{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:W6ZPZWXE6A7R54UXQV6KHQ2UX4","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":"c827e9e1b93ecae50c1098367b5ac4b5001a9702f9d8e265cb09c88954b28893","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T14:56:31Z","title_canon_sha256":"544a9012dcac68fb57ff47e27c9911300f422a37461d91eba027103558480988"},"schema_version":"1.0","source":{"id":"2305.10263","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10263","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10263v2","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10263","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"pith_short_12","alias_value":"W6ZPZWXE6A7R","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"pith_short_16","alias_value":"W6ZPZWXE6A7R54UX","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"pith_short_8","alias_value":"W6ZPZWXE","created_at":"2026-07-05T06:12:03Z"}],"graph_snapshots":[{"event_id":"sha256:1b0a6d2a1fb9f66a2fc9aa711ba48a986776556ca69a714d381ebbc6fdeebc34","target":"graph","created_at":"2026-07-05T06:12:03Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.10263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have recently made tremendous progress in a variety of aspects, e.g., cross-task generalization, instruction following. Comprehensively evaluating the capability of large language models in multiple tasks is of great importance. In this paper, we propose M3KE, a Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark, which is developed to measure knowledge acquired by Chinese large language models by testing their multitask accuracy in zero- and few-shot settings. We have collected 20,477 questions from 71 tasks. Our selection covers all major levels of Chinese ","authors_text":"Chuang Liu, Deyi Xiong, Jianxiang Peng, Linhao Yu, Peiyi Zhang, Qingqing Lyu, Qun Liu, Renren Jin, Shuting Zhang, Tianyu Dong, Xiaohan Peng, Xiaowen Su, Yuqi Ren","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T14:56:31Z","title":"M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10263","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6dc039c3bf85e5f80b4beeb603acce8413132e3719e4c922f506ac704c84ef78","target":"record","created_at":"2026-07-05T06:12:03Z","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":"c827e9e1b93ecae50c1098367b5ac4b5001a9702f9d8e265cb09c88954b28893","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T14:56:31Z","title_canon_sha256":"544a9012dcac68fb57ff47e27c9911300f422a37461d91eba027103558480988"},"schema_version":"1.0","source":{"id":"2305.10263","kind":"arxiv","version":2}},"canonical_sha256":"b7b2fcdae4f03f1ef297857ca3c354bf350c6eb4fe53060e1bb609b68ee8ce1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7b2fcdae4f03f1ef297857ca3c354bf350c6eb4fe53060e1bb609b68ee8ce1e","first_computed_at":"2026-07-05T06:12:03.237757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:03.237757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lwsfOAerZ23q7fqIwOgRX7s86Fd66reK16K3IIavNt2h/meiHu60VyVD2w8Bus6OM4hpcRPo/g3QeP8uWmX4Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:03.238144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10263","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6dc039c3bf85e5f80b4beeb603acce8413132e3719e4c922f506ac704c84ef78","sha256:1b0a6d2a1fb9f66a2fc9aa711ba48a986776556ca69a714d381ebbc6fdeebc34"],"state_sha256":"5518ac2e0c350e5b403ef440290983df5b19cc46f5b0e4786b04f27cf2134576"}