{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OLR246FPR5QJAYEMX72Y56GI7B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c560c0c01f4f4cfb86f0e86f8d3c2ab553e684c75b1e4d036e855c7916df2e5e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T23:45:49Z","title_canon_sha256":"24bf3dcda9e096f1656117b3b86d98b0003fe238f54b649180914f31752ea909"},"schema_version":"1.0","source":{"id":"2606.22723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22723","created_at":"2026-06-23T02:13:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22723v1","created_at":"2026-06-23T02:13:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22723","created_at":"2026-06-23T02:13:45Z"},{"alias_kind":"pith_short_12","alias_value":"OLR246FPR5QJ","created_at":"2026-06-23T02:13:45Z"},{"alias_kind":"pith_short_16","alias_value":"OLR246FPR5QJAYEM","created_at":"2026-06-23T02:13:45Z"},{"alias_kind":"pith_short_8","alias_value":"OLR246FP","created_at":"2026-06-23T02:13:45Z"}],"graph_snapshots":[{"event_id":"sha256:6961dc91a22c213f7cca75c43903fff02bcc8f5b80bac0505e606ee703b4f6e9","target":"graph","created_at":"2026-06-23T02:13:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.22723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although Large Language Models (LLMs) excel in many tasks, their assessment in Portuguese has received less attention, particularly for open-ended, discursive tasks that demand deeper reasoning and generation capabilities. While the original BLUEX benchmark addressed the scarcity of Portuguese evaluation datasets through multiple-choice questions from Brazilian university entrance exams, it did not cover the more challenging second-phase examinations, which require free-form written responses. In this work, we introduce BLUEX v2, a benchmark derived from the second-phase entrance exams of Braz","authors_text":"Giovana Kerche Bon\\'as, Helio Pedrini, Jo\\~ao Guilherme Alves Santos, Thales Sales Almeida, Thiago Laitz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T23:45:49Z","title":"BLUEX v2: Benchmarking LLMs on Open-Ended Questions from Brazilian University Entrance Exams"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22723","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:71aaed5238373e16f8827e7cdfd949ffc6f9c52b0af6919d274f8182fa1e355d","target":"record","created_at":"2026-06-23T02:13:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c560c0c01f4f4cfb86f0e86f8d3c2ab553e684c75b1e4d036e855c7916df2e5e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T23:45:49Z","title_canon_sha256":"24bf3dcda9e096f1656117b3b86d98b0003fe238f54b649180914f31752ea909"},"schema_version":"1.0","source":{"id":"2606.22723","kind":"arxiv","version":1}},"canonical_sha256":"72e3ae78af8f6090608cbff58ef8c8f864fb819be920c1a9146e58b36fe6bb46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72e3ae78af8f6090608cbff58ef8c8f864fb819be920c1a9146e58b36fe6bb46","first_computed_at":"2026-06-23T02:13:45.719200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:45.719200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"inkF0dInLGSByWR7KG9mHGTX0PW7DJ0HHGJ/33s8twDwGm9BJpOze0BmOubY7YfVVsljGpLCRTAF7arXSuq/BQ==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:45.719626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71aaed5238373e16f8827e7cdfd949ffc6f9c52b0af6919d274f8182fa1e355d","sha256:6961dc91a22c213f7cca75c43903fff02bcc8f5b80bac0505e606ee703b4f6e9"],"state_sha256":"e2fd5756861845aa7a50924d3aa8d709388917f9d1133c481dba2cfcf00bc428"}