{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YEV7LRNRRQUKDURFT7JEQTABMM","short_pith_number":"pith:YEV7LRNR","schema_version":"1.0","canonical_sha256":"c12bf5c5b18c28a1d2259fd2484c01633dc6b91bc7ad2f306d150fad83d6c069","source":{"kind":"arxiv","id":"2503.18071","version":1},"attestation_state":"computed","paper":{"title":"Mind with Eyes: from Language Reasoning to Multimodal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jitao Sang, Xian Zhao, Yifei Gao, Yunfan Yang, Zhiyu Lin","submitted_at":"2025-03-23T13:40:44Z","abstract_excerpt":"Language models have recently advanced into the realm of reasoning, yet it is through multimodal reasoning that we can fully unlock the potential to achieve more comprehensive, human-like cognitive capabilities. This survey provides a systematic overview of the recent multimodal reasoning approaches, categorizing them into two levels: language-centric multimodal reasoning and collaborative multimodal reasoning. The former encompasses one-pass visual perception and active visual perception, where vision primarily serves a supporting role in language reasoning. The latter involves action generat"},"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":"2503.18071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-23T13:40:44Z","cross_cats_sorted":[],"title_canon_sha256":"f8b6b18e9063f573b605d01f0fd6edba3cd585f5b47b22e79301b0a661449b7e","abstract_canon_sha256":"4c9e08701dd8cd1eb5fa870968ff099658b588415a536861aff7d5ff7fe72519"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:01.954590Z","signature_b64":"u/ykel2Y88JXPXif4/H+LjnUDYdNg+FgDyoMx+NGykE4a9Fgekx+5Dsn6Ho78i9eDF0d3YZRV5SOylNV4ojnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c12bf5c5b18c28a1d2259fd2484c01633dc6b91bc7ad2f306d150fad83d6c069","last_reissued_at":"2026-07-05T10:38:01.954178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:01.954178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mind with Eyes: from Language Reasoning to Multimodal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jitao Sang, Xian Zhao, Yifei Gao, Yunfan Yang, Zhiyu Lin","submitted_at":"2025-03-23T13:40:44Z","abstract_excerpt":"Language models have recently advanced into the realm of reasoning, yet it is through multimodal reasoning that we can fully unlock the potential to achieve more comprehensive, human-like cognitive capabilities. This survey provides a systematic overview of the recent multimodal reasoning approaches, categorizing them into two levels: language-centric multimodal reasoning and collaborative multimodal reasoning. The former encompasses one-pass visual perception and active visual perception, where vision primarily serves a supporting role in language reasoning. The latter involves action generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18071","kind":"arxiv","version":1},"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/2503.18071/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":"2503.18071","created_at":"2026-07-05T10:38:01.954236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18071v1","created_at":"2026-07-05T10:38:01.954236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18071","created_at":"2026-07-05T10:38:01.954236+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEV7LRNRRQUK","created_at":"2026-07-05T10:38:01.954236+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEV7LRNRRQUKDURF","created_at":"2026-07-05T10:38:01.954236+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEV7LRNR","created_at":"2026-07-05T10:38:01.954236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03483","citing_title":"BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEV7LRNRRQUKDURFT7JEQTABMM","json":"https://pith.science/pith/YEV7LRNRRQUKDURFT7JEQTABMM.json","graph_json":"https://pith.science/api/pith-number/YEV7LRNRRQUKDURFT7JEQTABMM/graph.json","events_json":"https://pith.science/api/pith-number/YEV7LRNRRQUKDURFT7JEQTABMM/events.json","paper":"https://pith.science/paper/YEV7LRNR"},"agent_actions":{"view_html":"https://pith.science/pith/YEV7LRNRRQUKDURFT7JEQTABMM","download_json":"https://pith.science/pith/YEV7LRNRRQUKDURFT7JEQTABMM.json","view_paper":"https://pith.science/paper/YEV7LRNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18071&json=true","fetch_graph":"https://pith.science/api/pith-number/YEV7LRNRRQUKDURFT7JEQTABMM/graph.json","fetch_events":"https://pith.science/api/pith-number/YEV7LRNRRQUKDURFT7JEQTABMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEV7LRNRRQUKDURFT7JEQTABMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEV7LRNRRQUKDURFT7JEQTABMM/action/storage_attestation","attest_author":"https://pith.science/pith/YEV7LRNRRQUKDURFT7JEQTABMM/action/author_attestation","sign_citation":"https://pith.science/pith/YEV7LRNRRQUKDURFT7JEQTABMM/action/citation_signature","submit_replication":"https://pith.science/pith/YEV7LRNRRQUKDURFT7JEQTABMM/action/replication_record"}},"created_at":"2026-07-05T10:38:01.954236+00:00","updated_at":"2026-07-05T10:38:01.954236+00:00"}