{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JE2DQKXLVZTEM3HMN4TWRHTQ5E","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":"9d8ea0c9882e7ffc902416ce4f3798bf7963edf2a08bbb474f7aed1126b7b940","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-31T08:18:34Z","title_canon_sha256":"f4ac130dec96a28cdd2bfa5a7818e264f2516ede4ee3c2fc286eae329071d30c"},"schema_version":"1.0","source":{"id":"2602.00593","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.00593","created_at":"2026-05-21T01:05:15Z"},{"alias_kind":"arxiv_version","alias_value":"2602.00593v3","created_at":"2026-05-21T01:05:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.00593","created_at":"2026-05-21T01:05:15Z"},{"alias_kind":"pith_short_12","alias_value":"JE2DQKXLVZTE","created_at":"2026-05-21T01:05:15Z"},{"alias_kind":"pith_short_16","alias_value":"JE2DQKXLVZTEM3HM","created_at":"2026-05-21T01:05:15Z"},{"alias_kind":"pith_short_8","alias_value":"JE2DQKXL","created_at":"2026-05-21T01:05:15Z"}],"graph_snapshots":[{"event_id":"sha256:af07544778efdc89b5366430490b4b609e056666465e0936dc2698008322fb06","target":"graph","created_at":"2026-05-21T01:05:15Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"the most advanced model (Gemini-3.1-Pro) achieves only 51.7% average accuracy, even with access to visual ground truth and search tools."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The questions and answers produced by PhD annotators from top universities faithfully represent expert-level challenges of fine-grained visual grounding plus external knowledge without introducing systematic biases or inconsistent difficulty."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Pix2Fact benchmark shows top VLMs achieve only 51.7 percent accuracy on fine-grained visual questions needing both detailed image grounding and web-verified external knowledge."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Current top vision-language models reach only 51.7 percent accuracy on questions that demand both precise visual details from high-resolution scenes and external knowledge verification."}],"snapshot_sha256":"216b1ca2821a3dd597ac82d45526274301a1869b4601e9ea8532bb2c4b01b06b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.00593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities in isolation. To fill this void, we introduce Pix2Fact, a visual question-answering benchmark designed to assess expert-level visual perception and knowledge search. Pix2Fact comprises 1,000 high-resolution (4K+) images spanning eight scenarios. Its questions and answers are meticulously crafted by PhD-holding annotators from top global universities across ","authors_text":"Bingzhang Wang, Bofei Zhang, Cong Zhang, Qiaofeng Zheng, Yew-Soon Ong, Yifan Jiang, Yifan Yang","cross_cats":["cs.LG"],"headline":"Current top vision-language models reach only 51.7 percent accuracy on questions that demand both precise visual details from high-resolution scenes and external knowledge verification.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-31T08:18:34Z","title":"Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.00593","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T09:11:44.471030Z","id":"18d063c2-dd20-497c-8c2a-5621250bc686","model_set":{"reader":"grok-4.3"},"one_line_summary":"Pix2Fact benchmark shows top VLMs achieve only 51.7 percent accuracy on fine-grained visual questions needing both detailed image grounding and web-verified external knowledge.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Current top vision-language models reach only 51.7 percent accuracy on questions that demand both precise visual details from high-resolution scenes and external knowledge verification.","strongest_claim":"the most advanced model (Gemini-3.1-Pro) achieves only 51.7% average accuracy, even with access to visual ground truth and search tools.","weakest_assumption":"The questions and answers produced by PhD annotators from top universities faithfully represent expert-level challenges of fine-grained visual grounding plus external knowledge without introducing systematic biases or inconsistent difficulty."}},"verdict_id":"18d063c2-dd20-497c-8c2a-5621250bc686"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:16326b54df595fcad51eecc374585cbf3037570ba3cf3f69fe0c6a30f85e4b61","target":"record","created_at":"2026-05-21T01:05:15Z","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":"9d8ea0c9882e7ffc902416ce4f3798bf7963edf2a08bbb474f7aed1126b7b940","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-31T08:18:34Z","title_canon_sha256":"f4ac130dec96a28cdd2bfa5a7818e264f2516ede4ee3c2fc286eae329071d30c"},"schema_version":"1.0","source":{"id":"2602.00593","kind":"arxiv","version":3}},"canonical_sha256":"4934382aebae66466cec6f27689e70e933c12b2fa0992274f3f1cdadfaae155f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4934382aebae66466cec6f27689e70e933c12b2fa0992274f3f1cdadfaae155f","first_computed_at":"2026-05-21T01:05:15.363778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:15.363778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"60qAourmq904RxiIYLnfMyYaNWZJeMl6KkOr8PbRd3IlMkBWWBsoZK7ANnxBgK0R8g0urvjm3BBab2wHECVpCQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:15.364638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.00593","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16326b54df595fcad51eecc374585cbf3037570ba3cf3f69fe0c6a30f85e4b61","sha256:af07544778efdc89b5366430490b4b609e056666465e0936dc2698008322fb06"],"state_sha256":"451ca31ee182ebc29e23fb0df427ac796a4060fd39115252f767ab63482858d5"}