{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F4423YOS3L24GIOZ533RDXOYTA","short_pith_number":"pith:F4423YOS","schema_version":"1.0","canonical_sha256":"2f39ade1d2daf5c321d9eef711ddd89812e69cac7d4d06f95dd9f48753cc5437","source":{"kind":"arxiv","id":"2305.08322","version":3},"attestation_state":"computed","paper":{"title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuancheng Lv, Jiayi Lei, Jinghan Zhang, Junlei Zhang, Junteng Liu, Junxian He, Maosong Sun, Tangjun Su, Yao Fu, Yikai Zhang, Yuzhen Huang, Yuzhuo Bai, Zhihao Zhu","submitted_at":"2023-05-15T03:20:19Z","abstract_excerpt":"New NLP benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present C-Eval, the first comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. C-Eval comprises multiple-choice questions across four difficulty levels: middle school, high school, college, and professional. The questions span 52 diverse disciplines, ranging from humanities to science and engineering. C-Eval is accompanied by C-Eval Hard, a subset of very challenging subjects in C-Eval that requ"},"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":"2305.08322","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T03:20:19Z","cross_cats_sorted":[],"title_canon_sha256":"676084a077fbfccbcc5e62a6ff27547fd6588f7983fa52c55c302068a245008f","abstract_canon_sha256":"a6cb4ee2a6fbc20d41c651606220d0cf52440ab45d909d333f25973c0e4c9d88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:28.612973Z","signature_b64":"XfS+gDThJaMBLOtKWO54fhcihk5Q3yzrYj0Vy0lmC6NbUlvArMtkB/uEoup2mjnLUomJxoFojNBSUhXT/YJpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f39ade1d2daf5c321d9eef711ddd89812e69cac7d4d06f95dd9f48753cc5437","last_reissued_at":"2026-07-05T07:09:28.612484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:28.612484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuancheng Lv, Jiayi Lei, Jinghan Zhang, Junlei Zhang, Junteng Liu, Junxian He, Maosong Sun, Tangjun Su, Yao Fu, Yikai Zhang, Yuzhen Huang, Yuzhuo Bai, Zhihao Zhu","submitted_at":"2023-05-15T03:20:19Z","abstract_excerpt":"New NLP benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present C-Eval, the first comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. C-Eval comprises multiple-choice questions across four difficulty levels: middle school, high school, college, and professional. The questions span 52 diverse disciplines, ranging from humanities to science and engineering. C-Eval is accompanied by C-Eval Hard, a subset of very challenging subjects in C-Eval that requ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08322","kind":"arxiv","version":3},"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/2305.08322/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":"2305.08322","created_at":"2026-07-05T07:09:28.612537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08322v3","created_at":"2026-07-05T07:09:28.612537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08322","created_at":"2026-07-05T07:09:28.612537+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4423YOS3L24","created_at":"2026-07-05T07:09:28.612537+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4423YOS3L24GIOZ","created_at":"2026-07-05T07:09:28.612537+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4423YOS","created_at":"2026-07-05T07:09:28.612537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18216","citing_title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01279","citing_title":"ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2309.10305","citing_title":"Baichuan 2: Open Large-scale Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2409.06624","citing_title":"A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2410.14702","citing_title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08738","citing_title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2406.11931","citing_title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2403.17297","citing_title":"InternLM2 Technical Report","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2403.04652","citing_title":"Yi: Open Foundation Models by 01.AI","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11663","citing_title":"Human-Grounded Multimodal Benchmark with 900K-Scale Aggregated Student Response Distributions from Japan's National Assessment of Academic Ability","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08738","citing_title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2401.06066","citing_title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05940","citing_title":"Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20549","citing_title":"Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02954","citing_title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2405.04434","citing_title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2310.02255","citing_title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05688","citing_title":"Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2507.20534","citing_title":"Kimi K2: Open Agentic Intelligence","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4423YOS3L24GIOZ533RDXOYTA","json":"https://pith.science/pith/F4423YOS3L24GIOZ533RDXOYTA.json","graph_json":"https://pith.science/api/pith-number/F4423YOS3L24GIOZ533RDXOYTA/graph.json","events_json":"https://pith.science/api/pith-number/F4423YOS3L24GIOZ533RDXOYTA/events.json","paper":"https://pith.science/paper/F4423YOS"},"agent_actions":{"view_html":"https://pith.science/pith/F4423YOS3L24GIOZ533RDXOYTA","download_json":"https://pith.science/pith/F4423YOS3L24GIOZ533RDXOYTA.json","view_paper":"https://pith.science/paper/F4423YOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08322&json=true","fetch_graph":"https://pith.science/api/pith-number/F4423YOS3L24GIOZ533RDXOYTA/graph.json","fetch_events":"https://pith.science/api/pith-number/F4423YOS3L24GIOZ533RDXOYTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4423YOS3L24GIOZ533RDXOYTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4423YOS3L24GIOZ533RDXOYTA/action/storage_attestation","attest_author":"https://pith.science/pith/F4423YOS3L24GIOZ533RDXOYTA/action/author_attestation","sign_citation":"https://pith.science/pith/F4423YOS3L24GIOZ533RDXOYTA/action/citation_signature","submit_replication":"https://pith.science/pith/F4423YOS3L24GIOZ533RDXOYTA/action/replication_record"}},"created_at":"2026-07-05T07:09:28.612537+00:00","updated_at":"2026-07-05T07:09:28.612537+00:00"}