{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GG6AE2MEC4IAZH5YOB7IXE43EU","short_pith_number":"pith:GG6AE2ME","schema_version":"1.0","canonical_sha256":"31bc02698417100c9fb8707e8b939b2501164c94f62c8b43f5ef71d182e955cf","source":{"kind":"arxiv","id":"2606.07962","version":1},"attestation_state":"computed","paper":{"title":"ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Zhu, Hao Li, Huangchong Yan, Jie Wang, Kexin Zhao, Li Yuan, Mingjun Pan, Munan Ning, Qishen Yin, Shuai Zhao, Tanqing Sun, Xinyi Wu, Yanhao Jia, Yunyang Ge, Yuwei Niu","submitted_at":"2026-06-06T03:40:47Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in open-world reasoning and understanding. However, a critical ambiguity persists: it remains unclear whether these models genuinely synthesize cross-modal information to construct physically grounded reasoning chains, or if they merely exploit strong language priors to mask single-modality reliance, thereby hallucinating advanced multimodal capabilities. Motivated by this, and to rigorously mitigate language modality bias and shortcuts, we propose a novel multimodal Chrono}logical Physical"},"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":"2606.07962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T03:40:47Z","cross_cats_sorted":[],"title_canon_sha256":"93c2ff38ed402aa178fc187071442e6d49558b47ea3833f820f6dd557b239f37","abstract_canon_sha256":"c7a57e638877009d7b6c480adb0a3733dce02c6fb86d7d76e202ae8664506bf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:56.574231Z","signature_b64":"xiRh9QcPj2WJVRIJLVQl4FSVsCHcgJaLpQVKo6GWJzxbmsxkl0us/jkR2dBpuXrdJBN2n9JLUgfSmXaoABuOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31bc02698417100c9fb8707e8b939b2501164c94f62c8b43f5ef71d182e955cf","last_reissued_at":"2026-06-09T01:04:56.573813Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:56.573813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Zhu, Hao Li, Huangchong Yan, Jie Wang, Kexin Zhao, Li Yuan, Mingjun Pan, Munan Ning, Qishen Yin, Shuai Zhao, Tanqing Sun, Xinyi Wu, Yanhao Jia, Yunyang Ge, Yuwei Niu","submitted_at":"2026-06-06T03:40:47Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in open-world reasoning and understanding. However, a critical ambiguity persists: it remains unclear whether these models genuinely synthesize cross-modal information to construct physically grounded reasoning chains, or if they merely exploit strong language priors to mask single-modality reliance, thereby hallucinating advanced multimodal capabilities. Motivated by this, and to rigorously mitigate language modality bias and shortcuts, we propose a novel multimodal Chrono}logical Physical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07962","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/2606.07962/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":"2606.07962","created_at":"2026-06-09T01:04:56.573878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07962v1","created_at":"2026-06-09T01:04:56.573878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07962","created_at":"2026-06-09T01:04:56.573878+00:00"},{"alias_kind":"pith_short_12","alias_value":"GG6AE2MEC4IA","created_at":"2026-06-09T01:04:56.573878+00:00"},{"alias_kind":"pith_short_16","alias_value":"GG6AE2MEC4IAZH5Y","created_at":"2026-06-09T01:04:56.573878+00:00"},{"alias_kind":"pith_short_8","alias_value":"GG6AE2ME","created_at":"2026-06-09T01:04:56.573878+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/GG6AE2MEC4IAZH5YOB7IXE43EU","json":"https://pith.science/pith/GG6AE2MEC4IAZH5YOB7IXE43EU.json","graph_json":"https://pith.science/api/pith-number/GG6AE2MEC4IAZH5YOB7IXE43EU/graph.json","events_json":"https://pith.science/api/pith-number/GG6AE2MEC4IAZH5YOB7IXE43EU/events.json","paper":"https://pith.science/paper/GG6AE2ME"},"agent_actions":{"view_html":"https://pith.science/pith/GG6AE2MEC4IAZH5YOB7IXE43EU","download_json":"https://pith.science/pith/GG6AE2MEC4IAZH5YOB7IXE43EU.json","view_paper":"https://pith.science/paper/GG6AE2ME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07962&json=true","fetch_graph":"https://pith.science/api/pith-number/GG6AE2MEC4IAZH5YOB7IXE43EU/graph.json","fetch_events":"https://pith.science/api/pith-number/GG6AE2MEC4IAZH5YOB7IXE43EU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GG6AE2MEC4IAZH5YOB7IXE43EU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GG6AE2MEC4IAZH5YOB7IXE43EU/action/storage_attestation","attest_author":"https://pith.science/pith/GG6AE2MEC4IAZH5YOB7IXE43EU/action/author_attestation","sign_citation":"https://pith.science/pith/GG6AE2MEC4IAZH5YOB7IXE43EU/action/citation_signature","submit_replication":"https://pith.science/pith/GG6AE2MEC4IAZH5YOB7IXE43EU/action/replication_record"}},"created_at":"2026-06-09T01:04:56.573878+00:00","updated_at":"2026-06-09T01:04:56.573878+00:00"}