{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2WINJSKGPGORRGU46S7F6PLQ67","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":"551fa50d82c75b6e004852358c88729fbbe5ad520219145868152862f845f79c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T01:23:28Z","title_canon_sha256":"c796216139561dd66d8a0633d39daaf2ecab2191ca754c168fc24f4661b4e166"},"schema_version":"1.0","source":{"id":"2508.21294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21294","created_at":"2026-07-05T12:01:32Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21294v1","created_at":"2026-07-05T12:01:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21294","created_at":"2026-07-05T12:01:32Z"},{"alias_kind":"pith_short_12","alias_value":"2WINJSKGPGOR","created_at":"2026-07-05T12:01:32Z"},{"alias_kind":"pith_short_16","alias_value":"2WINJSKGPGORRGU4","created_at":"2026-07-05T12:01:32Z"},{"alias_kind":"pith_short_8","alias_value":"2WINJSKG","created_at":"2026-07-05T12:01:32Z"}],"graph_snapshots":[{"event_id":"sha256:51244186d538f84011bb6003b1b2fda4d0bfa96e1725f49bb36abf6403f35e03","target":"graph","created_at":"2026-07-05T12:01:32Z","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/2508.21294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the growing capabilities of Large Language Models (LLMs), there is an increasing need for robust evaluation methods, especially in multilingual and non-English contexts. We present an updated version of the BLUEX dataset, now including 2024-2025 exams and automatically generated image captions using state-of-the-art models, enhancing its relevance for data contamination studies in LLM pretraining. Captioning strategies increase accessibility to text-only models by more than 40%, producing 1,422 usable questions, more than doubling the number in the original BLUEX. We evaluated commercial ","authors_text":"Giovana Kerche Bon\\'as, Jo\\~ao Guilherme Alves Santos, Thales Sales Almeida","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T01:23:28Z","title":"BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21294","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:fece38ba3511df7df4fbf18549e3e139dfa0f6e824895bdcfb10ef1e9cd4019b","target":"record","created_at":"2026-07-05T12:01:32Z","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":"551fa50d82c75b6e004852358c88729fbbe5ad520219145868152862f845f79c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T01:23:28Z","title_canon_sha256":"c796216139561dd66d8a0633d39daaf2ecab2191ca754c168fc24f4661b4e166"},"schema_version":"1.0","source":{"id":"2508.21294","kind":"arxiv","version":1}},"canonical_sha256":"d590d4c946799d189a9cf4be5f3d70f7e135a9e70357d67e2550ada4baec9be9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d590d4c946799d189a9cf4be5f3d70f7e135a9e70357d67e2550ada4baec9be9","first_computed_at":"2026-07-05T12:01:32.085513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:32.085513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X59/Fv3PXUKcQWrFLad1f6/4rEPvJKOfLlsQr+LbO4A5UeXhdd/4gIzUBd3GN+e0ergjXur4Z2DBK0rVH7VBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:32.086030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fece38ba3511df7df4fbf18549e3e139dfa0f6e824895bdcfb10ef1e9cd4019b","sha256:51244186d538f84011bb6003b1b2fda4d0bfa96e1725f49bb36abf6403f35e03"],"state_sha256":"c01acdf6d02ca13b37a1fa5bda6f7679940bfa27e18d0f7953de896167537430"}