{"work":{"id":"126a464a-4a73-495f-b669-de1e44aa8f09","openalex_id":"https://openalex.org/W4378474282","doi":"10.48550/arxiv.2305.15334","arxiv_id":"2305.15334","raw_key":null,"title":"Gorilla: Large Language Model Connected with Massive APIs","authors":null,"authors_text":"Shishir G. Patil, Tianjun Zhang, Xin Wang, Joseph E. Gonzalez","year":2023,"venue":"cs.CL","abstract":"Large Language Models (LLMs) have seen an impressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis. However, their potential to effectively use tools via API calls remains unfulfilled. This is a challenging task even for today's state-of-the-art LLMs such as GPT-4, largely due to their inability to generate accurate input arguments and their tendency to hallucinate the wrong usage of an API call. We release Gorilla, a finetuned LLaMA-based model that surpasses the performance of GPT-4 on writing API calls. When combined with a document retriever, Gorilla demonstrates a strong capability to adapt to test-time document changes, enabling flexible user updates or version changes. It also substantially mitigates the issue of hallucination, commonly encountered when prompting LLMs directly. To evaluate the model's ability, we introduce APIBench, a comprehensive dataset consisting of HuggingFace, TorchHub, and TensorHub APIs. The successful integration of the retrieval system with Gorilla demonstrates the potential for LLMs to use tools more accurately, keep up with frequently updated documentation, and consequently increase the reliability and applicability of their outputs. Gorilla's code, model, data, and demo are available at https://gorilla.cs.berkeley.edu","external_url":"https://arxiv.org/abs/2305.15334","cited_by_count":84,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2305.15334","created_at":"2026-05-09T01:54:36.093894+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Gorilla: Large Language Model Connected with Massive APIs","render_title":"Gorilla: Large Language Model Connected with Massive APIs"},"hub":{"state":{"work_id":"126a464a-4a73-495f-b669-de1e44aa8f09","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":111,"external_cited_by_count":84,"distinct_field_count":13,"first_pith_cited_at":"2023-04-14T14:05:32+00:00","last_pith_cited_at":"2026-07-08T17:34:28+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-20T20:59:20.252067+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":27},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":25},{"context_polarity":"unclear","n":2},{"context_polarity":"baseline","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Gorilla: Large Language Model Connected with Massive APIs","claims":[{"claim_text":"Large Language Models (LLMs) have seen an impressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis. However, their potential to effectively use tools via API calls remains unfulfilled. This is a challenging task even for today's state-of-the-art LLMs such as GPT-4, largely due to their inability to generate accurate input arguments and their tendency to hallucinate the wrong usage of an API call. We release Gorilla, a finetuned LLaMA-based model that surpasses the performance of GPT-4 on writing API calls. When ","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"'23, New York, NY , USA, 2023. Association for Computing Machinery. [37] Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019. [38] Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. Gorilla: Large language model connected with massive apis. arXiv prepri","claim_type":"background","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"bing-web-search-api , 2023. [80] Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334, 2023. [81] Rui Yang, Lin Song, Yanwei Li, Sijie Zhao, Yixiao Ge, Xiu Li, and Ying Shan. Gpt4tools: Teaching large language model to use tools via self-instruction, 2023. 42 [82] Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Runch","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"[2] interleaves reasoning traces with task -specific actions, showing that combined reasoning -and-acting improves interpretability and performance on question answering and interactive decision -making. HuggingGPT [ 3] treats the language model as a controller that plans tasks, selects external models, executes subtasks, and summarizes results. Gorilla [ 4] and ToolLLM [ 5] extend this direction toward larger API surfaces, emphasizing accurate API invocation, retrieval over changing documentati","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"is complementary to this line: its emphasis is not interface realism alone, but a workflow mixture derived from public demand signals and evaluated inside a reproducible release snapshot. Code and workspace agent benchmarks.Tool and code benchmarks provide the closest prece- dent for the workspace-repair side of Claw-Eval-Live. API-Bank [20], ToolBench/ToolLLM [33], Gorilla [31], MINT [40], τ-bench [48], and MCP-Bench [41] focus on API or tool manipulation. HumanEval [3], MBPP [ 2], DS-1000 [ 18","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"APIs reduce ambiguity-induced failures, enable structured error recovery, and enforce enterprise-grade access control without external orchestration layers-capabilities absent from conventional CRUD interfaces. Index Terms-LLM agents, tool APIs, API design, enterprise governance, multi-tenant systems, agentic AI I. INTRODUCTION The advent of tool-augmented Large Language Models [1], [2], [3] has catalyzed a fundamental shift in enterprise software architecture. Instead of human operators navigat","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"[19] Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G Patil, Ion Stoica, and Joseph E Gonzalez. Memgpt: Towards llms as operating systems.arXiv preprint arXiv:2310.08560, 