{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZTUJCQ5RCDDB4Y4FWGETBMOCAY","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":"fa3da6b224d4b43144d7f1fbf8dc3069c15898a61618743713808daf6c3ccab9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T10:04:17Z","title_canon_sha256":"bbf503e2db8d40fb9ef72d9b0e251d70367d25c3c266641ce13b835d69d104a6"},"schema_version":"1.0","source":{"id":"2402.14418","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14418","created_at":"2026-07-05T07:48:53Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14418v2","created_at":"2026-07-05T07:48:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14418","created_at":"2026-07-05T07:48:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZTUJCQ5RCDDB","created_at":"2026-07-05T07:48:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZTUJCQ5RCDDB4Y4F","created_at":"2026-07-05T07:48:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZTUJCQ5R","created_at":"2026-07-05T07:48:53Z"}],"graph_snapshots":[{"event_id":"sha256:b70b04ad34ad035668816b185cae2e1325e1a58d721af809c2ad2a70b285b341","target":"graph","created_at":"2026-07-05T07:48:53Z","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/2402.14418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models like GPT-4, LLaVA, and CogVLM have surged in popularity recently due to their impressive performance in several vision-language tasks. Current evaluation methods, however, overlook an essential component: uncertainty, which is crucial for a comprehensive assessment of VLMs. Addressing this oversight, we present a benchmark incorporating uncertainty quantification into evaluating VLMs.\n  Our analysis spans 20+ VLMs, focusing on the multiple-choice Visual Question Answering (VQA) task. We examine models on 5 datasets that evaluate various vision-language capabilities.\n  Us","authors_text":"Bulat Nutfullin, Eugene Ilyushin, Oleg Pilipenko, Vasily Kostumov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T10:04:17Z","title":"Uncertainty-Aware Evaluation for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14418","kind":"arxiv","version":2},"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":"sha256:97cf5c75e837b69cb0d26966b7d9a7eb06f204b69bf484436ceee96b7a7352b8","target":"record","created_at":"2026-07-05T07:48:53Z","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":"fa3da6b224d4b43144d7f1fbf8dc3069c15898a61618743713808daf6c3ccab9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T10:04:17Z","title_canon_sha256":"bbf503e2db8d40fb9ef72d9b0e251d70367d25c3c266641ce13b835d69d104a6"},"schema_version":"1.0","source":{"id":"2402.14418","kind":"arxiv","version":2}},"canonical_sha256":"cce89143b110c61e6385b18930b1c20611eddd3d1e02478d4abe155ce5162e23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cce89143b110c61e6385b18930b1c20611eddd3d1e02478d4abe155ce5162e23","first_computed_at":"2026-07-05T07:48:53.675388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:53.675388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YOsNbBlrjhePBrAtDTgV4tb+3RtkD3Uidjk3GtwSObBcQTESF2Ej6Oe677r/XRpYFYUguGk3s/j1jReotvjhAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:53.675843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14418","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97cf5c75e837b69cb0d26966b7d9a7eb06f204b69bf484436ceee96b7a7352b8","sha256:b70b04ad34ad035668816b185cae2e1325e1a58d721af809c2ad2a70b285b341"],"state_sha256":"856f1ecccd37e8e48cfca3d3b6cf7561b989e7fc9d64aea9887f8befbde7e005"}