% Background literature and early Jev studies.
% Background papers do not establish Jev's internal implementation.
% Primary-source metadata checks: docs/reviews/papers-2026-10-16.md.
% For arXiv records, the DOI identifies the work; the URL pins the reviewed
% version where a version was supplied. Inclusion does not imply peer review.

@article{gneiting2007proper,
  title = {Strictly Proper Scoring Rules, Prediction, and Estimation},
  author = {Gneiting, Tilmann and Raftery, Adrian E.},
  journal = {Journal of the American Statistical Association},
  year = {2007},
  volume = {102},
  number = {477},
  pages = {359--378},
  doi = {10.1198/016214506000001437},
  url = {https://doi.org/10.1198/016214506000001437}
}

@inproceedings{guo2017calibration,
  title = {On Calibration of Modern Neural Networks},
  author = {Guo, Chuan and Pleiss, Geoff and Sun, Yu and Weinberger, Kilian Q.},
  booktitle = {Proceedings of the 34th International Conference on Machine Learning},
  series = {Proceedings of Machine Learning Research},
  volume = {70},
  pages = {1321--1330},
  year = {2017},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v70/guo17a.html}
}

@inproceedings{geifman2019selectivenet,
  title = {{SelectiveNet}: A Deep Neural Network with an Integrated Reject Option},
  author = {Geifman, Yonatan and El-Yaniv, Ran},
  booktitle = {Proceedings of the 36th International Conference on Machine Learning},
  series = {Proceedings of Machine Learning Research},
  volume = {97},
  pages = {2151--2159},
  year = {2019},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v97/geifman19a.html}
}

@misc{kadavath2022know,
  title = {Language Models (Mostly) Know What They Know},
  author = {Kadavath, Saurav and Conerly, Tom and Askell, Amanda and Henighan, Tom and Drain, Dawn and Perez, Ethan and Schiefer, Nicholas and Hatfield-Dodds, Zac and DasSarma, Nova and Tran-Johnson, Eli and Johnston, Scott and El-Showk, Sheer and Jones, Andy and Elhage, Nelson and Hume, Tristan and Chen, Anna and Bai, Yuntao and Bowman, Sam and Fort, Stanislav and Ganguli, Deep and Hernandez, Danny and Jacobson, Josh and Kernion, Jackson and Kravec, Shauna and Lovitt, Liane and Ndousse, Kamal and Olsson, Catherine and Ringer, Sam and Amodei, Dario and Brown, Tom and Clark, Jack and Joseph, Nicholas and Mann, Ben and McCandlish, Sam and Olah, Chris and Kaplan, Jared},
  year = {2022},
  eprint = {2207.05221},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2207.05221},
  url = {https://arxiv.org/abs/2207.05221}
}

@inproceedings{beurerkellner2023lmql,
  title = {Prompting Is Programming: A Query Language for Large Language Models},
  author = {Beurer-Kellner, Luca and Fischer, Marc and Vechev, Martin},
  booktitle = {Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation},
  year = {2023},
  publisher = {ACM},
  doi = {10.1145/3591300},
  url = {https://www.sri.inf.ethz.ch/publications/beurerkellner2023prompting},
  eprint = {2212.06094},
  archivePrefix = {arXiv},
  note = {PLDI 2023; first arXiv version published in 2022}
}

@misc{dong2024xgrammar,
  title = {{XGrammar}: Flexible and Efficient Structured Generation Engine for Large Language Models},
  author = {Dong, Yixin and Ruan, Charlie F. and Cai, Yaxing and Lai, Ruihang and Xu, Ziyi and Zhao, Yilong and Chen, Tianqi},
  year = {2024},
  eprint = {2411.15100},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2411.15100},
  url = {https://arxiv.org/abs/2411.15100}
}

@misc{khattab2023dspy,
  title = {{DSPy}: Compiling Declarative Language Model Calls into Self-Improving Pipelines},
  author = {Khattab, Omar and Singhvi, Arnav and Maheshwari, Paridhi and Zhang, Zhiyuan and Santhanam, Keshav and Vardhamanan, Sri and Haq, Saiful and Sharma, Ashutosh and Joshi, Thomas T. and Moazam, Hanna and Miller, Heather and Zaharia, Matei and Potts, Christopher},
  year = {2023},
  eprint = {2310.03714},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2310.03714},
  url = {https://arxiv.org/abs/2310.03714}
}

