{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NTBX7Z4PIVBTCY5UDHGX3454T2","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":"61c164acb1140c3b80072cc74a63362f95ec171ceb21ed26617c626bcbca2913","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T17:59:53Z","title_canon_sha256":"8a06505234690395cf5a8c91b38f895b4d00a6a3f49397a42b4b78f33d9d6445"},"schema_version":"1.0","source":{"id":"2504.15279","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15279","created_at":"2026-07-05T10:51:59Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15279v1","created_at":"2026-07-05T10:51:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15279","created_at":"2026-07-05T10:51:59Z"},{"alias_kind":"pith_short_12","alias_value":"NTBX7Z4PIVBT","created_at":"2026-07-05T10:51:59Z"},{"alias_kind":"pith_short_16","alias_value":"NTBX7Z4PIVBTCY5U","created_at":"2026-07-05T10:51:59Z"},{"alias_kind":"pith_short_8","alias_value":"NTBX7Z4P","created_at":"2026-07-05T10:51:59Z"}],"graph_snapshots":[{"event_id":"sha256:74b2470bf99bd0e400c636857f7224f85f7143db4ba0d9f5e9f2b55fb0e4aff7","target":"graph","created_at":"2026-07-05T10:51:59Z","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/2504.15279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual reasoning is a core component of human intelligence and a critical capability for advanced multimodal models. Yet current reasoning evaluations of multimodal large language models (MLLMs) often rely on text descriptions and allow language-based reasoning shortcuts, failing to measure genuine vision-centric reasoning. To address this, we introduce VisuLogic: a benchmark of 1,000 human-verified problems across six categories (e.g., quantitative shifts, spatial relations, attribute comparisons). These various types of questions can be evaluated to assess the visual reasoning capabilities o","authors_text":"Aijun Yang, Houqiang Li, Jiahao Wang, Jifeng Dai, Jinguo Zhu, Lewei Lu, Weiye Xu, Weiyun Wang, Wengang Zhou, Wenhai Wang, Xiaohua Wang, Xizhou Zhu, Zhe Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T17:59:53Z","title":"VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15279","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":"sha256:0a6bbc2c5108930a904eb5f5230b8551ec143ce1cd83d595518e98259fa0f314","target":"record","created_at":"2026-07-05T10:51:59Z","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":"61c164acb1140c3b80072cc74a63362f95ec171ceb21ed26617c626bcbca2913","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T17:59:53Z","title_canon_sha256":"8a06505234690395cf5a8c91b38f895b4d00a6a3f49397a42b4b78f33d9d6445"},"schema_version":"1.0","source":{"id":"2504.15279","kind":"arxiv","version":1}},"canonical_sha256":"6cc37fe78f45433163b419cd7df3bc9e8f3d8c245b5fe39684b2164be2e0f80a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cc37fe78f45433163b419cd7df3bc9e8f3d8c245b5fe39684b2164be2e0f80a","first_computed_at":"2026-07-05T10:51:59.226003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:59.226003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1bR4AMeeIU2k77W+pTy9tRxDyibo6fK1M2wjT+2e/8Hma2MQs+iVGNN7lXBk/bMYhHNUV3GCTDris3s+F9Z2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:59.226504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15279","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a6bbc2c5108930a904eb5f5230b8551ec143ce1cd83d595518e98259fa0f314","sha256:74b2470bf99bd0e400c636857f7224f85f7143db4ba0d9f5e9f2b55fb0e4aff7"],"state_sha256":"7f30ab51c07a4ad2b72e245a0323cdd8f5acc05b5c2644267c5f3b4fb65f27ba"}