{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PKP5SBAWAKEI4CPTPBDMAP2BVJ","short_pith_number":"pith:PKP5SBAW","schema_version":"1.0","canonical_sha256":"7a9fd9041602888e09f37846c03f41aa761e17b79dfa3bdd8458a756519fec8c","source":{"kind":"arxiv","id":"2507.16863","version":2},"attestation_state":"computed","paper":{"title":"Position: Reasoning After Perception Means Reasoning Without Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","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","submitted_at":"2025-07-21T21:50:16Z","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"},"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":"2507.16863","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T21:50:16Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ab9e87c1aaccf6368763c960e30a94be1ab7e2cc33f995f18e63e21d9e7dadc5","abstract_canon_sha256":"5ce6000c5029ef9c05249825387875f689907a4f9141f2b4fcd5cb731695bb1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:17:45.607964Z","signature_b64":"pC9LAjFvU0pBd/C4irF4E9GVAgJ2mftcNwRdQHQGCn0oah1IzCpdw/irLZ5UTth9A+Q11j9x6mGuua67NLpRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a9fd9041602888e09f37846c03f41aa761e17b79dfa3bdd8458a756519fec8c","last_reissued_at":"2026-06-25T01:17:45.607492Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:17:45.607492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position: Reasoning After Perception Means Reasoning Without Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","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","submitted_at":"2025-07-21T21:50:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16863","kind":"arxiv","version":2},"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/2507.16863/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":"2507.16863","created_at":"2026-06-25T01:17:45.607552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16863v2","created_at":"2026-06-25T01:17:45.607552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16863","created_at":"2026-06-25T01:17:45.607552+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKP5SBAWAKEI","created_at":"2026-06-25T01:17:45.607552+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKP5SBAWAKEI4CPT","created_at":"2026-06-25T01:17:45.607552+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKP5SBAW","created_at":"2026-06-25T01:17:45.607552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKP5SBAWAKEI4CPTPBDMAP2BVJ","json":"https://pith.science/pith/PKP5SBAWAKEI4CPTPBDMAP2BVJ.json","graph_json":"https://pith.science/api/pith-number/PKP5SBAWAKEI4CPTPBDMAP2BVJ/graph.json","events_json":"https://pith.science/api/pith-number/PKP5SBAWAKEI4CPTPBDMAP2BVJ/events.json","paper":"https://pith.science/paper/PKP5SBAW"},"agent_actions":{"view_html":"https://pith.science/pith/PKP5SBAWAKEI4CPTPBDMAP2BVJ","download_json":"https://pith.science/pith/PKP5SBAWAKEI4CPTPBDMAP2BVJ.json","view_paper":"https://pith.science/paper/PKP5SBAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16863&json=true","fetch_graph":"https://pith.science/api/pith-number/PKP5SBAWAKEI4CPTPBDMAP2BVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PKP5SBAWAKEI4CPTPBDMAP2BVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKP5SBAWAKEI4CPTPBDMAP2BVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKP5SBAWAKEI4CPTPBDMAP2BVJ/action/storage_attestation","attest_author":"https://pith.science/pith/PKP5SBAWAKEI4CPTPBDMAP2BVJ/action/author_attestation","sign_citation":"https://pith.science/pith/PKP5SBAWAKEI4CPTPBDMAP2BVJ/action/citation_signature","submit_replication":"https://pith.science/pith/PKP5SBAWAKEI4CPTPBDMAP2BVJ/action/replication_record"}},"created_at":"2026-06-25T01:17:45.607552+00:00","updated_at":"2026-06-25T01:17:45.607552+00:00"}