@inproceedings{zheng2024sglang,
  title = {{SGLang}: Efficient Execution of Structured Language Model Programs},
  author = {Zheng, Lianmin and Yin, Liangsheng and Xie, Zhiqiang and Sun, Chuyue and Huang, Jeff and Yu, Cody Hao and Cao, Shiyi and Kozyrakis, Christos and Stoica, Ion and Gonzalez, Joseph E. and Barrett, Clark and Sheng, Ying},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2024},
  url = {https://papers.nips.cc/paper_files/paper/2024/file/724be4472168f31ba1c9ac630f15dec8-Paper-Conference.pdf},
  eprint = {2312.07104},
  archivePrefix = {arXiv},
  note = {NeurIPS 2024; first arXiv version published in 2023}
}

@misc{deusser2026jev,
  title = {Evaluating and Benchmarking the System One Model {Jev}},
  author = {Deu{\ss}er, Tobias and Sparrenberg, Lorenz and Sifa, Rafet},
  year = {2026},
  date = {2026-09-29},
  eprint = {2609.37647},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.37647},
  url = {https://arxiv.org/abs/2609.37647v1},
  note = {Version 1, 2026-09-29; preprint}
}

@misc{tang2026typed,
  title = {Typed Decision Models: An Early Evidence Audit and Evaluation Checklist},
  author = {Tang, Lijuan and Zheng, Yuemeng},
  year = {2026},
  date = {2026-09-26},
  eprint = {2609.32160},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.32160},
  url = {https://arxiv.org/abs/2609.32160v1},
  note = {Version 1, 2026-09-26; preprint}
}

@misc{li2026sameattack,
  title = {Same Attack, Different Judge: A First Controlled Adversarial Comparison of {Jev}, {LLM} Judges, and Purpose-Built Safety Classifiers},
  author = {Li, Xiang and Huang, Aichun and Zhang, Mingming and Liu, Zheli},
  year = {2026},
  date = {2026-10-13},
  eprint = {2610.17820},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2610.17820},
  url = {https://arxiv.org/abs/2610.17820v1},
  note = {Version 1, 2026-10-13; preprint}
}

@misc{denney2026jev,
  title = {{JEV} versus {LLMs}: Accuracy, Cost and Calibration on Seven Political Science Replications},
  author = {Denney, Steven and DiGiuseppe, Matthew},
  year = {2026},
  date = {2026-10-06},
  eprint = {2610.06625},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2610.06625},
  url = {https://arxiv.org/abs/2610.06625v2},
  note = {Version 2, 2026-10-06; first posted 2026-10-05; preprint}
}

@misc{li2026jevasajudge,
  title = {{JEV}-as-a-Judge: Accept When Confident, Escalate When Unsure},
  author = {Li, Yubo and Miao, Yidi and Krishnan, Ramayya and Padman, Rema},
  year = {2026},
  date = {2026-10-09},
  eprint = {2609.26550},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  doi = {10.48550/arXiv.2609.26550},
  url = {https://arxiv.org/abs/2609.26550v5},
  note = {Version 5, 2026-10-09; first posted 2026-09-22; preprint}
}

@misc{rao2026rubricjudges,
  title = {Decision Models vs. {LLMs} as Rubric Judges: Cheaper, Faster, and Wrong in the Same Places},
  author = {Rao, Delip and Callison-Burch, Chris},
  year = {2026},
  date = {2026-10-13},
  eprint = {2609.29769},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  doi = {10.48550/arXiv.2609.29769},
  url = {https://arxiv.org/abs/2609.29769v3},
  note = {Version 3, 2026-10-13; first posted 2026-09-24; preprint}
}


% Additional direct studies; metadata and abstract pages checked on 2026-10-15.

