{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DSCWIYEFDQWJV6MYT7UDRCKN5M","short_pith_number":"pith:DSCWIYEF","schema_version":"1.0","canonical_sha256":"1c856460851c2c9af9989fe838894deb1804a2eb8821bf7134d4952f659b817b","source":{"kind":"arxiv","id":"2505.15929","version":2},"attestation_state":"computed","paper":{"title":"PhyX: Does Your Model Have the \"Wits\" for Physical Reasoning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chaofan Tao, Hui Shen, Jing Xiong, Jizhou Wang, Kai Zhang, Ngai Wong, Ping Luo, Qi Han, Taiqiang Wu, Wendong Xu, Wenhu Chen, Xin Wang, Yuansheng Ni, Yunta Hsieh, Yuxin Cheng, Yuyue Zhang, Zhongwei Wan, Zhuoqing Mao, Zijian Hao","submitted_at":"2025-05-21T18:33:50Z","abstract_excerpt":"Existing benchmarks fail to capture a crucial aspect of intelligence: physical reasoning, the integrated ability to combine domain knowledge, symbolic reasoning, and understanding of real-world constraints. To address this gap, we introduce PhyX: the first large-scale benchmark designed to assess models capacity for physics-grounded reasoning in visual scenarios. PhyX includes 3K meticulously curated multimodal questions spanning 6 reasoning types across 25 sub-domains and 6 core physics domains: thermodynamics, electromagnetism, mechanics, modern physics, optics, and wave\\&acoustics. In our c"},"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":"2505.15929","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T18:33:50Z","cross_cats_sorted":[],"title_canon_sha256":"8e07b07e54dbb6bb9001b5558b7db91c43e82d37a4a0002d1678db590e4f6dcb","abstract_canon_sha256":"3c9c555a7711ebe3845adae93de0dc7b22cbfc7e89953d542018469d0d9ee9d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:11.433187Z","signature_b64":"k9ykVVMg39pwpP+2yJBfne7xNEanA8Lr6cqky3yqrgsbpaMKn6OdOAWY8aYPPuPYuvehU40dLuuoGgv6xKL1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c856460851c2c9af9989fe838894deb1804a2eb8821bf7134d4952f659b817b","last_reissued_at":"2026-07-05T11:12:11.432693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:11.432693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhyX: Does Your Model Have the \"Wits\" for Physical Reasoning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chaofan Tao, Hui Shen, Jing Xiong, Jizhou Wang, Kai Zhang, Ngai Wong, Ping Luo, Qi Han, Taiqiang Wu, Wendong Xu, Wenhu Chen, Xin Wang, Yuansheng Ni, Yunta Hsieh, Yuxin Cheng, Yuyue Zhang, Zhongwei Wan, Zhuoqing Mao, Zijian Hao","submitted_at":"2025-05-21T18:33:50Z","abstract_excerpt":"Existing benchmarks fail to capture a crucial aspect of intelligence: physical reasoning, the integrated ability to combine domain knowledge, symbolic reasoning, and understanding of real-world constraints. To address this gap, we introduce PhyX: the first large-scale benchmark designed to assess models capacity for physics-grounded reasoning in visual scenarios. PhyX includes 3K meticulously curated multimodal questions spanning 6 reasoning types across 25 sub-domains and 6 core physics domains: thermodynamics, electromagnetism, mechanics, modern physics, optics, and wave\\&acoustics. In our c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15929","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/2505.15929/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":"2505.15929","created_at":"2026-07-05T11:12:11.432750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15929v2","created_at":"2026-07-05T11:12:11.432750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15929","created_at":"2026-07-05T11:12:11.432750+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSCWIYEFDQWJ","created_at":"2026-07-05T11:12:11.432750+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSCWIYEFDQWJV6MY","created_at":"2026-07-05T11:12:11.432750+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSCWIYEF","created_at":"2026-07-05T11:12:11.432750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00248","citing_title":"Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13294","citing_title":"VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02311","citing_title":"Inferring Dynamic Physical Properties from Video Foundation Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.18472","citing_title":"Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02934","citing_title":"PolyReal: A Benchmark for Real-World Polymer Science Workflows","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03893","citing_title":"FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09266","citing_title":"SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09266","citing_title":"SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10219","citing_title":"Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09415","citing_title":"PhysInOne: Visual Physics Learning and Reasoning in One Suite","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14888","citing_title":"Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSCWIYEFDQWJV6MYT7UDRCKN5M","json":"https://pith.science/pith/DSCWIYEFDQWJV6MYT7UDRCKN5M.json","graph_json":"https://pith.science/api/pith-number/DSCWIYEFDQWJV6MYT7UDRCKN5M/graph.json","events_json":"https://pith.science/api/pith-number/DSCWIYEFDQWJV6MYT7UDRCKN5M/events.json","paper":"https://pith.science/paper/DSCWIYEF"},"agent_actions":{"view_html":"https://pith.science/pith/DSCWIYEFDQWJV6MYT7UDRCKN5M","download_json":"https://pith.science/pith/DSCWIYEFDQWJV6MYT7UDRCKN5M.json","view_paper":"https://pith.science/paper/DSCWIYEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15929&json=true","fetch_graph":"https://pith.science/api/pith-number/DSCWIYEFDQWJV6MYT7UDRCKN5M/graph.json","fetch_events":"https://pith.science/api/pith-number/DSCWIYEFDQWJV6MYT7UDRCKN5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSCWIYEFDQWJV6MYT7UDRCKN5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSCWIYEFDQWJV6MYT7UDRCKN5M/action/storage_attestation","attest_author":"https://pith.science/pith/DSCWIYEFDQWJV6MYT7UDRCKN5M/action/author_attestation","sign_citation":"https://pith.science/pith/DSCWIYEFDQWJV6MYT7UDRCKN5M/action/citation_signature","submit_replication":"https://pith.science/pith/DSCWIYEFDQWJV6MYT7UDRCKN5M/action/replication_record"}},"created_at":"2026-07-05T11:12:11.432750+00:00","updated_at":"2026-07-05T11:12:11.432750+00:00"}