{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K3HFUJSJSQDVYK3VPH2MDSUIUL","short_pith_number":"pith:K3HFUJSJ","schema_version":"1.0","canonical_sha256":"56ce5a264994075c2b7579f4c1ca88a2f1ec665e1e8f3eb3b08c2fa4b43f0f55","source":{"kind":"arxiv","id":"2505.23272","version":2},"attestation_state":"computed","paper":{"title":"Are MLMs Trapped in the Visual Room?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ben Yao, Chunwang Zou, Jing Qin, Lu Rong, Peng Zhang, Qimeng Liu, Qiuchi Li, Yazhou Zhang, Zheng Lian","submitted_at":"2025-05-29T09:20:12Z","abstract_excerpt":"Can multi-modal large models (MLMs) that can ``see'' an image be said to ``understand'' it? Drawing inspiration from Searle's Chinese Room, we propose the \\textbf{Visual Room} argument: a system may process and describe every detail of visual inputs by following algorithmic rules, without genuinely comprehending the underlying intention. This dilemma challenges the prevailing assumption that perceptual mastery implies genuine understanding. In implementation, we introduce a two-tier evaluation framework spanning perception and cognition. The perception component evaluates whether MLMs can accu"},"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":"2505.23272","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T09:20:12Z","cross_cats_sorted":[],"title_canon_sha256":"e4708e38c3eb1107e2ea7c276798d4abc4df9c697b009bcc30407c10c20faec6","abstract_canon_sha256":"cbe1c904a8461ba7dfae660c6eead4d91b605893e261068cd731f93683905fb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:34.689842Z","signature_b64":"6pGdAkkfObR3Rw/MiwG2YIYPFezVaaMl2JyCP0Z2exFBHizRpKUFOGvIEwBVzt8va2Ah9AAm7xr5TtK5SUy7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56ce5a264994075c2b7579f4c1ca88a2f1ec665e1e8f3eb3b08c2fa4b43f0f55","last_reissued_at":"2026-07-05T11:12:34.689322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:34.689322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are MLMs Trapped in the Visual Room?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ben Yao, Chunwang Zou, Jing Qin, Lu Rong, Peng Zhang, Qimeng Liu, Qiuchi Li, Yazhou Zhang, Zheng Lian","submitted_at":"2025-05-29T09:20:12Z","abstract_excerpt":"Can multi-modal large models (MLMs) that can ``see'' an image be said to ``understand'' it? Drawing inspiration from Searle's Chinese Room, we propose the \\textbf{Visual Room} argument: a system may process and describe every detail of visual inputs by following algorithmic rules, without genuinely comprehending the underlying intention. This dilemma challenges the prevailing assumption that perceptual mastery implies genuine understanding. In implementation, we introduce a two-tier evaluation framework spanning perception and cognition. The perception component evaluates whether MLMs can accu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23272","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/2505.23272/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":"2505.23272","created_at":"2026-07-05T11:12:34.689391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23272v2","created_at":"2026-07-05T11:12:34.689391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23272","created_at":"2026-07-05T11:12:34.689391+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3HFUJSJSQDV","created_at":"2026-07-05T11:12:34.689391+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3HFUJSJSQDVYK3V","created_at":"2026-07-05T11:12:34.689391+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3HFUJSJ","created_at":"2026-07-05T11:12:34.689391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19420","citing_title":"Commander-GPT: Dividing and Routing for Multimodal Sarcasm Detection","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL","json":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL.json","graph_json":"https://pith.science/api/pith-number/K3HFUJSJSQDVYK3VPH2MDSUIUL/graph.json","events_json":"https://pith.science/api/pith-number/K3HFUJSJSQDVYK3VPH2MDSUIUL/events.json","paper":"https://pith.science/paper/K3HFUJSJ"},"agent_actions":{"view_html":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL","download_json":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL.json","view_paper":"https://pith.science/paper/K3HFUJSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23272&json=true","fetch_graph":"https://pith.science/api/pith-number/K3HFUJSJSQDVYK3VPH2MDSUIUL/graph.json","fetch_events":"https://pith.science/api/pith-number/K3HFUJSJSQDVYK3VPH2MDSUIUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/action/storage_attestation","attest_author":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/action/author_attestation","sign_citation":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/action/citation_signature","submit_replication":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/action/replication_record"}},"created_at":"2026-07-05T11:12:34.689391+00:00","updated_at":"2026-07-05T11:12:34.689391+00:00"}