{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BZ76GVUUUTZ6Y4O42WAURKAKQA","short_pith_number":"pith:BZ76GVUU","schema_version":"1.0","canonical_sha256":"0e7fe35694a4f3ec71dcd58148a80a801e28553cd6fa20896152fba136d6b25b","source":{"kind":"arxiv","id":"2406.13677","version":3},"attestation_state":"computed","paper":{"title":"Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Erik Derner, Nuria Oliver, Paloma Moreda, Sara Sansalvador de la Fuente, Yoan Guti\\'errez","submitted_at":"2024-06-19T16:30:58Z","abstract_excerpt":"Large language models (LLMs) often inherit and amplify social biases embedded in their training data. A prominent social bias is gender bias. In this regard, prior work has mainly focused on gender stereotyping bias - the association of specific roles or traits with a particular gender - in English and on evaluating gender bias in model embeddings or generated outputs. In contrast, gender representation bias - the unequal frequency of references to individuals of different genders - in the training corpora has received less attention. Yet such imbalances in the training data constitute an upst"},"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":"2406.13677","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T16:30:58Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"c4600e267029a557af83f5917746c43b97c9080e83a72363b476905162656d1e","abstract_canon_sha256":"a59d5019eacf6c5661cba2b8e6e0f33b98f52e159389dc8d6b84ee38041f056b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:06.914649Z","signature_b64":"Ds/jQf9T28ZsXVJoWJiYMqPc/8bucXJa9OrVlESjCxhk/To/ialtdYVvNG74cm7Vt2FS8hzp5bGvUOh+H0/SBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e7fe35694a4f3ec71dcd58148a80a801e28553cd6fa20896152fba136d6b25b","last_reissued_at":"2026-07-05T11:23:06.914178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:06.914178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Erik Derner, Nuria Oliver, Paloma Moreda, Sara Sansalvador de la Fuente, Yoan Guti\\'errez","submitted_at":"2024-06-19T16:30:58Z","abstract_excerpt":"Large language models (LLMs) often inherit and amplify social biases embedded in their training data. A prominent social bias is gender bias. In this regard, prior work has mainly focused on gender stereotyping bias - the association of specific roles or traits with a particular gender - in English and on evaluating gender bias in model embeddings or generated outputs. In contrast, gender representation bias - the unequal frequency of references to individuals of different genders - in the training corpora has received less attention. Yet such imbalances in the training data constitute an upst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13677","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/2406.13677/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":"2406.13677","created_at":"2026-07-05T11:23:06.914233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13677v3","created_at":"2026-07-05T11:23:06.914233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13677","created_at":"2026-07-05T11:23:06.914233+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZ76GVUUUTZ6","created_at":"2026-07-05T11:23:06.914233+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZ76GVUUUTZ6Y4O4","created_at":"2026-07-05T11:23:06.914233+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZ76GVUU","created_at":"2026-07-05T11:23:06.914233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16557","citing_title":"Exploring Gender Bias in Large Language Models: An In-depth Dive into the German Language","ref_index":2019,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZ76GVUUUTZ6Y4O42WAURKAKQA","json":"https://pith.science/pith/BZ76GVUUUTZ6Y4O42WAURKAKQA.json","graph_json":"https://pith.science/api/pith-number/BZ76GVUUUTZ6Y4O42WAURKAKQA/graph.json","events_json":"https://pith.science/api/pith-number/BZ76GVUUUTZ6Y4O42WAURKAKQA/events.json","paper":"https://pith.science/paper/BZ76GVUU"},"agent_actions":{"view_html":"https://pith.science/pith/BZ76GVUUUTZ6Y4O42WAURKAKQA","download_json":"https://pith.science/pith/BZ76GVUUUTZ6Y4O42WAURKAKQA.json","view_paper":"https://pith.science/paper/BZ76GVUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13677&json=true","fetch_graph":"https://pith.science/api/pith-number/BZ76GVUUUTZ6Y4O42WAURKAKQA/graph.json","fetch_events":"https://pith.science/api/pith-number/BZ76GVUUUTZ6Y4O42WAURKAKQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZ76GVUUUTZ6Y4O42WAURKAKQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZ76GVUUUTZ6Y4O42WAURKAKQA/action/storage_attestation","attest_author":"https://pith.science/pith/BZ76GVUUUTZ6Y4O42WAURKAKQA/action/author_attestation","sign_citation":"https://pith.science/pith/BZ76GVUUUTZ6Y4O42WAURKAKQA/action/citation_signature","submit_replication":"https://pith.science/pith/BZ76GVUUUTZ6Y4O42WAURKAKQA/action/replication_record"}},"created_at":"2026-07-05T11:23:06.914233+00:00","updated_at":"2026-07-05T11:23:06.914233+00:00"}