{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LSXX3IAQ4JEACBLARGK2ZWT274","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":"acd6e8fa4a1a3993ca48a4a89ae37dd0694676963cf57adbfce09c61d88ecbf1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T13:58:59Z","title_canon_sha256":"9e450f32002d08d607cf83195d06dca256676252bcf500a068b0eabac6a9ac58"},"schema_version":"1.0","source":{"id":"2311.05374","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05374","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05374v1","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05374","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"pith_short_12","alias_value":"LSXX3IAQ4JEA","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"pith_short_16","alias_value":"LSXX3IAQ4JEACBLA","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"pith_short_8","alias_value":"LSXX3IAQ","created_at":"2026-07-05T07:10:58Z"}],"graph_snapshots":[{"event_id":"sha256:8caf5c963ce1f1913e628a30ba17f571e88c1bd864a3239e6c4457ec8d683221","target":"graph","created_at":"2026-07-05T07:10:58Z","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/2311.05374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown impressive capabilities across various natural language tasks. However, evaluating their alignment with human preferences remains a challenge. To this end, we propose a comprehensive human evaluation framework to assess LLMs' proficiency in following instructions on diverse real-world tasks. We construct a hierarchical task tree encompassing 7 major areas covering over 200 categories and over 800 tasks, which covers diverse capabilities such as question answering, reasoning, multiturn dialogue, and text generation, to evaluate LLMs in a comprehensive and","authors_text":"Dong Yu, Donlin Zhou, Jing Nie, Lifeng Jin, Pengzhi Wei, Shaobo Wang, Shuyi Xie, Wenlin Yao, Xinhua Feng, Yong Dai, Yuhong Liu, Yujie Lin, Zhengyou Zhang, Zhichao Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T13:58:59Z","title":"TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05374","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":"sha256:6bdb19481e31b5327de9c7c4da33fbe5ac55063981db7ff92a0166b5cd116043","target":"record","created_at":"2026-07-05T07:10:58Z","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":"acd6e8fa4a1a3993ca48a4a89ae37dd0694676963cf57adbfce09c61d88ecbf1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T13:58:59Z","title_canon_sha256":"9e450f32002d08d607cf83195d06dca256676252bcf500a068b0eabac6a9ac58"},"schema_version":"1.0","source":{"id":"2311.05374","kind":"arxiv","version":1}},"canonical_sha256":"5caf7da010e2480105608995acda7aff3c9b4ed0bca933565cfce45cf14f17e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5caf7da010e2480105608995acda7aff3c9b4ed0bca933565cfce45cf14f17e8","first_computed_at":"2026-07-05T07:10:58.790383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:58.790383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6pSRNUf4tdtvxkGwFo0Fiy4ScXGdFVqrAaa0G1tzae8CjeEaz/9+9Z4CgMnkF2AUZrHAYrhUstOVLTceIdeFAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:58.790912Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05374","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bdb19481e31b5327de9c7c4da33fbe5ac55063981db7ff92a0166b5cd116043","sha256:8caf5c963ce1f1913e628a30ba17f571e88c1bd864a3239e6c4457ec8d683221"],"state_sha256":"b61463b6876ad3d5e714c9649b9273c79a5e4ce323188796691867b2f4791397"}