{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AY7B3MSLIICKEHJXAFZ7D62B7J","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d9c30447ea56c65bd128e617eaa5ad9b4e951a27c9baad2ab43a562a40a37796","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T15:49:51Z","title_canon_sha256":"85638d27497b05a8b6e6cfc2333eaaca9948e66c407771973cfd620a8c90441e"},"schema_version":"1.0","source":{"id":"2306.09212","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09212","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09212v2","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09212","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"AY7B3MSLIICK","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"AY7B3MSLIICKEHJX","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"AY7B3MSL","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:a4b3b9cc52e517db137e843ceddeed259f284b6a85329458d79ef4549a4d0970","target":"graph","created_at":"2026-05-17T23:38:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"most existing LLMs struggle to achieve an average accuracy of 50%, even when provided with in-context examples and chain-of-thought prompts, whereas the random baseline stands at 25%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The questions in CMMLU accurately represent the knowledge and reasoning demands of real Chinese-language tasks across the covered subjects."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CMMLU benchmark shows most advanced LLMs score below 50% accuracy on Chinese multitask understanding, well above the 25% random baseline but revealing major room for improvement."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Most large language models score below 50 percent on a new Chinese multitask understanding benchmark."}],"snapshot_sha256":"afd9388db84a4af3ea61c6f5c90367cea2a2ecbba52536f98631f829755bf1fe"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9600d38a99db9286fc9a63dad72fb1478b226bdd6e157f3b3acdfdb5cd52bdde"},"paper":{"abstract_excerpt":"As the capabilities of large language models (LLMs) continue to advance, evaluating their performance becomes increasingly crucial and challenging. This paper aims to bridge this gap by introducing CMMLU, a comprehensive Chinese benchmark that covers various subjects, including natural science, social sciences, engineering, and humanities. We conduct a thorough evaluation of 18 advanced multilingual- and Chinese-oriented LLMs, assessing their performance across different subjects and settings. The results reveal that most existing LLMs struggle to achieve an average accuracy of 50%, even when ","authors_text":"Fajri Koto, Hai Zhao, Haonan Li, Nan Duan, Timothy Baldwin, Yeyun Gong, Yifei Yang, Yixuan Zhang","cross_cats":[],"headline":"Most large language models score below 50 percent on a new Chinese multitask understanding benchmark.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T15:49:51Z","title":"CMMLU: Measuring massive multitask language understanding in Chinese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09212","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T20:58:16.649845Z","id":"7e67a584-1eaf-49f9-b182-dc341b1f0120","model_set":{"reader":"grok-4.3"},"one_line_summary":"CMMLU benchmark shows most advanced LLMs score below 50% accuracy on Chinese multitask understanding, well above the 25% random baseline but revealing major room for improvement.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Most large language models score below 50 percent on a new Chinese multitask understanding benchmark.","strongest_claim":"most existing LLMs struggle to achieve an average accuracy of 50%, even when provided with in-context examples and chain-of-thought prompts, whereas the random baseline stands at 25%.","weakest_assumption":"The questions in CMMLU accurately represent the knowledge and reasoning demands of real Chinese-language tasks across the covered subjects."}},"verdict_id":"7e67a584-1eaf-49f9-b182-dc341b1f0120"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5aadda9c414455872ebcbc19c0e7560bb40567ad3373ded447219ca8a824ab9a","target":"record","created_at":"2026-05-17T23:38:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d9c30447ea56c65bd128e617eaa5ad9b4e951a27c9baad2ab43a562a40a37796","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T15:49:51Z","title_canon_sha256":"85638d27497b05a8b6e6cfc2333eaaca9948e66c407771973cfd620a8c90441e"},"schema_version":"1.0","source":{"id":"2306.09212","kind":"arxiv","version":2}},"canonical_sha256":"063e1db24b4204a21d370173f1fb41fa4a41edf019b497bd0f153385a2b3ba48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"063e1db24b4204a21d370173f1fb41fa4a41edf019b497bd0f153385a2b3ba48","first_computed_at":"2026-05-17T23:38:46.587873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.587873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k66DnZfs4bEnjYNQjeBZetig6fSkrRdVvjGp4NKFXffYv0dA5oS/kBtsQijvM9Lb60FaetuDx+juPyNngLB1DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.588295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09212","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5aadda9c414455872ebcbc19c0e7560bb40567ad3373ded447219ca8a824ab9a","sha256:a4b3b9cc52e517db137e843ceddeed259f284b6a85329458d79ef4549a4d0970"],"state_sha256":"ee81be8248b48310e53b282667a07c9cd25fd9e79bc3b636c262fb49e597caf2"}