{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YALVU555X4MOMKT5YUIX4DE4SJ","short_pith_number":"pith:YALVU555","schema_version":"1.0","canonical_sha256":"c0175a77bdbf18e62a7dc5117e0c9c926bc671f95c4bc87580f627f5b11bbaed","source":{"kind":"arxiv","id":"2503.06492","version":1},"attestation_state":"computed","paper":{"title":"VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haoyang Li, Jing Zhang, Ke Xu, Lixin Liu, Qi Li, Shasha Guo, Xiaodong Chen, Yanling Wang, Yihan Zhao, Yong Xiao","submitted_at":"2025-03-09T07:25:32Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.06492","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-09T07:25:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"32bf112bded8a32931b9f5f2a8cbef48feae018d00947fa17dfc2207fa3a139b","abstract_canon_sha256":"b179848307dad60552cca47c48bef60e257039330ac4eb3998f9dc5492fef0ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:35.256740Z","signature_b64":"f5JizNNZ7B3jeX4xBwowB1cYR2NhvRZICMXOI0Kk2DOEx8C1MCmv9c+mxydUUR5cmHZFe6OteOyNQGI2Sc/CCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0175a77bdbf18e62a7dc5117e0c9c926bc671f95c4bc87580f627f5b11bbaed","last_reissued_at":"2026-07-05T10:27:35.256158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:35.256158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haoyang Li, Jing Zhang, Ke Xu, Lixin Liu, Qi Li, Shasha Guo, Xiaodong Chen, Yanling Wang, Yihan Zhao, Yong Xiao","submitted_at":"2025-03-09T07:25:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06492","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.06492/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.06492","created_at":"2026-07-05T10:27:35.256239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06492v1","created_at":"2026-07-05T10:27:35.256239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06492","created_at":"2026-07-05T10:27:35.256239+00:00"},{"alias_kind":"pith_short_12","alias_value":"YALVU555X4MO","created_at":"2026-07-05T10:27:35.256239+00:00"},{"alias_kind":"pith_short_16","alias_value":"YALVU555X4MOMKT5","created_at":"2026-07-05T10:27:35.256239+00:00"},{"alias_kind":"pith_short_8","alias_value":"YALVU555","created_at":"2026-07-05T10:27:35.256239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20236","citing_title":"Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YALVU555X4MOMKT5YUIX4DE4SJ","json":"https://pith.science/pith/YALVU555X4MOMKT5YUIX4DE4SJ.json","graph_json":"https://pith.science/api/pith-number/YALVU555X4MOMKT5YUIX4DE4SJ/graph.json","events_json":"https://pith.science/api/pith-number/YALVU555X4MOMKT5YUIX4DE4SJ/events.json","paper":"https://pith.science/paper/YALVU555"},"agent_actions":{"view_html":"https://pith.science/pith/YALVU555X4MOMKT5YUIX4DE4SJ","download_json":"https://pith.science/pith/YALVU555X4MOMKT5YUIX4DE4SJ.json","view_paper":"https://pith.science/paper/YALVU555","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06492&json=true","fetch_graph":"https://pith.science/api/pith-number/YALVU555X4MOMKT5YUIX4DE4SJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YALVU555X4MOMKT5YUIX4DE4SJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YALVU555X4MOMKT5YUIX4DE4SJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YALVU555X4MOMKT5YUIX4DE4SJ/action/storage_attestation","attest_author":"https://pith.science/pith/YALVU555X4MOMKT5YUIX4DE4SJ/action/author_attestation","sign_citation":"https://pith.science/pith/YALVU555X4MOMKT5YUIX4DE4SJ/action/citation_signature","submit_replication":"https://pith.science/pith/YALVU555X4MOMKT5YUIX4DE4SJ/action/replication_record"}},"created_at":"2026-07-05T10:27:35.256239+00:00","updated_at":"2026-07-05T10:27:35.256239+00:00"}