@misc{cheng2026thisthat,
  title = {{this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent}},
  author = {Cheng, Zehua and Dai, Wei and Sun, Jiahao},
  year = {2026},
  date = {2026-09-20},
  eprint = {2609.23886},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.23886},
  url = {https://arxiv.org/abs/2609.23886v1},
  note = {Version 1, 2026-09-20; preprint}
}

@misc{jiang2026jevmem,
  title = {{Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents}},
  author = {Jiang, Dongming and Li, Yi and Li, Bingzhe},
  year = {2026},
  date = {2026-09-21},
  eprint = {2609.23986},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.23986},
  url = {https://arxiv.org/abs/2609.23986v1},
  note = {Version 1, 2026-09-21; preprint}
}

@misc{zhou2026pixeljev,
  title = {{From Text Decisions to Pixels: An Study of Jev-Style Visual Choice Model}},
  author = {Zhou, Xunlan and Yang, Xianliang and Zhao, Li},
  year = {2026},
  date = {2026-09-24},
  eprint = {2609.29283},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.29283},
  url = {https://arxiv.org/abs/2609.29283v1},
  note = {Version 1, 2026-09-24; preprint}
}

@misc{hu2026jevadvbench,
  title = {{JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models}},
  author = {Hu, Jianyi and Zhang, Hangtao and Liu, Yi and Zeng, Yeqi and Zeng, Li and Wang, Xianlong and Wang, Rui and Zhang, Leo Yu},
  year = {2026},
  date = {2026-09-25},
  eprint = {2609.31142},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.31142},
  url = {https://arxiv.org/abs/2609.31142v1},
  note = {Version 1, 2026-09-25; preprint}
}

@misc{li2026probabilityaxioms,
  title = {{Beyond Calibration: Do a Typed-Decision Model's Probabilities Obey the Probability Axioms?}},
  author = {Li, Keyi and He, Yihao and Li, Quanyi},
  year = {2026},
  date = {2026-09-27},
  eprint = {2609.33209},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.33209},
  url = {https://arxiv.org/abs/2609.33209v1},
  note = {Version 1, 2026-09-27; preprint}
}

@misc{liu2026agentsecurity,
  title = {{Evaluating System One Models for Agent Security Decisions: Reliability, Calibration, and Selective Automation}},
  author = {Liu, Yixuan},
  year = {2026},
  date = {2026-10-03},
  eprint = {2609.33401},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.33401},
  url = {https://arxiv.org/abs/2609.33401v3},
  note = {Version 3, 2026-10-03; first posted 2026-09-27; preprint}
}

@misc{porcedda2026sys1cal,
  title = {{Jev thinks ``I don't know'', but doesn't say it: Introducing Sys1Cal-v1 Dataset for Probability Calibration}},
  author = {Porcedda, Riccardo},
  year = {2026},
  date = {2026-09-28},
  eprint = {2609.35342},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.35342},
  url = {https://arxiv.org/abs/2609.35342v1},
  note = {Version 1, 2026-09-28; preprint}
}

@misc{wang2026chinesejev,
  title = {{Chinese-Jev: Bringing System One Model to Chinese-Language Tasks}},
  author = {Wang, Zexiao and Zhang, Zihao and Wang, Xudong and Wang, Pan and Ye, Ziyi and Zhao, Haoyu and Wu, Zuxuan and Yan, Shuicheng},
  year = {2026},
  date = {2026-09-29},
  eprint = {2609.36965},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.36965},
  url = {https://arxiv.org/abs/2609.36965v1},
  note = {Version 1, 2026-09-29; preprint}
}

@misc{li2026jeva,
  title = {{Jeva: System One Models from First Principles}},
  author = {Li, Qi and Wang, Xinchao},
  year = {2026},
  date = {2026-10-13},
  eprint = {2610.18773},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2610.18773},
  url = {https://arxiv.org/abs/2610.18773v1},
  note = {Version 1, 2026-10-13; preprint}
}

@misc{chen2026system1arena,
  title = {{System1-Arena: Which Decisions Can Be Left to System 1?}},
  author = {Chen, Tianyu and Liu, Xinyang and An, Ruyi and Wang, Zhendong and Zhou, Mingyuan},
  year = {2026},
  date = {2026-10-15},
  eprint = {2610.21244},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2610.21244},
  url = {https://arxiv.org/abs/2610.21244v1},
  note = {Version 1, 2026-10-15; preprint}
}


% Primary-source metadata checked for the first scheduled-scan review.