2023. [20] Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. Gorilla: Large language model connected with massive APIs.arXiv preprint arXiv:2305.15334, 2023. [21] Long Phan et al. Humanity's last exam.arXiv preprint arXiv:2501.14249, 2025. [22] Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Gorilla: Large Language Model Connected with Massive APIs because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (27 contexts).","role_counts":[{"n":27,"context_role":"background"},{"n":1,"context_role":"baseline"}]},"error":null,"updated_at":"2026-07-03T10:33:58.374730+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"c95fa5d3-90f2-454e-94cb-b384ae36cdb7","orcid":null,"display_name":"Shishir G. Patil"},{"id":"3af63c1b-861c-481d-b7ed-5864bcb60b2a","orcid":null,"display_name":"Tianjun Zhang"},{"id":"558dee86-17ef-43a5-a795-87bde6e53776","orcid":null,"display_name":"Xin Wang"},{"id":"6636e6b2-ef2d-4768-84ff-1acd703dfa66","orcid":null,"display_name":"Joseph E. Gonzalez"}]},"error":null,"updated_at":"2026-07-03T10:33:58.571524+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T17:49:21.649855+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","work_id":"3c555b48-a4d9-42dd-9fdd-0f6018fbe9cb","shared_citers":16},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":12},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":11},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":10},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":10},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":8},{"title":"The Rise and Potential of Large Language Model Based Agents: A Survey","work_id":"985ca219-7e34-4c4f-bdc5-ccd39763ad61","shared_citers":8},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":7},{"title":"WebGPT: Browser-assisted question-answering with human feedback","work_id":"e25ef3e1-4848-4cb9-bf28-67a420591165","shared_citers":7},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":6},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":6},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":6},{"title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","work_id":"6a8d8dc4-0cc0-4052-8109-abbcdcd4a962","shared_citers":5},{"title":"AgentBench: Evaluating LLMs as Agents","work_id":"a37549b4-4c94-412d-acc4-4efeb08509be","shared_citers":5},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":5},{"title":"doi:10.48550/arXiv.2304.08244 , urldate =","work_id":"a20d9332-ab34-485c-a060-1ba47cc98930","shared_citers":5},{"title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","work_id":"3d4c3b66-d749-4939-b1bc-62b10b2ebbb6","shared_citers":5},{"title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","work_id":"5cbfcda4-ec26-44e4-be60-e1525956d71d","shared_citers":5},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":5},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":5},{"title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","work_id":"f1762ea0-e382-4f38-a28c-adc643789859","shared_citers":5},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":5},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":5},{"title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","work_id":"a1f2574b-a899-4713-be60-c87ba332656c","shared_citers":5}],"time_series":[{"n":2,"year":2023},{"n":4,"year":2024},{"n":2,"year":2025},{"n":35,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T17:49:14.986535+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T17:48:44.019005+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Gorilla: Large Language Model Connected with Massive APIs","claims":[{"claim_text":"Large Language Models (LLMs) have seen an impressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis. However, their potential to effectively use tools via API calls remains unfulfilled. This is a challenging task even for today's state-of-the-art LLMs such as GPT-4, largely due to their inability to generate accurate input arguments and their tendency to hallucinate the wrong usage of an API call. We release Gorilla, a finetuned LLaMA-based model that surpasses the performance of GPT-4 on writing API calls. When ","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"'23, New York, NY , USA, 2023. Association for Computing Machinery. [37] Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019. [38] Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. Gorilla: Large language model connected with massive apis. arXiv prepri","claim_type":"background","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"bing-web-search-api , 2023. [80] Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334, 2023. [81] Rui Yang, Lin Song, Yanwei Li, Sijie Zhao, Yixiao Ge, Xiu Li, and Ying Shan. Gpt4tools: Teaching large language model to use tools via self-instruction, 2023. 42 [82] Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Runch","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"[2] interleaves reasoning traces with task -specific actions, showing that combined reasoning -and-acting improves interpretability and performance on question answering and interactive decision -making. HuggingGPT [ 3] treats the language model as a controller that plans tasks, selects external models, executes subtasks, and summarizes results. Gorilla [ 4] and ToolLLM [ 5] extend this direction toward larger API surfaces, emphasizing accurate API invocation, retrieval over changing documentati","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"is complementary to this line: its emphasis is not interface realism alone, but a workflow mixture derived from public demand signals and evaluated inside a reproducible release snapshot. Code and workspace agent benchmarks.Tool and code benchmarks provide the closest prece- dent for the workspace-repair side of Claw-Eval-Live. API-Bank [20], ToolBench/ToolLLM [33], Gorilla [31], MINT [40], τ-bench [48], and