{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IWXQGJHDXIGAF2J34XNTCFGTKX","short_pith_number":"pith:IWXQGJHD","schema_version":"1.0","canonical_sha256":"45af0324e3ba0c02e93be5db3114d355e58606300f434a761fecffc5a454ae06","source":{"kind":"arxiv","id":"2307.15020","version":1},"attestation_state":"computed","paper":{"title":"SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anqi Li, Changtai Zhu, Hang Xue, Haonan He, Kangkang Zhao, Lei Zhu, Liang Xu, Qiyue Kang, Xuanwei Zhang, Zhenzhong Lan","submitted_at":"2023-07-27T17:24:09Z","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"},"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":"2307.15020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-27T17:24:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f0754e3955f46d22c1ed1a8ab66c7d01d90aa446e753fa0196ada8b4aa1d964","abstract_canon_sha256":"54691bf0e0526bac2c42c2009fb35df58a340406180dd39e43186e58b1d5db6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:20.923887Z","signature_b64":"tkmVlCMHqJx3XNRHEHmxE3zOVWwk1VZqYve2Jgzaq3WmKgrpNAoSXHEpm0uCY9nOXcub7a7gwYzHj5c/LPHFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45af0324e3ba0c02e93be5db3114d355e58606300f434a761fecffc5a454ae06","last_reissued_at":"2026-07-05T06:35:20.923376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:20.923376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anqi Li, Changtai Zhu, Hang Xue, Haonan He, Kangkang Zhao, Lei Zhu, Liang Xu, Qiyue Kang, Xuanwei Zhang, Zhenzhong Lan","submitted_at":"2023-07-27T17:24:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15020","kind":"arxiv","version":1},"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/2307.15020/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":"2307.15020","created_at":"2026-07-05T06:35:20.923437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15020v1","created_at":"2026-07-05T06:35:20.923437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15020","created_at":"2026-07-05T06:35:20.923437+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWXQGJHDXIGA","created_at":"2026-07-05T06:35:20.923437+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWXQGJHDXIGAF2J3","created_at":"2026-07-05T06:35:20.923437+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWXQGJHD","created_at":"2026-07-05T06:35:20.923437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23825","citing_title":"It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amplified by the language of the prompt","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15947","citing_title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08904","citing_title":"OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":222,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IWXQGJHDXIGAF2J34XNTCFGTKX","json":"https://pith.science/pith/IWXQGJHDXIGAF2J34XNTCFGTKX.json","graph_json":"https://pith.science/api/pith-number/IWXQGJHDXIGAF2J34XNTCFGTKX/graph.json","events_json":"https://pith.science/api/pith-number/IWXQGJHDXIGAF2J34XNTCFGTKX/events.json","paper":"https://pith.science/paper/IWXQGJHD"},"agent_actions":{"view_html":"https://pith.science/pith/IWXQGJHDXIGAF2J34XNTCFGTKX","download_json":"https://pith.science/pith/IWXQGJHDXIGAF2J34XNTCFGTKX.json","view_paper":"https://pith.science/paper/IWXQGJHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15020&json=true","fetch_graph":"https://pith.science/api/pith-number/IWXQGJHDXIGAF2J34XNTCFGTKX/graph.json","fetch_events":"https://pith.science/api/pith-number/IWXQGJHDXIGAF2J34XNTCFGTKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWXQGJHDXIGAF2J34XNTCFGTKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWXQGJHDXIGAF2J34XNTCFGTKX/action/storage_attestation","attest_author":"https://pith.science/pith/IWXQGJHDXIGAF2J34XNTCFGTKX/action/author_attestation","sign_citation":"https://pith.science/pith/IWXQGJHDXIGAF2J34XNTCFGTKX/action/citation_signature","submit_replication":"https://pith.science/pith/IWXQGJHDXIGAF2J34XNTCFGTKX/action/replication_record"}},"created_at":"2026-07-05T06:35:20.923437+00:00","updated_at":"2026-07-05T06:35:20.923437+00:00"}