@misc{sun2026typesafeerror,
  title = {{Type-Safe Is Not Error-Free: Typed Decision Models Follow the Option Name, Not the Definition Bound to It}},
  author = {Sun, Yu and Xu, Junhao and Shi, Jiajia and Yang, Zijin},
  year = {2026},
  date = {2026-10-08},
  eprint = {2609.26758},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.26758},
  url = {https://arxiv.org/abs/2609.26758v3},
  note = {Version 3, 2026-10-08; first posted 2026-09-22; preprint}
}

@misc{zhang2026anyjev,
  title = {{AnyJev Technical Report}},
  author = {Zhang, Jiamu and Yang, Tianze and Shi, Yucheng and Chen, Evan and Nie, Zixiang and Wan, Kelly and Hong, Liangjie and Liu, Ninghao and Wu, Liang},
  year = {2026},
  date = {2026-09-30},
  eprint = {2610.00831},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2610.00831},
  url = {https://arxiv.org/abs/2610.00831v1},
  note = {Version 1, 2026-09-30; preprint}
}

@misc{yilmaz2026lavoir,
  title = {{LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information}},
  author = {Yilmaz, Furkan and Tasdemir, Habibe Aleyna and Gozay, Muhammed Faruk},
  year = {2026},
  date = {2026-09-25},
  eprint = {2609.30706},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.30706},
  url = {https://arxiv.org/abs/2609.30706v1},
  note = {Version 1, 2026-09-25; preprint}
}

@misc{duan2026generaldecision,
  title = {{General Decision Models: Benchmarking and Insights Beyond Jev}},
  author = {Duan, Feiyu and Lin, Jiayu and Wang, Jia and Xiang, Jun and Wu, Jialiang and Zhang, Xinnong and Yan, Hanqi and Wang, Siyuan and Wei, Zhongyu},
  year = {2026},
  date = {2026-10-12},
  eprint = {2610.03935},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2610.03935},
  url = {https://arxiv.org/abs/2610.03935v2},
  note = {Version 2, 2026-10-12; first posted 2026-10-02; preprint}
}

@misc{zhu2026jevagentharness,
  title = {{JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs}},
  author = {Zhu, Kunlun and Feng, Tao and Han, Xu and Wang, Heng and Yang, Ling and Tang, Xiangru and You, Jiaxuan and Ji, Heng},
  year = {2026},
  date = {2026-10-15},
  eprint = {2610.21412},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2610.21412},
  url = {https://arxiv.org/abs/2610.21412v1},
  note = {Version 1, 2026-10-15; preprint}
}


% Added after primary abstract/metadata checks on 2026-10-16.

@misc{su2026jevspawn,
  title = {{JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces}},
  author = {Su, Haoyang and Huang, Weiran},
  year = {2026},
  date = {2026-09-30},
  eprint = {2610.00437},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  doi = {10.48550/arXiv.2610.00437},
  url = {https://arxiv.org/abs/2610.00437v1},
  note = {Version 1, 2026-09-30; preprint}
}

@misc{cheng2026metaencoder,
  title = {{MetaEncoder: Exploring the Limit of Bi-Encoders for Multimodal System One Decision Making with Natural Language Interface}},
  author = {Cheng, Jianpeng and Sun, Guangyu and Singh, Aashu and Zhang, Benyu and Dai, Haixing and Mansour, Hossein and Zhang, Jiangfan and Mishra, Shlok Kumar and Sun, Wei and Cui, Xuanming and Liu, Yanli and Guo, Qi and Fan, Max Xiangjun and Xiao, Jun},
  year = {2026},
  date = {2026-10-08},
  eprint = {2610.11316},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  doi = {10.48550/arXiv.2610.11316},
  url = {https://arxiv.org/abs/2610.11316v1},
  note = {Version 1, 2026-10-08; preprint}
}

@misc{li2026readingright,
  title = {{Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops}},
  author = {Li, Yubo and Krishnan, Ramayya and Padman, Rema},
  year = {2026},
  date = {2026-10-13},
  eprint = {2610.18579},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  doi = {10.48550/arXiv.2610.18579},
  url = {https://arxiv.org/abs/2610.18579v1},
  note = {Version 1, 2026-10-13; preprint}
}

@misc{lan2026decisionrobust,
  title = {{DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision}},
  author = {Lan, Yifan and Liu, Zhongye and Chang, Yurui and Wang, Hanyu and Du, Yongkang and Lin, Lu and Chen, Jinghui},
  year = {2026},
  date = {2026-10-13},
  eprint = {2610.19118},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  doi = {10.48550/arXiv.2610.19118},
  url = {https://arxiv.org/abs/2610.19118v1},
  note = {Version 1, 2026-10-13; preprint}
}

% Follow-up selection after primary metadata and targeted section checks on 2026-10-16.