MCP-Bench [41] focus on API or tool manipulation. HumanEval [3], MBPP [ 2], DS-1000 [ 18","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"APIs reduce ambiguity-induced failures, enable structured error recovery, and enforce enterprise-grade access control without external orchestration layers-capabilities absent from conventional CRUD interfaces. Index Terms-LLM agents, tool APIs, API design, enterprise governance, multi-tenant systems, agentic AI I. INTRODUCTION The advent of tool-augmented Large Language Models [1], [2], [3] has catalyzed a fundamental shift in enterprise software architecture. Instead of human operators navigat","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"[19] Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G Patil, Ion Stoica, and Joseph E Gonzalez. Memgpt: Towards llms as operating systems.arXiv preprint arXiv:2310.08560, 2023. [20] Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. Gorilla: Large language model connected with massive APIs.arXiv preprint arXiv:2305.15334, 2023. [21] Long Phan et al. Humanity's last exam.arXiv preprint arXiv:2501.14249, 2025. [22] Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Gorilla: Large Language Model Connected with Massive APIs because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (27 contexts).","role_counts":[{"n":27,"context_role":"background"},{"n":1,"context_role":"baseline"}]},"error":null,"updated_at":"2026-07-03T10:33:58.379355+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Gorilla: Large Language Model Connected with Massive APIs","claims":[{"claim_text":"Large Language Models (LLMs) have seen an impressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis. However, their potential to effectively use tools via API calls remains unfulfilled. This is a challenging task even for today's state-of-the-art LLMs such as GPT-4, largely due to their inability to generate accurate input arguments and their tendency to hallucinate the wrong usage of an API call. We release Gorilla, a finetuned LLaMA-based model that surpasses the performance of GPT-4 on writing API calls. When ","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Gorilla: Large Language Model Connected with Massive APIs because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T17:49:00.348064+00:00"}},"summary":{"title":"Gorilla: Large Language Model Connected with Massive APIs","claims":[{"claim_text":"Large Language Models (LLMs) have seen an impressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis. However, their potential to effectively use tools via API calls remains unfulfilled. This is a challenging task even for today's state-of-the-art LLMs such as GPT-4, largely due to their inability to generate accurate input arguments and their tendency to hallucinate the wrong usage of an API call. We release Gorilla, a finetuned LLaMA-based model that surpasses the performance of GPT-4 on writing API calls. When ","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Gorilla: Large Language Model Connected with Massive APIs because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","work_id":"3c555b48-a4d9-42dd-9fdd-0f6018fbe9cb","shared_citers":16},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":12},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":11},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":10},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":10},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":8},{"title":"The Rise and Potential of Large Language Model Based Agents: A Survey","work_id":"985ca219-7e34-4c4f-bdc5-ccd39763ad61","shared_citers":8},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":7},{"title":"WebGPT: Browser-assisted question-answering with human feedback","work_id":"e25ef3e1-4848-4cb9-bf28-67a420591165","shared_citers":7},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":6},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":6},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":6},{"title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","work_id":"6a8d8dc4-0cc0-4052-8109-abbcdcd4a962","shared_citers":5},{"title":"AgentBench: Evaluating LLMs as Agents","work_id":"a37549b4-4c94-412d-acc4-4efeb08509be","shared_citers":5},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":5},{"title":"doi:10.48550/arXiv.2304.08244 , urldate =","work_id":"a20d9332-ab34-485c-a060-1ba47cc98930","shared_citers":5},{"title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","work_id":"3d4c3b66-d749-4939-b1bc-62b10b2ebbb6","shared_citers":5},{"title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","work_id":"5cbfcda4-ec26-44e4-be60-e1525956d71d","shared_citers":5},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":5},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":5},{"title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","work_id":"f1762ea0-e382-4f38-a28c-adc643789859","shared_citers":5},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":5},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":5},{"title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","work_id":"a1f2574b-a899-4713-be60-c87ba332656c","shared_citers":5}],"time_series":[{"n":2,"year":2023},{"n":4,"year":2024},{"n":2,"year":2025},{"n":35,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"6636e6b2-ef2d-4768-84ff-1acd703dfa66","orcid":null,"display_name":"Joseph E. Gonzalez","source":"manual","import_confidence":0.72},{"id":"c95fa5d3-90f2-454e-94cb-b384ae36cdb7","orcid":null,"display_name":"Shishir G. Patil","source":"manual","import_confidence":0.72},{"id":"3af63c1b-861c-481d-b7ed-5864bcb60b2a","orcid":null,"display_name":"Tianjun Zhang","source":"manual","import_confidence":0.72},{"id":"558dee86-17ef-43a5-a795-87bde6e53776","orcid":null,"display_name":"Xin Wang","source":"manual","import_confidence":0.72}]}}