{"work":{"id":"ed8c5be1-1069-44c0-8dc4-627a7de3a371","openalex_id":"https://openalex.org/W4404534210","doi":"10.1145/3703155","arxiv_id":null,"raw_key":null,"title":"Huang et al","authors":[{"ORCID":"https://orcid.org/0009-0002-9650-8353","given":"Lei","family":"Huang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0002-7449-3093","given":"Weijiang","family":"Yu","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, China"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0009-0007-8631-3858","given":"Weitao","family":"Ma","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0009-0002-4063-668X","given":"Weihong","family":"Zhong","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0001-5909-1339","given":"Zhangyin","family":"Feng","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0009-0001-5363-3886","given":"Haotian","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0002-7845-1544","given":"Qianglong","family":"Chen","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, China"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0003-3380-6409","given":"Weihua","family":"Peng","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, China"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0001-6011-0496","given":"Xiaocheng","family":"Feng","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0002-2543-5604","given":"Bing","family":"Qin","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0009-0007-1999-2600","given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"authenticated-orcid":false}],"authors_text":"L","year":2025,"venue":"ACM Transactions on Information Systems","abstract":null,"external_url":"https://doi.org/10.1145/3703155","cited_by_count":1313,"metadata_source":"doi_reference","metadata_fetched_at":"2026-07-10T16:07:20.243096+00:00","pith_arxiv_id":null,"created_at":"2026-05-08T17:23:41.161483+00:00","updated_at":"2026-07-10T16:07:20.243096+00:00","title_quality_ok":false,"display_title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","render_title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions"},"hub":{"state":{"work_id":"ed8c5be1-1069-44c0-8dc4-627a7de3a371","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":112,"external_cited_by_count":1313,"distinct_field_count":13,"first_pith_cited_at":"2025-04-01T05:58:14+00:00","last_pith_cited_at":"2026-07-08T19:38:54+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":"2026-08-22T02:09:24.041922+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":21},{"context_role":"method","n":2}],"polarity_counts":[{"context_polarity":"background","n":19},{"context_polarity":"use_method","n":2},{"context_polarity":"support","n":1},{"context_polarity":"unclear","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","claims":[{"claim_text":"ICLR work blames shortcut alignment: models prefer plausible heuristics over explicit logical chains[100]. Calibration studies reveal over -confidence: RLHF-tuned ChatGPT probabilities overshoot empirical accuracy by 15 percentage points [101]. Multilingual MT audits observe hallucination rates triple for Amharic relative to English, indicating that fidelity metrics mask low - resource failures [102]. Long-document summarisation evaluations count twelve factual errors per 1 000 tokens, while hie","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Bing Qin, and Ting Liu. 2025. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.ACM Transactions on Information Systems43, 2, Article 43 (2025). https://doi.org/10.1145/3703155 [26] Thomas R Insel. 2017. Digital phenotyping: technology for a new science of behavior.Jama318, 13 (2017), 1215-1216. [27] Sijie Ji, Xinzhe Zheng, Jiawei Sun, Renqi Chen, Wei Gao, and Mani Srivastava. 2024. MindGuard: Towards Accessible and Sitgma-free Mental Health","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"their rapid adoption across numerous applications [20,58,60]. Despite these ad- vances, deploying MLLMs in knowledge-intensive scenarios still raises important reliability concerns. In particular, MLLMs may produce multimodal hallucina- tions and often lack access to private or domain-specific knowledge, since their parameters are primarily trained on large-scale public corpora [33,68,79]. ToarXiv:2604.04969v1 [cs.IR] 4 Apr 2026 2 Sijun Dai et al. address these limitations, Multimodal Retrieval-","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"The OW ASP Top 10 for LLM Applica- tions [30] catalogues these risks, including