{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WAC67T2T2D4KOLLIFS2JA6AU3C","short_pith_number":"pith:WAC67T2T","schema_version":"1.0","canonical_sha256":"b005efcf53d0f8a72d682cb4907814d89aa739c070822675ec531445a98cb7b6","source":{"kind":"arxiv","id":"2411.02265","version":3},"attestation_state":"computed","paper":{"title":"Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ao Liu, Bin Hu, Bo Wang, Chao Yu, Chenchen Zhang, Chengcheng Xu, Chengzhong Xu, Chongqing Zhao, Chong Zha, Decheng Wu, Dengpeng Wu, Dian Jiao, Di Wang, Dong Du, Fan Jiang, Feifei Liu, Feng Zhang, Fengzong Lian, Fusheng Xiang, Guanghui Xu, Guiyang Li, Hai Wang, Han Liu, Hao Fei, Hao Gong, Hu Chen, Huilin Xu, Jiahao Bu, Jiajia Wu, Jianchen Zhu, Jianfeng Yan, Jianglu Hu, Jianqiang Ma, Jiaqi Zhu, Jiawei Song, Jie Jiang, Jie Liu, Jinbao Xue, Jonny Han, Junqiang Zheng, Jun Xia, Kai Liu, Kai Zhang, Kan Wu, Lei Jiang, Liang Dong, Lulu Wu, Meng Chen, Mengyuan Huang, Peijie Yu, Qian Wang, Roberts Wang, Rong Gan, Rongpeng Chen, Ruibin Chen, Rui Yuan, Ruobing Xie, Saiyong Yang, Shaohua Chen, Shihui Hu, Shuaipeng Li, Shuang Chen, Suncong Zheng, Tao Yang, Tengfei Cao, Tinghao Yu, Weichao Wang, Weijie Liu, Weiwen Jia, Wen Ouyang, Winston Hu, Xiang Li, Xiaobo Shu, Xiao Feng, Xiaoqin Ren, Xingwu Sun, Xinhua Feng, Xiong Kuang, Xipeng Zhang, Xirui Li, Xuebin Hou, Xuemeng Huang, Xun Cao, Yanfeng Chen, Yangyu Tao, Yao Ding, Yaping Deng, Yigeng Hong, Yinben Xia, Yiqi Chen, Yiqing Huang, Yi Shen, Yong Yang, Yuchi Deng, Yue Mao, Yuhong Liu, Yuyuan Zeng, Zekun He, Ze Zhao, Zhanhui Kang, Zhenxiang Yan, Zhen Yang, Zhichao Hu, Zhiyuan Xiong, Zhongzhi Chen, Zifan Wu, Zilong Zhao, Zongwei Li","submitted_at":"2024-11-04T16:56:26Z","abstract_excerpt":"In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens. We conduct a thorough evaluation of Hunyuan-Large's superior performance across various benchmarks including language understanding and generation, logical reasoning, mathematical problem-solving, coding, long-context, and aggregated tasks, where it outperforms LLama3.1-70B and exhibits comparable performance when compared to the significantly larger L"},"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":"2411.02265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T16:56:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"92433959642ede7e49f07d01133c133f706e636c01554d17eaaa1234e5541957","abstract_canon_sha256":"0557ef470e8bc64294d621d5e4bdfda77f45037c6b0c5e4f236f28e48f4f05d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:51.659720Z","signature_b64":"V4hIkfGnfoRZUzqKOJ1rbnnaOtHNONknNMXTkWTIqP53p0wet0s7JZ21Azf9O7Xyav4BbrR9lOkSvJjYnCtjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b005efcf53d0f8a72d682cb4907814d89aa739c070822675ec531445a98cb7b6","last_reissued_at":"2026-07-05T09:31:51.659199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:51.659199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ao Liu, Bin Hu, Bo Wang, Chao Yu, Chenchen Zhang, Chengcheng Xu, Chengzhong Xu, Chongqing Zhao, Chong Zha, Decheng Wu, Dengpeng Wu, Dian Jiao, Di Wang, Dong Du, Fan Jiang, Feifei Liu, Feng Zhang, Fengzong Lian, Fusheng Xiang, Guanghui Xu, Guiyang Li, Hai Wang, Han Liu, Hao Fei, Hao Gong, Hu Chen, Huilin Xu, Jiahao Bu, Jiajia Wu, Jianchen Zhu, Jianfeng Yan, Jianglu Hu, Jianqiang Ma, Jiaqi Zhu, Jiawei Song, Jie Jiang, Jie Liu, Jinbao Xue, Jonny Han, Junqiang Zheng, Jun Xia, Kai Liu, Kai Zhang, Kan Wu, Lei Jiang, Liang Dong, Lulu Wu, Meng Chen, Mengyuan Huang, Peijie Yu, Qian Wang, Roberts Wang, Rong Gan, Rongpeng Chen, Ruibin Chen, Rui Yuan, Ruobing Xie, Saiyong Yang, Shaohua Chen, Shihui Hu, Shuaipeng Li, Shuang Chen, Suncong Zheng, Tao Yang, Tengfei Cao, Tinghao Yu, Weichao Wang, Weijie Liu, Weiwen Jia, Wen Ouyang, Winston Hu, Xiang Li, Xiaobo Shu, Xiao Feng, Xiaoqin Ren, Xingwu Sun, Xinhua Feng, Xiong Kuang, Xipeng Zhang, Xirui Li, Xuebin Hou, Xuemeng Huang, Xun Cao, Yanfeng Chen, Yangyu Tao, Yao Ding, Yaping Deng, Yigeng Hong, Yinben Xia, Yiqi Chen, Yiqing Huang, Yi Shen, Yong Yang, Yuchi Deng, Yue Mao, Yuhong Liu, Yuyuan Zeng, Zekun He, Ze Zhao, Zhanhui Kang, Zhenxiang Yan, Zhen Yang, Zhichao Hu, Zhiyuan Xiong, Zhongzhi Chen, Zifan Wu, Zilong Zhao, Zongwei Li","submitted_at":"2024-11-04T16:56:26Z","abstract_excerpt":"In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens. We