{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PKP5SBAWAKEI4CPTPBDMAP2BVJ","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":"5ce6000c5029ef9c05249825387875f689907a4f9141f2b4fcd5cb731695bb1e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T21:50:16Z","title_canon_sha256":"ab9e87c1aaccf6368763c960e30a94be1ab7e2cc33f995f18e63e21d9e7dadc5"},"schema_version":"1.0","source":{"id":"2507.16863","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16863","created_at":"2026-06-25T01:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16863v2","created_at":"2026-06-25T01:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16863","created_at":"2026-06-25T01:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"PKP5SBAWAKEI","created_at":"2026-06-25T01:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"PKP5SBAWAKEI4CPT","created_at":"2026-06-25T01:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"PKP5SBAW","created_at":"2026-06-25T01:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:67bb3507ba955581676a06e8fb9c46a65be1835510eb34fbb543ee53e266308e","target":"graph","created_at":"2026-06-25T01:17:45Z","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/2507.16863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A common belief in multimodal research is that the perceptual weaknesses of vision--language models can be compensated by stronger language reasoning (e.g., chain-of-thought, in-context learning, or external tools). We challenge this assumption. We argue that for a broad class of visual tasks hard to specify in language, failures stem from a structural fatality where the temporal decision of \\textit{when} to reason strictly dictates the spatial constraint of \\textit{where} reasoning takes place. When visual reasoning is deferred to language generation, current architectures do not merely delay","authors_text":"Balong Bi, Ge Wu, Haoyang Li, Hongcheng Gao, Hongyu Chen, Jingyi Tang, Lin Xu, Minhua Lin, Olive Huang, Taihang Hu, Wentao Zhang, Xinhao Li, Xinlong Yang, Yue Liu, Zihao Huang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T21:50:16Z","title":"Position: Reasoning After Perception Means Reasoning Without Vision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16863","kind":"arxiv","version":2},"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":"sha256:1153dca1594cf0fd5877174e00e91a9b9f29b732fc2254b123d797bbb3a10abc","target":"record","created_at":"2026-06-25T01:17:45Z","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":"5ce6000c5029ef9c05249825387875f689907a4f9141f2b4fcd5cb731695bb1e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T21:50:16Z","title_canon_sha256":"ab9e87c1aaccf6368763c960e30a94be1ab7e2cc33f995f18e63e21d9e7dadc5"},"schema_version":"1.0","source":{"id":"2507.16863","kind":"arxiv","version":2}},"canonical_sha256":"7a9fd9041602888e09f37846c03f41aa761e17b79dfa3bdd8458a756519fec8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a9fd9041602888e09f37846c03f41aa761e17b79dfa3bdd8458a756519fec8c","first_computed_at":"2026-06-25T01:17:45.607492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:17:45.607492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pC9LAjFvU0pBd/C4irF4E9GVAgJ2mftcNwRdQHQGCn0oah1IzCpdw/irLZ5UTth9A+Q11j9x6mGuua67NLpRDA==","signature_status":"signed_v1","signed_at":"2026-06-25T01:17:45.607964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.16863","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1153dca1594cf0fd5877174e00e91a9b9f29b732fc2254b123d797bbb3a10abc","sha256:67bb3507ba955581676a06e8fb9c46a65be1835510eb34fbb543ee53e266308e"],"state_sha256":"813ca69451bbe04627a32bf2225e0e7f4cb7c24794a1262feaf3cd60d2316fe2"}