{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BG6KOY6CM3RKLSDY6X2RSNMIAC","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":"e06eec9a522049bb54688489248f8922c21121b3f70e5e0429f151449eae9464","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-09T06:20:17Z","title_canon_sha256":"2175894e042d99792aaf61c8ee9d2fa6bb3b8a564ea5b6c8f0053010e56afed7"},"schema_version":"1.0","source":{"id":"2407.06581","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06581","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06581v6","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06581","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"BG6KOY6CM3RK","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"BG6KOY6CM3RKLSDY","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"BG6KOY6C","created_at":"2026-07-05T10:40:01Z"}],"graph_snapshots":[{"event_id":"sha256:fb35500501fc176047e5221a728c384eba400a9aee2e6b20fdcdc0bb7a4b1000","target":"graph","created_at":"2026-07-05T10:40:01Z","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/2407.06581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models with vision capabilities (VLMs), e.g., GPT-4o and Gemini 1.5 Pro, score high on many vision-understanding benchmarks, they are still struggling with low-level vision tasks that are easy to humans. Specifically, on BlindTest, our suite of 7 very simple tasks, including identifying (a) whether two circles overlap; (b) how many times two lines intersect; (c) which letter is being circled in a word; and (d) the number of circles in an Olympic-like logo, four state-of-the-art VLMs are only 58.07% accurate on average. Claude 3.5 Sonnet performs the best at 77.84% accuracy","authors_text":"Anh Totti Nguyen, Logan Bolton, Mohammad Reza Taesiri, Pooyan Rahmanzadehgervi","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-09T06:20:17Z","title":"Vision language models are blind: Failing to translate detailed visual features into words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06581","kind":"arxiv","version":6},"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:ea5969d5921bda1c53eb3a7b9fc32524355b742d00f39bc298522b1964a1a3a4","target":"record","created_at":"2026-07-05T10:40:01Z","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":"e06eec9a522049bb54688489248f8922c21121b3f70e5e0429f151449eae9464","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-09T06:20:17Z","title_canon_sha256":"2175894e042d99792aaf61c8ee9d2fa6bb3b8a564ea5b6c8f0053010e56afed7"},"schema_version":"1.0","source":{"id":"2407.06581","kind":"arxiv","version":6}},"canonical_sha256":"09bca763c266e2a5c878f5f519358800899b740e3662a488acd43ee337938f74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09bca763c266e2a5c878f5f519358800899b740e3662a488acd43ee337938f74","first_computed_at":"2026-07-05T10:40:01.797129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:01.797129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5eJNAew1jk7izm6uRF7GBuIqL84H4s5sPIb3gQLZcyx8/j2zEjUu97Bh8+E4LroSt5CL4RKikywWFkcA70yoAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:01.797649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.06581","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea5969d5921bda1c53eb3a7b9fc32524355b742d00f39bc298522b1964a1a3a4","sha256:fb35500501fc176047e5221a728c384eba400a9aee2e6b20fdcdc0bb7a4b1000"],"state_sha256":"003e26b809e9ffa1821a4aacaa197943957ad25303ca9ab51f083523eb962a76"}