conduct a thorough evaluation of Hunyuan-Large's superior performance across various benchmarks including language understanding and generation, logical reasoning, mathematical problem-solving, coding, long-context, and aggregated tasks, where it outperforms LLama3.1-70B and exhibits comparable performance when compared to the significantly larger L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02265","kind":"arxiv","version":3},"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/2411.02265/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":"2411.02265","created_at":"2026-07-05T09:31:51.659260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02265v3","created_at":"2026-07-05T09:31:51.659260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02265","created_at":"2026-07-05T09:31:51.659260+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAC67T2T2D4K","created_at":"2026-07-05T09:31:51.659260+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAC67T2T2D4KOLLI","created_at":"2026-07-05T09:31:51.659260+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAC67T2T","created_at":"2026-07-05T09:31:51.659260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25334","citing_title":"Bridging the Post-discharge Gap: A Traceable Multi-agent Framework for Safe and Continuous Care","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26769","citing_title":"ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20374","citing_title":"ARGUS: Production-Scale Tracing and Performance Diagnosis for over 10,000-GPU Clusters","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20970","citing_title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15079","citing_title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03578","citing_title":"Diffusing in the Right Space: A Systematic Study of Latent Diffusability","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29555","citing_title":"From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31590","citing_title":"TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2506.00182","citing_title":"Overfitting has a limitation: a model-independent generalization gap bound based on R\\'enyi entropy","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08008","citing_title":"Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14311","citing_title":"Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2510.05497","citing_title":"Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09298","citing_title":"Multi-Modal LLM based Image Captioning in ICT: Bridging the Gap Between General and Industry Domain","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14311","citing_title":"Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25937","citing_title":"SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02200","citing_title":"ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAC67T2T2D4KOLLIFS2JA6AU3C","json":"https://pith.science/pith/WAC67T2T2D4KOLLIFS2JA6AU3C.json","graph_json":"https://pith.science/api/pith-number/WAC67T2T2D4KOLLIFS2JA6AU3C/graph.json","events_json":"https://pith.science/api/pith-number/WAC67T2T2D4KOLLIFS2JA6AU3C/events.json","paper":"https://pith.science/paper/WAC67T2T"},"agent_actions":{"view_html":"https://pith.science/pith/WAC67T2T2D4KOLLIFS2JA6AU3C","download_json":"https://pith.science/pith/WAC67T2T2D4KOLLIFS2JA6AU3C.json","view_paper":"https://pith.science/paper/WAC67T2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02265&json=true","fetch_graph":"https://pith.science/api/pith-number/WAC67T2T2D4KOLLIFS2JA6AU3C/graph.json","fetch_events":"https://pith.science/api/pith-number/WAC67T2T2D4KOLLIFS2JA6AU3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAC67T2T2D4KOLLIFS2JA6AU3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAC67T2T2D4KOLLIFS2JA6AU3C/action/storage_attestation","attest_author":"https://pith.science/pith/WAC67T2T2D4KOLLIFS2JA6AU3C/action/author_attestation","sign_citation":"https://pith.science/pith/WAC67T2T2D4KOLLIFS2JA6AU3C/action/citation_signature","submit_replication":"https://pith.science/pith/WAC67T2T2D4KOLLIFS2JA6AU3C/action/replication_record"}},"created_at":"2026-07-05T09:31:51.659260+00:00","updated_at":"2026-07-05T09:31:51.659260+00:00"}