{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:75NPDY7HV6BL5ISAY2JFI3U467","short_pith_number":"pith:75NPDY7H","schema_version":"1.0","canonical_sha256":"ff5af1e3e7af82bea240c692546e9cf7e8c593ac11df2cc23f5e64f66e8096dc","source":{"kind":"arxiv","id":"2401.11944","version":4},"attestation_state":"computed","paper":{"title":"CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Bei Chen, Chenghua Lin, Chunpu Xu, Fengji Zhang, Ge Zhang, Haoran Zhang, Jie Fu, Junjie Wang, Kang Zhu, Ruibin Yuan, Shuyue Guo, Tianyu Zheng, Tongxu Luo, Wenhao Huang, Xingwei Qu, Xinrun Du, Yiming Liang, Yizhi Li, Yudong Liu, Yu-Hsuan Tsai, Yuyang Cheng, Zekun Wang","submitted_at":"2024-01-22T13:34:34Z","abstract_excerpt":"As the capabilities of large multimodal models (LMMs) continue to advance, evaluating the performance of LMMs emerges as an increasing need. Additionally, there is an even larger gap in evaluating the advanced knowledge and reasoning abilities of LMMs in non-English contexts such as Chinese. We introduce CMMMU, a new Chinese Massive Multi-discipline Multimodal Understanding benchmark designed to evaluate LMMs on tasks demanding college-level subject knowledge and deliberate reasoning in a Chinese context. CMMMU is inspired by and strictly follows the annotation and analysis pattern of MMMU. CM"},"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":"2401.11944","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T13:34:34Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"79c1917b85131ee86ead3dac242a652681d7f671a385fcde16ca50cd9d10ee0f","abstract_canon_sha256":"0e33069456baaf2ba6592283ad1544c76c6446028b59fa8e61578ff6cba32ed3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:06.520873Z","signature_b64":"ti3maLQkDG7b9B828/re4xWXFo/uWRuWB6Ix0V2ghrPdM+BwU7RniQ6PsjY7TDNa2oFeIYV0zTTLSDztZ7kyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff5af1e3e7af82bea240c692546e9cf7e8c593ac11df2cc23f5e64f66e8096dc","last_reissued_at":"2026-07-05T09:30:06.520371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:06.520371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Bei Chen, Chenghua Lin, Chunpu Xu, Fengji Zhang, Ge Zhang, Haoran Zhang, Jie Fu, Junjie Wang, Kang Zhu, Ruibin Yuan, Shuyue Guo, Tianyu Zheng, Tongxu Luo, Wenhao Huang, Xingwei Qu, Xinrun Du, Yiming Liang, Yizhi Li, Yudong Liu, Yu-Hsuan Tsai, Yuyang Cheng, Zekun Wang","submitted_at":"2024-01-22T13:34:34Z","abstract_excerpt":"As the capabilities of large multimodal models (LMMs) continue to advance, evaluating the performance of LMMs emerges as an increasing need. Additionally, there is an even larger gap in evaluating the advanced knowledge and reasoning abilities of LMMs in non-English contexts such as Chinese. We introduce CMMMU, a new Chinese Massive Multi-discipline Multimodal Understanding benchmark designed to evaluate LMMs on tasks demanding college-level subject knowledge and deliberate reasoning in a Chinese context. CMMMU is inspired by and strictly follows the annotation and analysis pattern of MMMU. CM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11944","kind":"arxiv","version":4},"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/2401.11944/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":"2401.11944","created_at":"2026-07-05T09:30:06.520435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11944v4","created_at":"2026-07-05T09:30:06.520435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11944","created_at":"2026-07-05T09:30:06.520435+00:00"},{"alias_kind":"pith_short_12","alias_value":"75NPDY7HV6BL","created_at":"2026-07-05T09:30:06.520435+00:00"},{"alias_kind":"pith_short_16","alias_value":"75NPDY7HV6BL5ISA","created_at":"2026-07-05T09:30:06.520435+00:00"},{"alias_kind":"pith_short_8","alias_value":"75NPDY7H","created_at":"2026-07-05T09:30:06.520435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":247,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17283","citing_title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00321","citing_title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2403.05525","citing_title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09907","citing_title":"From UAV Imagery to Agronomic Reasoning: A Multimodal LLM Benchmark for Plant Phenotyping","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75NPDY7HV6BL5ISAY2JFI3U467","json":"https://pith.science/pith/75NPDY7HV6BL5ISAY2JFI3U467.json","graph_json":"https://pith.science/api/pith-number/75NPDY7HV6BL5ISAY2JFI3U467/graph.json","events_json":"https://pith.science/api/pith-number/75NPDY7HV6BL5ISAY2JFI3U467/events.json","paper":"https://pith.science/paper/75NPDY7H"},"agent_actions":{"view_html":"https://pith.science/pith/75NPDY7HV6BL5ISAY2JFI3U467","download_json":"https://pith.science/pith/75NPDY7HV6BL5ISAY2JFI3U467.json","view_paper":"https://pith.science/paper/75NPDY7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11944&json=true","fetch_graph":"https://pith.science/api/pith-number/75NPDY7HV6BL5ISAY2JFI3U467/graph.json","fetch_events":"https://pith.science/api/pith-number/75NPDY7HV6BL5ISAY2JFI3U467/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75NPDY7HV6BL5ISAY2JFI3U467/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75NPDY7HV6BL5ISAY2JFI3U467/action/storage_attestation","attest_author":"https://pith.science/pith/75NPDY7HV6BL5ISAY2JFI3U467/action/author_attestation","sign_citation":"https://pith.science/pith/75NPDY7HV6BL5ISAY2JFI3U467/action/citation_signature","submit_replication":"https://pith.science/pith/75NPDY7HV6BL5ISAY2JFI3U467/action/replication_record"}},"created_at":"2026-07-05T09:30:06.520435+00:00","updated_at":"2026-07-05T09:30:06.520435+00:00"}