{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXUCZHBETMKYDBPJRPBDSH4O7Q","short_pith_number":"pith:MXUCZHBE","schema_version":"1.0","canonical_sha256":"65e82c9c249b158185e98bc2391f8efc337a5e73973a11fa44bb0cfc973e7e63","source":{"kind":"arxiv","id":"2505.24182","version":1},"attestation_state":"computed","paper":{"title":"Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Fangming Liu, Haochen Han, Junchao Yi, Linjie Li, Xiangxi Zheng, Zhuobai Dong, Ziyuan Zheng","submitted_at":"2025-05-30T03:48:59Z","abstract_excerpt":"Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While recent advances such as OpenAI o3 and GPT-4o demonstrate impressive perceptual and reasoning capabilities, our investigation reveals these models struggle profoundly with visual physical reasoning, failing to grasp basic physical laws, spatial interactions, and causal effects in complex scenes. More importantly, they often fail to follow coherent reasoning chains grounded in visual evidence, especially when multiple "},"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":"2505.24182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:48:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b53c3eb5b1560085b88934e0cbffacf9ef41d5b63c8067a862ad04ae4858257","abstract_canon_sha256":"08db21cac5ca8d45473385c7a927d3729ef814ac4a0492ef20290489d7b90209"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:43.699917Z","signature_b64":"z3LHqnfFevzl5kkFXeK5PzagBxfS7DbEcAhYzmy4lkqRFyuMPUtiHgOG4j0HA+IzCfjiewxwrBwR4/d9ZY+HCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65e82c9c249b158185e98bc2391f8efc337a5e73973a11fa44bb0cfc973e7e63","last_reissued_at":"2026-07-05T11:12:43.699343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:43.699343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Fangming Liu, Haochen Han, Junchao Yi, Linjie Li, Xiangxi Zheng, Zhuobai Dong, Ziyuan Zheng","submitted_at":"2025-05-30T03:48:59Z","abstract_excerpt":"Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While recent advances such as OpenAI o3 and GPT-4o demonstrate impressive perceptual and reasoning capabilities, our investigation reveals these models struggle profoundly with visual physical reasoning, failing to grasp basic physical laws, spatial interactions, and causal effects in complex scenes. More importantly, they often fail to follow coherent reasoning chains grounded in visual evidence, especially when multiple "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24182","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/2505.24182/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":"2505.24182","created_at":"2026-07-05T11:12:43.699410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24182v1","created_at":"2026-07-05T11:12:43.699410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24182","created_at":"2026-07-05T11:12:43.699410+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXUCZHBETMKY","created_at":"2026-07-05T11:12:43.699410+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXUCZHBETMKYDBPJ","created_at":"2026-07-05T11:12:43.699410+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXUCZHBE","created_at":"2026-07-05T11:12:43.699410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05966","citing_title":"Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06725","citing_title":"Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXUCZHBETMKYDBPJRPBDSH4O7Q","json":"https://pith.science/pith/MXUCZHBETMKYDBPJRPBDSH4O7Q.json","graph_json":"https://pith.science/api/pith-number/MXUCZHBETMKYDBPJRPBDSH4O7Q/graph.json","events_json":"https://pith.science/api/pith-number/MXUCZHBETMKYDBPJRPBDSH4O7Q/events.json","paper":"https://pith.science/paper/MXUCZHBE"},"agent_actions":{"view_html":"https://pith.science/pith/MXUCZHBETMKYDBPJRPBDSH4O7Q","download_json":"https://pith.science/pith/MXUCZHBETMKYDBPJRPBDSH4O7Q.json","view_paper":"https://pith.science/paper/MXUCZHBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24182&json=true","fetch_graph":"https://pith.science/api/pith-number/MXUCZHBETMKYDBPJRPBDSH4O7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/MXUCZHBETMKYDBPJRPBDSH4O7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXUCZHBETMKYDBPJRPBDSH4O7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXUCZHBETMKYDBPJRPBDSH4O7Q/action/storage_attestation","attest_author":"https://pith.science/pith/MXUCZHBETMKYDBPJRPBDSH4O7Q/action/author_attestation","sign_citation":"https://pith.science/pith/MXUCZHBETMKYDBPJRPBDSH4O7Q/action/citation_signature","submit_replication":"https://pith.science/pith/MXUCZHBETMKYDBPJRPBDSH4O7Q/action/replication_record"}},"created_at":"2026-07-05T11:12:43.699410+00:00","updated_at":"2026-07-05T11:12:43.699410+00:00"}