{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BV4MQ5U2BILB53BVKYCPS2FZ4T","short_pith_number":"pith:BV4MQ5U2","schema_version":"1.0","canonical_sha256":"0d78c8769a0a161eec355604f968b9e4c7659ab3010ae5752f85129e85070617","source":{"kind":"arxiv","id":"2507.11216","version":1},"attestation_state":"computed","paper":{"title":"EsBBQ and CaBBQ: The Spanish and Catalan Bias Benchmarks for Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aitor Gonzalez-Agirre, Anna Sall\\'es, J\\'ulia Falc\\~ao, Luis Vasquez-Reina, Mario Mina, Olatz Perez-de-Vi\\~naspre, Valle Ruiz-Fern\\'andez","submitted_at":"2025-07-15T11:37:30Z","abstract_excerpt":"Previous literature has largely shown that Large Language Models (LLMs) perpetuate social biases learnt from their pre-training data. Given the notable lack of resources for social bias evaluation in languages other than English, and for social contexts outside of the United States, this paper introduces the Spanish and the Catalan Bias Benchmarks for Question Answering (EsBBQ and CaBBQ). Based on the original BBQ, these two parallel datasets are designed to assess social bias across 10 categories using a multiple-choice QA setting, now adapted to the Spanish and Catalan languages and to the s"},"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":"2507.11216","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T11:37:30Z","cross_cats_sorted":[],"title_canon_sha256":"e2ad020782979d25cb092f9f6f5409d7aadae9302ed62f08a559ff40ed0576a3","abstract_canon_sha256":"f21ea3dd31a4f8c819a9cfd1be217c194bf7f17810e76bf0ef9c82ac3db575da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:34.376056Z","signature_b64":"XOZgXrHy9mYb1W0Dd0MX0HsdWeV9D93vbc/mok02oXfZyuCDWaQlpEm2UmJKm4o6hYD0i7xO2N7so2SImbsSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d78c8769a0a161eec355604f968b9e4c7659ab3010ae5752f85129e85070617","last_reissued_at":"2026-07-05T11:37:34.375612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:34.375612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EsBBQ and CaBBQ: The Spanish and Catalan Bias Benchmarks for Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aitor Gonzalez-Agirre, Anna Sall\\'es, J\\'ulia Falc\\~ao, Luis Vasquez-Reina, Mario Mina, Olatz Perez-de-Vi\\~naspre, Valle Ruiz-Fern\\'andez","submitted_at":"2025-07-15T11:37:30Z","abstract_excerpt":"Previous literature has largely shown that Large Language Models (LLMs) perpetuate social biases learnt from their pre-training data. Given the notable lack of resources for social bias evaluation in languages other than English, and for social contexts outside of the United States, this paper introduces the Spanish and the Catalan Bias Benchmarks for Question Answering (EsBBQ and CaBBQ). Based on the original BBQ, these two parallel datasets are designed to assess social bias across 10 categories using a multiple-choice QA setting, now adapted to the Spanish and Catalan languages and to the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11216","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/2507.11216/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":"2507.11216","created_at":"2026-07-05T11:37:34.375683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.11216v1","created_at":"2026-07-05T11:37:34.375683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11216","created_at":"2026-07-05T11:37:34.375683+00:00"},{"alias_kind":"pith_short_12","alias_value":"BV4MQ5U2BILB","created_at":"2026-07-05T11:37:34.375683+00:00"},{"alias_kind":"pith_short_16","alias_value":"BV4MQ5U2BILB53BV","created_at":"2026-07-05T11:37:34.375683+00:00"},{"alias_kind":"pith_short_8","alias_value":"BV4MQ5U2","created_at":"2026-07-05T11:37:34.375683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21296","citing_title":"Discriminatory Compliance: How LLMs Answer Queries from Protected Groups","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BV4MQ5U2BILB53BVKYCPS2FZ4T","json":"https://pith.science/pith/BV4MQ5U2BILB53BVKYCPS2FZ4T.json","graph_json":"https://pith.science/api/pith-number/BV4MQ5U2BILB53BVKYCPS2FZ4T/graph.json","events_json":"https://pith.science/api/pith-number/BV4MQ5U2BILB53BVKYCPS2FZ4T/events.json","paper":"https://pith.science/paper/BV4MQ5U2"},"agent_actions":{"view_html":"https://pith.science/pith/BV4MQ5U2BILB53BVKYCPS2FZ4T","download_json":"https://pith.science/pith/BV4MQ5U2BILB53BVKYCPS2FZ4T.json","view_paper":"https://pith.science/paper/BV4MQ5U2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.11216&json=true","fetch_graph":"https://pith.science/api/pith-number/BV4MQ5U2BILB53BVKYCPS2FZ4T/graph.json","fetch_events":"https://pith.science/api/pith-number/BV4MQ5U2BILB53BVKYCPS2FZ4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BV4MQ5U2BILB53BVKYCPS2FZ4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BV4MQ5U2BILB53BVKYCPS2FZ4T/action/storage_attestation","attest_author":"https://pith.science/pith/BV4MQ5U2BILB53BVKYCPS2FZ4T/action/author_attestation","sign_citation":"https://pith.science/pith/BV4MQ5U2BILB53BVKYCPS2FZ4T/action/citation_signature","submit_replication":"https://pith.science/pith/BV4MQ5U2BILB53BVKYCPS2FZ4T/action/replication_record"}},"created_at":"2026-07-05T11:37:34.375683+00:00","updated_at":"2026-07-05T11:37:34.375683+00:00"}