{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YALVU555X4MOMKT5YUIX4DE4SJ","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":"b179848307dad60552cca47c48bef60e257039330ac4eb3998f9dc5492fef0ef","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-09T07:25:32Z","title_canon_sha256":"32bf112bded8a32931b9f5f2a8cbef48feae018d00947fa17dfc2207fa3a139b"},"schema_version":"1.0","source":{"id":"2503.06492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06492","created_at":"2026-07-05T10:27:35Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06492v1","created_at":"2026-07-05T10:27:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06492","created_at":"2026-07-05T10:27:35Z"},{"alias_kind":"pith_short_12","alias_value":"YALVU555X4MO","created_at":"2026-07-05T10:27:35Z"},{"alias_kind":"pith_short_16","alias_value":"YALVU555X4MOMKT5","created_at":"2026-07-05T10:27:35Z"},{"alias_kind":"pith_short_8","alias_value":"YALVU555","created_at":"2026-07-05T10:27:35Z"}],"graph_snapshots":[{"event_id":"sha256:6c1978ce548238852b519e2864f7af24a91da1471129b011783fd0f50cd50285","target":"graph","created_at":"2026-07-05T10:27:35Z","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/2503.06492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) have demonstrated remarkable achievements, yet the generation of non-factual responses remains prevalent in fact-seeking question answering (QA). Current multimodal fact-seeking benchmarks primarily focus on comparing model outputs to ground truth answers, providing limited insights into the performance of modality-specific modules. To bridge this gap, we introduce VisualSimpleQA, a multimodal fact-seeking benchmark with two key features. First, it enables streamlined and decoupled evaluation of LVLMs in visual and linguistic modalities. Second, it incorpor","authors_text":"Haoyang Li, Jing Zhang, Ke Xu, Lixin Liu, Qi Li, Shasha Guo, Xiaodong Chen, Yanling Wang, Yihan Zhao, Yong Xiao","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-09T07:25:32Z","title":"VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06492","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":"sha256:456bc6cbf7118124326663af16ac0a67f77a347e5058b8523354dad6a2dfa345","target":"record","created_at":"2026-07-05T10:27:35Z","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":"b179848307dad60552cca47c48bef60e257039330ac4eb3998f9dc5492fef0ef","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-09T07:25:32Z","title_canon_sha256":"32bf112bded8a32931b9f5f2a8cbef48feae018d00947fa17dfc2207fa3a139b"},"schema_version":"1.0","source":{"id":"2503.06492","kind":"arxiv","version":1}},"canonical_sha256":"c0175a77bdbf18e62a7dc5117e0c9c926bc671f95c4bc87580f627f5b11bbaed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0175a77bdbf18e62a7dc5117e0c9c926bc671f95c4bc87580f627f5b11bbaed","first_computed_at":"2026-07-05T10:27:35.256158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:35.256158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f5JizNNZ7B3jeX4xBwowB1cYR2NhvRZICMXOI0Kk2DOEx8C1MCmv9c+mxydUUR5cmHZFe6OteOyNQGI2Sc/CCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:35.256740Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.06492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:456bc6cbf7118124326663af16ac0a67f77a347e5058b8523354dad6a2dfa345","sha256:6c1978ce548238852b519e2864f7af24a91da1471129b011783fd0f50cd50285"],"state_sha256":"26d7ecc9c101d318bb2c8a30e4555a38bb9eba998793e44c7510b215e3194522"}