@misc{geuter2026innerjev,
  title = {{Releasing the Inner Jev: A Simple Recipe for Open Decision Models}},
  author = {Geuter, Jonathan and Cheng, Andrew and Alvarez-Melis, David},
  year = {2026},
  date = {2026-10-12},
  eprint = {2610.17205},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  doi = {10.48550/arXiv.2610.17205},
  url = {https://arxiv.org/abs/2610.17205v1},
  note = {Version 1, 2026-10-12; preprint}
}

@misc{gan2026sansi,
  title = {{SanSi: A Looped Typed Decision Model for System 1.5 Thinking}},
  author = {Gan, Shuyu and Lee, Young-Jun and Kang, Dongyeop},
  year = {2026},
  date = {2026-10-10},
  eprint = {2610.07730},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  doi = {10.48550/arXiv.2610.07730},
  url = {https://arxiv.org/abs/2610.07730v2},
  note = {Version 2, 2026-10-10; first posted 2026-10-06; preprint}
}

@misc{li2026jevcascade,
  title = {{JevCascade: Readout Stability and Inference-Time Compute Allocation for Prefill-Only Decision Models}},
  author = {Li, Ran and Chen, Lei},
  year = {2026},
  date = {2026-10-10},
  eprint = {2610.07716},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  doi = {10.48550/arXiv.2610.07716},
  url = {https://arxiv.org/abs/2610.07716v2},
  note = {Version 2, 2026-10-10; first posted 2026-10-06; preprint}
}

% Direct studies selected from the reviewed source expansion on 2026-10-16.

@misc{wu2026reflexjev,
  title = {{REFLEX with Jev for Efficient Selective Control in LLM Agents}},
  author = {Wu, Tiantong and Lim, Wei Yang Bryan},
  year = {2026},
  date = {2026-09-22},
  eprint = {2609.26532},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.26532},
  url = {https://arxiv.org/abs/2609.26532v1},
  note = {Version 1, 2026-09-22; preprint}
}

@misc{wang2026mnemon,
  title = {{Mnemon: Raw Records, Fast Judgments, Slow Thoughts}},
  author = {Wang, Guangren},
  year = {2026},
  date = {2026-09-28},
  eprint = {2609.36059},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.36059},
  url = {https://arxiv.org/abs/2609.36059v1},
  note = {Version 1, 2026-09-28; preprint}
}

@misc{ding2026bongard,
  title = {{Bongard: Training Machine Intuition}},
  author = {Ding, Li and Jin, Haidi and Ji, Chen},
  year = {2026},
  date = {2026-09-30},
  eprint = {2609.39111},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2609.39111},
  url = {https://arxiv.org/abs/2609.39111v1},
  note = {Version 1, 2026-09-30; preprint}
}

@misc{zhu2026videojev,
  title = {{VideoJev: System One Model for Video Understanding and Interaction}},
  author = {Zhu, Yuhan and Zeng, Xiangyu and Si, Qingyi and Yang, Chenxu and Li, Yifei and Qin, Luozheng and Zhou, Junhao and Yao, Dingyu and Zhang, Jun and Qin, Chuanyu and Zhang, Zhiqiu and Yang, Yuandong and Xu, Yuqi and Zhang, Tianyu and Guo, Hongcheng and Wang, Jiaqi and Duan, Nan and Wang, Limin},
  year = {2026},
  date = {2026-10-13},
  eprint = {2610.18615},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2610.18615},
  url = {https://arxiv.org/abs/2610.18615v1},
  note = {Version 1, 2026-10-13; preprint}
}

@misc{zhang2026typedtabular,
  title = {{Typed Decision Models on Tabular Data}},
  author = {Zhang, Baowen and Ye, Hangting and Zha, Hongyuan},
  year = {2026},
  date = {2026-10-14},
  eprint = {2610.19536},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.19536v1},
  note = {Version 1, 2026-10-14; preprint}
}

@misc{zheng2026selectivereasoning,
  title = {{Selective Reasoning for Typed Decision Models: When to Start, Read, and Stop}},
  author = {Zheng, Bin and Chen, Zheng},
  year = {2026},
  date = {2026-10-14},
  eprint = {2610.19644},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.19644v1},
  note = {Version 1, 2026-10-14; preprint}
}

