{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I4BEE7V6NG6T5GOXUZFOGG5LSL","short_pith_number":"pith:I4BEE7V6","schema_version":"1.0","canonical_sha256":"4702427ebe69bd3e99d7a64ae31bab92d1210b41c9d3a44ff842bf5bceb13c8b","source":{"kind":"arxiv","id":"2508.15835","version":1},"attestation_state":"computed","paper":{"title":"Alvorada-Bench: Can Language Models Solve Brazilian University Entrance Exams?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Henrique Godoy","submitted_at":"2025-08-19T03:59:04Z","abstract_excerpt":"Language models are increasingly used in Brazil, but most evaluation remains English-centric. This paper presents Alvorada-Bench, a 4,515-question, text-only benchmark drawn from five Brazilian university entrance examinations. Evaluating twenty models under zero-shot, role-playing, and chain-of-thought prompting, producing 270,900 responses with structured self-reports of confidence, perceived difficulty, and Bloom level. The top models exceed 94% accuracy overall, but accuracy declines on Mathematics and on the engineering oriented IME and ITA exams, indicating persistent weaknesses in multi"},"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":"2508.15835","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-19T03:59:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a280e408e8e0177ac250d3c64aece3fa9a6bc78aa75ae4425203d47348259d19","abstract_canon_sha256":"8520c06f02d51088ca65f0496a66d24d693fd5372ccb521164b21ad0cc78e803"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:21.732692Z","signature_b64":"jbTdQzno5KdQWEcdn59MiMvTBT04Xbl4sg0jxCmGBQOh/Xx+rSAzhy9twwz8EVAhD29Wj6CbTDF0wLtsRocsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4702427ebe69bd3e99d7a64ae31bab92d1210b41c9d3a44ff842bf5bceb13c8b","last_reissued_at":"2026-07-05T11:57:21.732254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:21.732254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alvorada-Bench: Can Language Models Solve Brazilian University Entrance Exams?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Henrique Godoy","submitted_at":"2025-08-19T03:59:04Z","abstract_excerpt":"Language models are increasingly used in Brazil, but most evaluation remains English-centric. This paper presents Alvorada-Bench, a 4,515-question, text-only benchmark drawn from five Brazilian university entrance examinations. Evaluating twenty models under zero-shot, role-playing, and chain-of-thought prompting, producing 270,900 responses with structured self-reports of confidence, perceived difficulty, and Bloom level. The top models exceed 94% accuracy overall, but accuracy declines on Mathematics and on the engineering oriented IME and ITA exams, indicating persistent weaknesses in multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15835","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/2508.15835/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":"2508.15835","created_at":"2026-07-05T11:57:21.732310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15835v1","created_at":"2026-07-05T11:57:21.732310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15835","created_at":"2026-07-05T11:57:21.732310+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4BEE7V6NG6T","created_at":"2026-07-05T11:57:21.732310+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4BEE7V6NG6T5GOX","created_at":"2026-07-05T11:57:21.732310+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4BEE7V6","created_at":"2026-07-05T11:57:21.732310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07853","citing_title":"Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4BEE7V6NG6T5GOXUZFOGG5LSL","json":"https://pith.science/pith/I4BEE7V6NG6T5GOXUZFOGG5LSL.json","graph_json":"https://pith.science/api/pith-number/I4BEE7V6NG6T5GOXUZFOGG5LSL/graph.json","events_json":"https://pith.science/api/pith-number/I4BEE7V6NG6T5GOXUZFOGG5LSL/events.json","paper":"https://pith.science/paper/I4BEE7V6"},"agent_actions":{"view_html":"https://pith.science/pith/I4BEE7V6NG6T5GOXUZFOGG5LSL","download_json":"https://pith.science/pith/I4BEE7V6NG6T5GOXUZFOGG5LSL.json","view_paper":"https://pith.science/paper/I4BEE7V6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15835&json=true","fetch_graph":"https://pith.science/api/pith-number/I4BEE7V6NG6T5GOXUZFOGG5LSL/graph.json","fetch_events":"https://pith.science/api/pith-number/I4BEE7V6NG6T5GOXUZFOGG5LSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4BEE7V6NG6T5GOXUZFOGG5LSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4BEE7V6NG6T5GOXUZFOGG5LSL/action/storage_attestation","attest_author":"https://pith.science/pith/I4BEE7V6NG6T5GOXUZFOGG5LSL/action/author_attestation","sign_citation":"https://pith.science/pith/I4BEE7V6NG6T5GOXUZFOGG5LSL/action/citation_signature","submit_replication":"https://pith.science/pith/I4BEE7V6NG6T5GOXUZFOGG5LSL/action/replication_record"}},"created_at":"2026-07-05T11:57:21.732310+00:00","updated_at":"2026-07-05T11:57:21.732310+00:00"}