insecure output handling, excessive agency, and model denial-of-service, as systemic threats to any production LLM deployment.Second, uncontrolled tool access granted to LLM agents may lead to privilege escalation or data exfiltration [31], [32].Third, LLM hallucinations [33], fabricated IoCs, malformed rules, or incorrect MITRE ATT&CK mappings can erode analyst trust and, in the worst case, cause operational damage ","claim_type":"background","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"names in public registries and waiting for future users to install them, thereby turning model errors into supply chain compromises [10], [11]. Existing studies largely treat package hallucination as a passive model failure caused by imperfect ∗The first two authors made equal contributions. †Corresponding authors. memorization, probabilistic generation, or distributional un- certainty [9], [12], [13], [14], [15]. This leaves an important question unanswered: can an attacker actively influence w","claim_type":"background","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"and automated program understanding is a known hard problem [46]. But, recent studies [47], [48], [49] show thatLLMs are good at code summarization with proper context information and scoping. Although A VLs is closed source, we can use syscall tracing and other logging mechanisms to capture its interactions with KD. These logs will provide the necessary context for LLMs. However, as previous work shows [50], providing the entire source code (i.e.,entire KD sources) to LLMs might be detrimental ","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (21 contexts).","role_counts":[{"n":21,"context_role":"background"},{"n":2,"context_role":"method"}]},"error":null,"updated_at":"2026-06-29T21:39:17.739560+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"fc710582-f3a8-45f3-a2d1-231edff12d7a","orcid":null,"display_name":"Lei Huang"},{"id":"3fd68f16-0d50-4b97-8adc-18feaa6ed093","orcid":null,"display_name":"Weijiang Yu"},{"id":"0726644a-7e7a-4490-98b9-2aa45fe6605a","orcid":null,"display_name":"Weitao Ma"},{"id":"4c9a5cd7-4623-4d69-9af2-c3284e9bcfb5","orcid":null,"display_name":"Weihong Zhong"},{"id":"5351c1c9-2f0e-43d8-b06e-555e511d0e94","orcid":null,"display_name":"Zhangyin Feng"},{"id":"407300aa-e586-4d83-8921-a0e620f90d75","orcid":null,"display_name":"Haotian Wang"},{"id":"8a765df1-4255-4b33-98cc-ac6aeadfe421","orcid":null,"display_name":"Qianglong Chen"},{"id":"01c34357-0535-477d-962e-2134b622215c","orcid":null,"display_name":"Weihua Peng"},{"id":"0bde9399-71c1-4c9d-b67b-e29c5afcdb31","orcid":null,"display_name":"Xiaocheng Feng"},{"id":"f9b884ae-1962-41b2-b537-d49b505ad9a0","orcid":null,"display_name":"Bing Qin"},{"id":"46cd82ee-1bb4-424b-8996-4a4b4fc3c4c7","orcid":null,"display_name":"Ting Liu"}]},"error":null,"updated_at":"2026-06-29T21:39:18.271726+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T18:49:36.427133+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus","work_id":"aa2fb99f-beb8-463c-8cd4-c575e96e2512","shared_citers":8},{"title":"doi: 10.18653/v1/2023.emnlp-main.741","work_id":"f952e39f-7d85-4a4f-9dd7-9da09cf2c1d8","shared_citers":6},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":6},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":5},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":4},{"title":"Language Models (Mostly) Know What They Know","work_id":"8ca58a10-da41-4f70-baae-7e449512e345","shared_citers":4},{"title":"URLhttps://doi.org/10.48550/arXiv","work_id":"5c2060c6-427c-4321-be22-49ccae439d80","shared_citers":4},{"title":"Andrey Malinin and Mark Gales","work_id":"668c2115-8eeb-420f-8e23-0c5315e216c3","shared_citers":3},{"title":"arXiv:2402.03744 [cs]","work_id":"01db46ad-1693-4ad4-96c9-8f4620693f17","shared_citers":3},{"title":"Bradley Efron and Robert J Tibshirani.An introduction to the bootstrap, volume","work_id":"414143a1-235c-49ec-a733-5cff2faefa32","shared_citers":3},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":3},{"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","shared_citers":3},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":3},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":3},{"title":"H alu E val: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","work_id":"e6b96d1b-7944-4233-8a28-a097f26db294","shared_citers":3},{"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","shared_citers":3},{"title":"Mistral 