@misc{xu2026samenumbercitations,
  title = {{Same-Number Citation Swaps: Stress-Testing Jev as a Financial Evidence Judge}},
  author = {Xu, Chuhong and Su, Bo and Chen, Ziyao and Xu, Ruiyang and Dai, Shimeng and Qiu, Xinyu},
  year = {2026},
  date = {2026-10-06},
  eprint = {2610.08675},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.08675v1},
  note = {Version 1, 2026-10-06; preprint}
}

@misc{shankaranarayana2026beyondconfidence,
  title = {{Beyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Model}},
  author = {Shankaranarayana, Sharath M and Runje, Davor and Jannink, Jan},
  year = {2026},
  date = {2026-10-01},
  eprint = {2610.01006},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.01006v1},
  note = {Version 1, 2026-10-01; preprint}
}

@misc{li2026specializedjev,
  title = {{Specialized Decision Models vs. General-Purpose LLMs: Benchmarking Jev Across Knowledge, Reasoning, and Multilingual Tasks}},
  author = {Li, Xing and Chang, Qingcheng and Ning, Jinzhong and Xu, Changfeng and Zhang, Shenlong and Zhang, Yijia and Luo, Ling and Lin, Hongfei},
  year = {2026},
  date = {2026-10-08},
  eprint = {2610.11978},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.11978v1},
  note = {Version 1, 2026-10-08; preprint}
}

@misc{azizi2026optionchannel,
  title = {{One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails}},
  author = {Azizi, Seyedarmin and Baghaei Potraghloo, Erfan and Pedram, Massoud},
  year = {2026},
  date = {2026-10-08},
  eprint = {2610.12292},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.12292v1},
  note = {Version 1, 2026-10-08; preprint}
}

@misc{asseri2026calibratedwhom,
  title = {{Calibrated to Whom? Persona and Language Effects on Cultural Values in JEV}},
  author = {Asseri, Bushra and Asseri, Abdulaziz},
  year = {2026},
  date = {2026-10-03},
  eprint = {2609.36399},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.36399v2},
  note = {Version 2, 2026-10-03; first posted 2026-09-28; preprint}
}

@misc{chen2026memoryretirement,
  title = {{Suggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate}},
  author = {Chen, Xupeng and Le, Chenqian},
  year = {2026},
  date = {2026-10-11},
  eprint = {2610.15710},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.15710v1},
  note = {Version 1, 2026-10-11; preprint}
}

@misc{ma2026derivationgap,
  title = {{Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments}},
  author = {Ma, Linhai and Wang, Yan and Qian, Lingfei and Cao, Yupeng and Gutiérrez-Basulto, Víctor},
  year = {2026},
  date = {2026-10-13},
  eprint = {2610.18497},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.18497v1},
  note = {Version 1, 2026-10-13; preprint}
}

@misc{wu2026decisionhijacking,
  title = {{Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions}},
  author = {Wu, Tiantong and Lim, Wei Yang Bryan},
  year = {2026},
  date = {2026-09-23},
  eprint = {2609.28613},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.28613v1},
  note = {Version 1, 2026-09-23; preprint}
}

@misc{xu2026jevout,
  title = {{JevOut: Natural Context Can Flip Decision Models}},
  author = {Xu, Zixiang and Song, Zirui and Zhang, Chiyu and Chen, Xiuying and Liu, Xi and Hu, Xiyang and Zhao, Yue},
  year = {2026},
  date = {2026-10-08},
  eprint = {2609.30243},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.30243v2},
  note = {Version 2, 2026-10-08; first posted 2026-09-24; preprint}
}

@misc{wang2026jevtracesecurity,
  title = {{JEV as a Judge for Agent Trace Security: An Empirical Comparison with Generative LLM Judges}},
  author = {Wang, Zhiqiang and Gao, Yichao},
  year = {2026},
  date = {2026-09-28},
  eprint = {2609.34862},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.34862v1},
  note = {Version 1, 2026-09-28; preprint}
}

@misc{ibrahim2026cssannotation,
  title = {{Evaluating Decision Models for Text Annotation in Computational Social Science}},
  author = {Ibrahim, Hazem and Zaki, Yasir},
  year = {2026},
  date = {2026-09-23},
  eprint = {2609.24574},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.24574v2},
  note = {Version 2, 2026-09-23; first posted 2026-09-21; preprint}
}

