{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F7DABBN7XLNJQFOS2BDKT5KWKS","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":"96b5a2c3bc3442544c8eeb93d995a591e5d900163c14273623b62934717200e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T17:16:36Z","title_canon_sha256":"1911c48591f3f7867d4188ba331e2b5631597c302b936bfb117d704a5518d8ec"},"schema_version":"1.0","source":{"id":"2505.20236","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20236","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20236v1","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20236","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"F7DABBN7XLNJ","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"F7DABBN7XLNJQFOS","created_at":"2026-07-05T11:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"F7DABBN7","created_at":"2026-07-05T11:09:54Z"}],"graph_snapshots":[{"event_id":"sha256:736be23addef8dc7137bc336290f0e314cc8a21d84d94c08c8bfbfd0356a4aa6","target":"graph","created_at":"2026-07-05T11:09:54Z","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/2505.20236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models express their confidence through natural language, has emerged as a lightweight and interpretable solution in large language models (LLMs). However, its effectiveness in vision-language models (VLMs) remains insufficiently studied. In this work, we conduct a comprehensive evaluation of verbalized confidence in VLMs, spanning three model categories, four task domains, and three evaluation scenarios. Our results show that ","authors_text":"Heli Qi, Junjue Wang, Naoto Yokoya, Qingcheng Zeng, Weihao Xuan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T17:16:36Z","title":"Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20236","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":"sha256:8cdcfb8a949976a9bb99f8e1b84b19c871b739213ff7b364a8858e309ae14958","target":"record","created_at":"2026-07-05T11:09:54Z","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":"96b5a2c3bc3442544c8eeb93d995a591e5d900163c14273623b62934717200e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T17:16:36Z","title_canon_sha256":"1911c48591f3f7867d4188ba331e2b5631597c302b936bfb117d704a5518d8ec"},"schema_version":"1.0","source":{"id":"2505.20236","kind":"arxiv","version":1}},"canonical_sha256":"2fc60085bfbada9815d2d046a9f55654b90b2e97ff2da6c1472975bc570caa48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fc60085bfbada9815d2d046a9f55654b90b2e97ff2da6c1472975bc570caa48","first_computed_at":"2026-07-05T11:09:54.857034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:54.857034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WYprBLH61gb7pJEFIOX50EIAT1gGurcMzShZYFsd5I/gwMsKq/Gb114yRYeHFp0TDCt6dHpnQc5sI4vN7pjoBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:54.857541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20236","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cdcfb8a949976a9bb99f8e1b84b19c871b739213ff7b364a8858e309ae14958","sha256:736be23addef8dc7137bc336290f0e314cc8a21d84d94c08c8bfbfd0356a4aa6"],"state_sha256":"daca5931bcf9a2191c1bf4d16faabca40a02e1b646477a7523867b25d24420e2"}