":"80b66e6755cdee3eea6c9a5820d949205734b1cbc4a93b5823b57e546b0be460"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:39.799475Z","signature_b64":"cR6Ckzg6E+j9TiJQJk3UWxRmIiQw0S2BA2W8DYS4+JaojGq0o3wAKIBSluJdHzF3+mLXJlFvaFmSwrRqRDl3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79ee4e2c99f9a090569b9a158a6b5782a2ebaddd8aad5eb8d2b4ce0b30a0282d","last_reissued_at":"2026-07-05T07:38:39.799059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:39.799059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnMASKed: Quantifying Gender Biases in Masked Language Models through Linguistically Informed Job Market Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"I\\~nigo Parra","submitted_at":"2024-01-28T23:00:40Z","abstract_excerpt":"Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training. This research delves into the inherent biases present in masked language models (MLMs), with a specific focus on gender biases. This study evaluated six prominent models: BERT, RoBERTa, DistilBERT, BERT-multilingual, XLM-RoBERTa, and DistilBERT-multilingual. The methodology employed a novel dataset, bifurcated into two subsets: one containing prompts that enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15798","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/2401.15798/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":"2401.15798","created_at":"2026-07-05T07:38:39.799119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.15798v1","created_at":"2026-07-05T07:38:39.799119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15798","created_at":"2026-07-05T07:38:39.799119+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHXE4LEZ7GQJ","created_at":"2026-07-05T07:38:39.799119+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHXE4LEZ7GQJAVU3","created_at":"2026-07-05T07:38:39.799119+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHXE4LEZ","created_at":"2026-07-05T07:38:39.799119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23492","citing_title":"Sample Margin-Aware Recalibration of Temperature Scaling","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHXE4LEZ7GQJAVU3TIKYU22XQK","json":"https://pith.science/pith/PHXE4LEZ7GQJAVU3TIKYU22XQK.json","graph_json":"https://pith.science/api/pith-number/PHXE4LEZ7GQJAVU3TIKYU22XQK/graph.json","events_json":"https://pith.science/api/pith-number/PHXE4LEZ7GQJAVU3TIKYU22XQK/events.json","paper":"https://pith.science/paper/PHXE4LEZ"},"agent_actions":{"view_html":"https://pith.science/pith/PHXE4LEZ7GQJAVU3TIKYU22XQK","download_json":"https://pith.science/pith/PHXE4LEZ7GQJAVU3TIKYU22XQK.json","view_paper":"https://pith.science/paper/PHXE4LEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.15798&json=true","fetch_graph":"https://pith.science/api/pith-number/PHXE4LEZ7GQJAVU3TIKYU22XQK/graph.json","fetch_events":"https://pith.science/api/pith-number/PHXE4LEZ7GQJAVU3TIKYU22XQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHXE4LEZ7GQJAVU3TIKYU22XQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHXE4LEZ7GQJAVU3TIKYU22XQK/action/storage_attestation","attest_author":"https://pith.science/pith/PHXE4LEZ7GQJAVU3TIKYU22XQK/action/author_attestation","sign_citation":"https://pith.science/pith/PHXE4LEZ7GQJAVU3TIKYU22XQK/action/citation_signature","submit_replication":"https://pith.science/pith/PHXE4LEZ7GQJAVU3TIKYU22XQK/action/replication_record"}},"created_at":"2026-07-05T07:38:39.799119+00:00","updated_at":"2026-07-05T07:38:39.799119+00:00"}