@misc{deng2026scientificjev,
  title = {{Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences}},
  author = {Deng, Boyuan and Fan, Shuyi and Zhang, Hongyang and Xie, Xinhong},
  year = {2026},
  date = {2026-10-15},
  eprint = {2609.24965},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.24965v3},
  note = {Version 3, 2026-10-15; first posted 2026-09-21; preprint}
}

@misc{zhang2026legaldecisions,
  title = {{Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding}},
  author = {Zhang, Fan and Chen, Yankai and Xie, Zhuohan and Zhou, Yixi and Peng, Sijia and Fan, Lei and Ji, Xinhua and Zheng, Cunyuan and Shan, Huangyong and Yu, Philip S. and Liu, Xue and Chen, Yu and Nakov, Preslav and He, Songwei},
  year = {2026},
  date = {2026-10-10},
  eprint = {2609.27678},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27678v2},
  note = {Version 2, 2026-10-10; first posted 2026-09-23; preprint}
}

@misc{madridgarcia2026jevmedicine,
  title = {{Jev in Medicine: A Benchmark Evaluation}},
  author = {Madrid-García, Alfredo and Merino-Barbancho, Beatriz},
  year = {2026},
  date = {2026-10-10},
  eprint = {2609.34024},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.34024v4},
  note = {Version 4, 2026-10-10; first posted 2026-09-27; preprint}
}

@misc{li2026kite,
  title = {{KITE: Scaling Jev Population Experiments with Sparse Flagship Calibration}},
  author = {Li, Hengyu},
  year = {2026},
  date = {2026-09-23},
  eprint = {2609.27535},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27535v1},
  note = {Version 1, 2026-09-23; first posted 2026-09-23; preprint}
}

@misc{huang2026radiologyjev,
  title = {{Can Jev Judge Radiology Reports? Evaluating a System One Model for Clinical Factuality}},
  author = {Huang, Jiaju and Yang, Hao and Ma, Xinyu and Liang, Xinglong and Cai, Kunyan and Ma, Junqiang and Chen, Shaobin and Sun, Yue and Tan, Tao},
  year = {2026},
  date = {2026-09-23},
  eprint = {2609.27607},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27607v1},
  note = {Version 1, 2026-09-23; preprint}
}

@misc{gao2026ordinalscale,
  title = {{More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models}},
  author = {Gao, Tianxiang and Li, Jinzhe and Li, Zhiyuan and Chang, Yi and Wu, Yuan},
  year = {2026},
  date = {2026-10-14},
  eprint = {2609.38827},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.38827v2},
  note = {Version 2, 2026-10-14; first posted 2026-09-30; preprint}
}

@misc{yu2026visualjev,
  title = {{Visual Jev: Accurate and Efficient Decisions from Shared Visual Context}},
  author = {Yu, Guanxu and Yao, Yuhang},
  year = {2026},
  date = {2026-09-22},
  eprint = {2609.25845},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.25845v1},
  note = {Version 1, 2026-09-22; preprint}
}

@misc{guo2026justaskjev,
  title = {{Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures}},
  author = {Guo, Ruoqi and Liu, Yi and Deng, Gelei and Li, Yuekang and Zhao, Lida and Wu, Yutao and Chen, Simin and Zhang, Ying and Zhang, Leo Yu},
  year = {2026},
  date = {2026-09-24},
  eprint = {2609.29429},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2609.29429v1},
  note = {Version 1, 2026-09-24; preprint}
}

@misc{rafe2026decisiongates,
  title = {{Benchmarking System One decision models against trained classifiers and language models for automated decision gates}},
  author = {Rafe, Amir and Das, Subasish},
  year = {2026},
  date = {2026-10-06},
  eprint = {2610.00346},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.00346v2},
  note = {Version 2, 2026-10-06; first posted 2026-09-29; preprint}
}

@misc{li2026llmasjev,
  title = {{LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them}},
  author = {Li, Yinheng and Wagle, Justin},
  year = {2026},
  date = {2026-10-13},
  eprint = {2610.02076},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.02076v3},
  note = {Version 3, 2026-10-13; first posted 2026-10-01; preprint}
}

@misc{teke2026hakembench,
  title = {{HakemBench: A Turkish Benchmark of Typed Decisions}},
  author = {Teke, Sait Furkan},
  year = {2026},
  date = {2026-10-01},
  eprint = {2610.02293},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.02293v1},
  note = {Version 1, 2026-10-01; first posted 2026-10-01; preprint}
}