{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K3HFUJSJSQDVYK3VPH2MDSUIUL","short_pith_number":"pith:K3HFUJSJ","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"},"canonical_sha256":"56ce5a264994075c2b7579f4c1ca88a2f1ec665e1e8f3eb3b08c2fa4b43f0f55","source":{"kind":"arxiv","id":"2505.23272","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23272","created_at":"2026-07-05T11:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23272v2","created_at":"2026-07-05T11:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23272","created_at":"2026-07-05T11:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"K3HFUJSJSQDV","created_at":"2026-07-05T11:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"K3HFUJSJSQDVYK3V","created_at":"2026-07-05T11:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"K3HFUJSJ","created_at":"2026-07-05T11:12:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K3HFUJSJSQDVYK3VPH2MDSUIUL","target":"record","payload":{"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"},"canonical_sha256":"56ce5a264994075c2b7579f4c1ca88a2f1ec665e1e8f3eb3b08c2fa4b43f0f55","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"},"source_kind":"arxiv","source_id":"2505.23272","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0f410l243njJq9HBY+evuveSkFiFg8JmfxNcMom7h8HxxOUjM4yjcB0+Kfiwvc0zKZh93KKYKkiwqhCi5q6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:42:50.527811Z"},"content_sha256":"c31bc76419f7d2637a0bbb8fa79c1699ab4598f893a448b890277123ea0c0250","schema_version":"1.0","event_id":"sha256:c31bc76419f7d2637a0bbb8fa79c1699ab4598f893a448b890277123ea0c0250"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K3HFUJSJSQDVYK3VPH2MDSUIUL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Io+STD5mXzpk1W167lcfwxF5N1LE0+7rXCYsfwfwMTTpIS9a/S451JptOT5ZgLZdubulB+JRfp3DpF+0vc5DCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:42:50.528191Z"},"content_sha256":"fd6053b7b4e2edc66a5faf784290b7ead44989845067fe80ccda2172ec43a31a","schema_version":"1.0","event_id":"sha256:fd6053b7b4e2edc66a5faf784290b7ead44989845067fe80ccda2172ec43a31a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/bundle.json","state_url":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T19:42:50Z","links":{"resolver":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL","bundle":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/bundle.json","state":"https://pith.science/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K3HFUJSJSQDVYK3VPH2MDSUIUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K3HFUJSJSQDVYK3VPH2MDSUIUL","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":"cbe1c904a8461ba7dfae660c6eead4d91b605893e261068cd731f93683905fb5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T09:20:12Z","title_canon_sha256":"e4708e38c3eb1107e2ea7c276798d4abc4df9c697b009bcc30407c10c20faec6"},"schema_version":"1.0","source":{"id":"2505.23272","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23272","created_at":"2026-07-05T11:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23272v2","created_at":"2026-07-05T11:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23272","created_at":"2026-07-05T11:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"K3HFUJSJSQDV","created_at":"2026-07-05T11:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"K3HFUJSJSQDVYK3V","created_at":"2026-07-05T11:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"K3HFUJSJ","created_at":"2026-07-05T11:12:34Z"}],"graph_snapshots":[{"event_id":"sha256:fd6053b7b4e2edc66a5faf784290b7ead44989845067fe80ccda2172ec43a31a","target":"graph","created_at":"2026-07-05T11:12:34Z","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/2505.23272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ben Yao, Chunwang Zou, Jing Qin, Lu Rong, Peng Zhang, Qimeng Liu, Qiuchi Li, Yazhou Zhang, Zheng Lian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T09:20:12Z","title":"Are MLMs Trapped in the Visual Room?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23272","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:c31bc76419f7d2637a0bbb8fa79c1699ab4598f893a448b890277123ea0c0250","target":"record","created_at":"2026-07-05T11:12:34Z","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":"cbe1c904a8461ba7dfae660c6eead4d91b605893e261068cd731f93683905fb5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T09:20:12Z","title_canon_sha256":"e4708e38c3eb1107e2ea7c276798d4abc4df9c697b009bcc30407c10c20faec6"},"schema_version":"1.0","source":{"id":"2505.23272","kind":"arxiv","version":2}},"canonical_sha256":"56ce5a264994075c2b7579f4c1ca88a2f1ec665e1e8f3eb3b08c2fa4b43f0f55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56ce5a264994075c2b7579f4c1ca88a2f1ec665e1e8f3eb3b08c2fa4b43f0f55","first_computed_at":"2026-07-05T11:12:34.689322Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:34.689322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6pGdAkkfObR3Rw/MiwG2YIYPFezVaaMl2JyCP0Z2exFBHizRpKUFOGvIEwBVzt8va2Ah9AAm7xr5TtK5SUy7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:34.689842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23272","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c31bc76419f7d2637a0bbb8fa79c1699ab4598f893a448b890277123ea0c0250","sha256:fd6053b7b4e2edc66a5faf784290b7ead44989845067fe80ccda2172ec43a31a"],"state_sha256":"c14e42acf8bb8f1f270d5adfd8beb029fa218a0fb8a4fa32ffcb6c5913b7a20e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"srkjTzQJsCvGfzIlJ5xZbJHCFisiAYIuTQwpBlteTVX+vtLYQyEuKtehBnYZSU6/0TXlBMEIF9y7nT0EFoysAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:42:50.530276Z","bundle_sha256":"fa275d33fd48c198c46b59ed4570ae1aac48cbe660ed4c05d9329c5fc393ed90"}}