{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IWXQGJHDXIGAF2J34XNTCFGTKX","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":"54691bf0e0526bac2c42c2009fb35df58a340406180dd39e43186e58b1d5db6d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T17:24:09Z","title_canon_sha256":"9f0754e3955f46d22c1ed1a8ab66c7d01d90aa446e753fa0196ada8b4aa1d964"},"schema_version":"1.0","source":{"id":"2307.15020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15020","created_at":"2026-07-05T06:35:20Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15020v1","created_at":"2026-07-05T06:35:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15020","created_at":"2026-07-05T06:35:20Z"},{"alias_kind":"pith_short_12","alias_value":"IWXQGJHDXIGA","created_at":"2026-07-05T06:35:20Z"},{"alias_kind":"pith_short_16","alias_value":"IWXQGJHDXIGAF2J3","created_at":"2026-07-05T06:35:20Z"},{"alias_kind":"pith_short_8","alias_value":"IWXQGJHD","created_at":"2026-07-05T06:35:20Z"}],"graph_snapshots":[{"event_id":"sha256:67b784ba5e696c1849d7f395d5bacf724056da62ab2ebb3d3bc824b78d8b07e6","target":"graph","created_at":"2026-07-05T06:35:20Z","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/2307.15020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown the potential to be integrated into human daily lives. Therefore, user preference is the most critical criterion for assessing LLMs' performance in real-world scenarios. However, existing benchmarks mainly focus on measuring models' accuracy using multi-choice questions, which limits the understanding of their capabilities in real applications. We fill this gap by proposing a comprehensive Chinese benchmark SuperCLUE, named after another popular Chinese LLM benchmark CLUE. SuperCLUE encompasses three sub-tasks: actual users' queries and ratings derived f","authors_text":"Anqi Li, Changtai Zhu, Hang Xue, Haonan He, Kangkang Zhao, Lei Zhu, Liang Xu, Qiyue Kang, Xuanwei Zhang, Zhenzhong Lan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T17:24:09Z","title":"SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15020","kind":"arxiv","version":1},"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:f8965f2362560e86ba022cbfb07f88b5b5eb2b01d7bf9b202ad9955588683e53","target":"record","created_at":"2026-07-05T06:35:20Z","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":"54691bf0e0526bac2c42c2009fb35df58a340406180dd39e43186e58b1d5db6d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T17:24:09Z","title_canon_sha256":"9f0754e3955f46d22c1ed1a8ab66c7d01d90aa446e753fa0196ada8b4aa1d964"},"schema_version":"1.0","source":{"id":"2307.15020","kind":"arxiv","version":1}},"canonical_sha256":"45af0324e3ba0c02e93be5db3114d355e58606300f434a761fecffc5a454ae06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45af0324e3ba0c02e93be5db3114d355e58606300f434a761fecffc5a454ae06","first_computed_at":"2026-07-05T06:35:20.923376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:20.923376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tkmVlCMHqJx3XNRHEHmxE3zOVWwk1VZqYve2Jgzaq3WmKgrpNAoSXHEpm0uCY9nOXcub7a7gwYzHj5c/LPHFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:20.923887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8965f2362560e86ba022cbfb07f88b5b5eb2b01d7bf9b202ad9955588683e53","sha256:67b784ba5e696c1849d7f395d5bacf724056da62ab2ebb3d3bc824b78d8b07e6"],"state_sha256":"603b10b5335ab99203de2c59be24fcd37235007d6c4cc112c334c2364d6cdef5"}