7B","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","shared_citers":3},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":3},{"title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","work_id":"1f8027cc-877a-494d-b9e5-a01d32d3d76f","shared_citers":3},{"title":"Why Language Models Hallucinate","work_id":"6bfb3eed-1270-492c-8fbe-a5671f3f779c","shared_citers":3},{"title":"and Lin, Kevin and Hewitt, John and Paranjape, Ashwin and Bevilacqua, Michele and Petroni, Fabio and Liang, Percy","work_id":"9c9c91f9-a321-4e33-8897-d66f6ad0f659","shared_citers":2},{"title":"Are reasoning models more prone to hallucination?","work_id":"cbb24d0e-0a95-46cb-a43e-115b3c4115d7","shared_citers":2},{"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","shared_citers":2},{"title":"B ayesian Prompt Ensembles: Model Uncertainty Estimation for Black-Box Large Language Models","work_id":"be821273-d9bf-4a33-a6a1-627d9c93cb15","shared_citers":2}],"time_series":[{"n":35,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T18:49:27.103409+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":"2026-05-14T18:49:46.783112+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","claims":[{"claim_text":"ICLR work blames shortcut alignment: models prefer plausible heuristics over explicit logical chains[100]. Calibration studies reveal over -confidence: RLHF-tuned ChatGPT probabilities overshoot empirical accuracy by 15 percentage points [101]. Multilingual MT audits observe hallucination rates triple for Amharic relative to English, indicating that fidelity metrics mask low - resource failures [102]. Long-document summarisation evaluations count twelve factual errors per 1 000 tokens, while hie","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Bing Qin, and Ting Liu. 2025. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.ACM Transactions on Information Systems43, 2, Article 43 (2025). https://doi.org/10.1145/3703155 [26] Thomas R Insel. 2017. Digital phenotyping: technology for a new science of behavior.Jama318, 13 (2017), 1215-1216. [27] Sijie Ji, Xinzhe Zheng, Jiawei Sun, Renqi Chen, Wei Gao, and Mani Srivastava. 2024. MindGuard: Towards Accessible and Sitgma-free Mental Health","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"their rapid adoption across numerous applications [20,58,60]. Despite these ad- vances, deploying MLLMs in knowledge-intensive scenarios still raises important reliability concerns. In particular, MLLMs may produce multimodal hallucina- tions and often lack access to private or domain-specific knowledge, since their parameters are primarily trained on large-scale public corpora [33,68,79]. ToarXiv:2604.04969v1 [cs.IR] 4 Apr 2026 2 Sijun Dai et al. address these limitations, Multimodal Retrieval-","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"The OW ASP Top 10 for LLM Applica- tions [30] catalogues these risks, including insecure output handling, excessive agency, and model denial-of-service, as systemic threats to any production LLM deployment.Second, uncontrolled tool access granted to LLM agents may lead to privilege escalation or data exfiltration [31], [32].Third, LLM hallucinations [33], fabricated IoCs, malformed rules, or incorrect MITRE ATT&CK mappings can erode analyst trust and, in the worst case, cause operational damage ","claim_type":"background","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"names in public registries and waiting for future users to install them, thereby turning model errors into supply chain compromises [10], [11]. Existing studies largely treat package hallucination as a passive model failure caused by imperfect ∗The first two authors made equal contributions. †Corresponding authors. memorization, probabilistic generation, or distributional un- certainty [9], [12], [13], [14], [15]. This leaves an important question unanswered: can an attacker actively influence w","claim_type":"background","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"and automated program understanding is a known hard problem [46]. But, recent studies [47], [48], [49] show thatLLMs are good at code summarization with proper context information and scoping. Although A VLs is closed source, we can use syscall tracing and other logging mechanisms to capture its interactions with KD. These logs will provide the necessary context for LLMs. However, as previous work shows [50], providing the entire source code (i.e.,entire KD sources) to LLMs might be detrimental ","claim_type":"background","confidence":0.8,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (21 contexts).","role_counts":[{"n":21,"context_role":"background"},{"n":2,"context_role":"method"}]},"error":null,"updated_at":"2026-06-29T21:39:18.274847+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","claims":[],"why_cited":"Pith tracks A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T18:49:25.411678+00:00"}},"summary":{"title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","claims":[],"why_cited":"Pith tracks A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus","work_id":"aa2fb99f-beb8-463c-8cd4-c575e96e2512","shared_citers":8},{"title":"doi: 10.18653/v1/2023.emnlp-main.741","work_id":"f952e39f-7d85-4a4f-9dd7-9da09cf2c1d8","shared_citers":6},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":6},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":5},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":4},{"title":"Language Models (Mostly) Know What They Know","work_id":"8ca58a10-da41-4f70-baae-7e449512e345","shared_citers":4},{"title":"URLhttps://doi.org/10.48550/arXiv","work_id":"5c2060c6-427c-4321-be22-49ccae439d80","shared_citers":4},{"title":"Andrey Malinin and Mark Gales","work_id":"668c2115-8eeb-420f-8e23-0c5315e216c3","shared_citers":3},{"title":"arXiv:2402.03744 [cs]","work_id":"01db46ad-1693-4ad4-96c9-8f4620693f17","shared_citers":3},{"title":"Bradley Efron and Robert J Tibshirani.An introduction to the bootstrap, volume","work_id":"414143a1-235c-49ec-a733-5cff2faefa32","shared_citers":3},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":3},{"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","shared_citers":3},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":3},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":3},{"title":"H alu E val: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","work_id":"e6b96d1b-7944-4233-8a28-a097f26db294","shared_citers":3},{"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","shared_citers":3},{"title":"Mistral 7B","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","shared_citers":3},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":3},{"title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","work_id":"1f8027cc-877a-494d-b9e5-a01d32d3d76f","shared_citers":3},{"title":"Why Language Models Hallucinate","work_id":"6bfb3eed-1270-492c-8fbe-a5671f3f779c","shared_citers":3},{"title":"and Lin, Kevin and Hewitt, John and Paranjape, Ashwin and Bevilacqua, Michele and Petroni, Fabio and Liang, Percy","work_id":"9c9c91f9-a321-4e33-8897-d66f6ad0f659","shared_citers":2},{"title":"Are reasoning models more prone to hallucination?","work_id":"cbb24d0e-0a95-46cb-a43e-115b3c4115d7","shared_citers":2},{"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","shared_citers":2},{"title":"B ayesian Prompt Ensembles: Model Uncertainty Estimation for Black-Box Large Language Models","work_id":"be821273-d9bf-4a33-a6a1-627d9c93cb15","shared_citers":2}],"time_series":[{"n":35,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"f9b884ae-1962-41b2-b537-d49b505ad9a0","orcid":null,"display_name":"Bing Qin","source":"manual","import_confidence":0.72},{"id":"407300aa-e586-4d83-8921-a0e620f90d75","orcid":null,"display_name":"Haotian Wang","source":"manual","import_confidence":0.72},{"id":"fc710582-f3a8-45f3-a2d1-231edff12d7a","orcid":null,"display_name":"Lei Huang","source":"manual","import_confidence":0.72},{"id":"8a765df1-4255-4b33-98cc-ac6aeadfe421","orcid":null,"display_name":"Qianglong Chen","source":"manual","import_confidence":0.72},{"id":"46cd82ee-1bb4-424b-8996-4a4b4fc3c4c7","orcid":null,"display_name":"Ting Liu","source":"manual","import_confidence":0.72},{"id":"4c9a5cd7-4623-4d69-9af2-c3284e9bcfb5","orcid":null,"display_name":"Weihong Zhong","source":"manual","import_confidence":0.72},{"id":"01c34357-0535-477d-962e-2134b622215c","orcid":null,"display_name":"Weihua Peng","source":"manual","import_confidence":0.72},{"id":"3fd68f16-0d50-4b97-8adc-18feaa6ed093","orcid":null,"display_name":"Weijiang Yu","source":"manual","import_confidence":0.72},{"id":"0726644a-7e7a-4490-98b9-2aa45fe6605a","orcid":null,"display_name":"Weitao Ma","source":"manual","import_confidence":0.72},{"id":"0bde9399-71c1-4c9d-b67b-e29c5afcdb31","orcid":null,"display_name":"Xiaocheng Feng","source":"manual","import_confidence":0.72},{"id":"5351c1c9-2f0e-43d8-b06e-555e511d0e94","orcid":null,"display_name":"Zhangyin Feng","source":"manual","import_confidence":0.72}]}}