{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IGJZX2CNNVKFEHYQ53EYJCIZKT","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":"6c9ddf7d979078ddf49ddcecd96947fcc7a4a79b016a7817c342634f5ec948b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T07:43:43Z","title_canon_sha256":"cce4cd9fddcf2cd9c12b2b2e5aa9617e9d4476b3bb97da5895b50006095aded0"},"schema_version":"1.0","source":{"id":"2403.03514","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03514","created_at":"2026-07-05T09:21:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03514v2","created_at":"2026-07-05T09:21:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03514","created_at":"2026-07-05T09:21:02Z"},{"alias_kind":"pith_short_12","alias_value":"IGJZX2CNNVKF","created_at":"2026-07-05T09:21:02Z"},{"alias_kind":"pith_short_16","alias_value":"IGJZX2CNNVKFEHYQ","created_at":"2026-07-05T09:21:02Z"},{"alias_kind":"pith_short_8","alias_value":"IGJZX2CN","created_at":"2026-07-05T09:21:02Z"}],"graph_snapshots":[{"event_id":"sha256:bf1289b39f27527d138285635f6a4956d385607d1a2b6b0a9c4bed8cc8f70c4e","target":"graph","created_at":"2026-07-05T09:21:02Z","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/2403.03514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing Large Language Models (LLMs) with robust long-context capabilities has been the recent research focus, resulting in the emergence of long-context LLMs proficient in Chinese. However, the evaluation of these models remains underdeveloped due to a lack of benchmarks. To address this gap, we present CLongEval, a comprehensive Chinese benchmark for evaluating long-context LLMs. CLongEval is characterized by three key features: (1) Sufficient data volume, comprising 7 distinct tasks and 7,267 examples; (2) Broad applicability, accommodating to models with context windows size from 1K to ","authors_text":"Irwin King, Jingjing Li, Shijue Huang, Wanjun Zhong, Xiaoqi Jiao, Zexuan Qiu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T07:43:43Z","title":"CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03514","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":"sha256:0b6e64bc17e83b21fb5e31c63c22e9b3ad3b07f48a49a6c2af411465673bb927","target":"record","created_at":"2026-07-05T09:21:02Z","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":"6c9ddf7d979078ddf49ddcecd96947fcc7a4a79b016a7817c342634f5ec948b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T07:43:43Z","title_canon_sha256":"cce4cd9fddcf2cd9c12b2b2e5aa9617e9d4476b3bb97da5895b50006095aded0"},"schema_version":"1.0","source":{"id":"2403.03514","kind":"arxiv","version":2}},"canonical_sha256":"41939be84d6d54521f10eec984891954dc713aee22c6db00a5a508fb76a94a67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41939be84d6d54521f10eec984891954dc713aee22c6db00a5a508fb76a94a67","first_computed_at":"2026-07-05T09:21:02.969785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:02.969785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TkoYphiI04IgicC2DadeZsj8HB+GpXK1CGdInjwLKv5BSHIR5LUsZ4XDOqaboXZz1HWjT9Lw8SwSgh9Uj8MnCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:02.970368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03514","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b6e64bc17e83b21fb5e31c63c22e9b3ad3b07f48a49a6c2af411465673bb927","sha256:bf1289b39f27527d138285635f6a4956d385607d1a2b6b0a9c4bed8cc8f70c4e"],"state_sha256":"f4d0522c47dd0bf3d41761d8d4169a866f0967a1e650ff421cbfbf0f9127a603"}