{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BJRMOFF2346OSX6TV6YIGTK3FT","short_pith_number":"pith:BJRMOFF2","schema_version":"1.0","canonical_sha256":"0a62c714badf3ce95fd3afb0834d5b2ccb6baff5cb03cf865201213b2023ca04","source":{"kind":"arxiv","id":"2509.03329","version":1},"attestation_state":"computed","paper":{"title":"SESGO: Spanish Evaluation of Stereotypical Generative Outputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Catalina Bernal, Denniss Raigoso, Mateo Dulce Rubio, Melissa Robles","submitted_at":"2025-09-03T14:04:51Z","abstract_excerpt":"This paper addresses the critical gap in evaluating bias in multilingual Large Language Models (LLMs), with a specific focus on Spanish language within culturally-aware Latin American contexts. Despite widespread global deployment, current evaluations remain predominantly US-English-centric, leaving potential harms in other linguistic and cultural contexts largely underexamined. We introduce a novel, culturally-grounded framework for detecting social biases in instruction-tuned LLMs. Our approach adapts the underspecified question methodology from the BBQ dataset by incorporating culturally-sp"},"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":"2509.03329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-09-03T14:04:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a0711855d77d20b2a2a0dd1e0c59bebc1a5324ccc796efd084b23e71c9e205f8","abstract_canon_sha256":"c0691e2c184242b292c87f61c5e31bbccbf8808107c9dde7a5f0608b420dc621"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:20.525798Z","signature_b64":"Y+H6jJNXUrA2XF9BeLpxhEeiWZ200BxdqSE8j85SsDoMZg55HyuDL97V7pwkxOm3vIv8L4NkiAPT8lmZMEyIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a62c714badf3ce95fd3afb0834d5b2ccb6baff5cb03cf865201213b2023ca04","last_reissued_at":"2026-07-05T12:04:20.525312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:20.525312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SESGO: Spanish Evaluation of Stereotypical Generative Outputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Catalina Bernal, Denniss Raigoso, Mateo Dulce Rubio, Melissa Robles","submitted_at":"2025-09-03T14:04:51Z","abstract_excerpt":"This paper addresses the critical gap in evaluating bias in multilingual Large Language Models (LLMs), with a specific focus on Spanish language within culturally-aware Latin American contexts. Despite widespread global deployment, current evaluations remain predominantly US-English-centric, leaving potential harms in other linguistic and cultural contexts largely underexamined. We introduce a novel, culturally-grounded framework for detecting social biases in instruction-tuned LLMs. Our approach adapts the underspecified question methodology from the BBQ dataset by incorporating culturally-sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03329","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/2509.03329/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":"2509.03329","created_at":"2026-07-05T12:04:20.525389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03329v1","created_at":"2026-07-05T12:04:20.525389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03329","created_at":"2026-07-05T12:04:20.525389+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJRMOFF2346O","created_at":"2026-07-05T12:04:20.525389+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJRMOFF2346OSX6T","created_at":"2026-07-05T12:04:20.525389+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJRMOFF2","created_at":"2026-07-05T12:04:20.525389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.21774","citing_title":"Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJRMOFF2346OSX6TV6YIGTK3FT","json":"https://pith.science/pith/BJRMOFF2346OSX6TV6YIGTK3FT.json","graph_json":"https://pith.science/api/pith-number/BJRMOFF2346OSX6TV6YIGTK3FT/graph.json","events_json":"https://pith.science/api/pith-number/BJRMOFF2346OSX6TV6YIGTK3FT/events.json","paper":"https://pith.science/paper/BJRMOFF2"},"agent_actions":{"view_html":"https://pith.science/pith/BJRMOFF2346OSX6TV6YIGTK3FT","download_json":"https://pith.science/pith/BJRMOFF2346OSX6TV6YIGTK3FT.json","view_paper":"https://pith.science/paper/BJRMOFF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03329&json=true","fetch_graph":"https://pith.science/api/pith-number/BJRMOFF2346OSX6TV6YIGTK3FT/graph.json","fetch_events":"https://pith.science/api/pith-number/BJRMOFF2346OSX6TV6YIGTK3FT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJRMOFF2346OSX6TV6YIGTK3FT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJRMOFF2346OSX6TV6YIGTK3FT/action/storage_attestation","attest_author":"https://pith.science/pith/BJRMOFF2346OSX6TV6YIGTK3FT/action/author_attestation","sign_citation":"https://pith.science/pith/BJRMOFF2346OSX6TV6YIGTK3FT/action/citation_signature","submit_replication":"https://pith.science/pith/BJRMOFF2346OSX6TV6YIGTK3FT/action/replication_record"}},"created_at":"2026-07-05T12:04:20.525389+00:00","updated_at":"2026-07-05T12:04:20.525389+00:00"}