papers/kai/references.bib

% References for kai.
%
% A line beginning "% TODO" marks an entry whose details we did not verify
% against the publisher's record. Page ranges we were unsure of are omitted
% rather than guessed.

% -- the system and its sources

@misc{jevnote,
  key          = {Jev},
  title        = {Jev Engineering for Coding Agents: The {TypeSafe} Founder's
                  Blueprint for Building with {Jev}},
  year         = {2026},
  note         = {Working note, September 2026. A synthesis of design notes
                  by Diogo Almeida (TypeSafe), independently compiled; not
                  affiliated with or endorsed by TypeSafe}
}

@misc{typesafejev,
  author       = {{TypeSafe}},
  title        = {Jev},
  howpublished = {Served as \texttt{typesafe/jev-1.13} through OpenRouter},
  year         = {2026},
  note         = {Typed decision model; listed on OpenRouter 2026-09-24}
}

@misc{openrouterdecisions,
  author       = {{OpenRouter}},
  title        = {Decisions {API} (alpha): \texttt{POST /api/alpha/decisions}},
  howpublished = {\url{https://openrouter.ai}},
  year         = {2026},
  note         = {Accessed 2026-09-24}
}

% TODO: author attribution taken from the repository owner and the Hugging
% Face organisation; the card gives no citation block.
@misc{laya,
  author       = {{Convai Innovations}},
  title        = {Laya: a multilingual, non-autoregressive decision engine},
  howpublished = {\url{https://github.com/NandhaKishorM/laya} and
                  \url{https://huggingface.co/convaiinnovations/laya}},
  year         = {2026},
  note         = {Version 0.3.20, Apache-2.0; model card accessed 2026-09-24}
}

@misc{hanzographpaper,
  author       = {{Hanzo AI Research}},
  title        = {A Temporal Assertion Graph: Valid-time and transaction-time
                  reads, schema as assertions, and erasure in an append-only
                  store},
  howpublished = {\url{https://github.com/hanzoai/papers}},
  year         = {2026},
  note         = {2026-09-22}
}

@misc{armysbir,
  author       = {{U.S. Army}},
  title        = {{ARM26BX06-NV012}: Agentic-{AI}, Schema-Driven Decision
                  Management for Auditable Studies and Acquisition Decisions},
  howpublished = {\url{https://armysbir.army.mil/topics/agentic-ai-schema-driven-decision-management/}},
  year         = {2026},
  note         = {SBIR topic; accessed 2026-09-24}
}

% TODO: SysML v2 formal specification version and date.
@misc{sysmlv2,
  author       = {{Object Management Group}},
  title        = {{OMG} Systems Modeling Language ({SysML}), Version 2},
  howpublished = {\url{https://www.omg.org/sysml/}},
  year         = {2025}
}

@misc{jevbenchabdel,
  author       = {{AbdelStark}},
  title        = {jev-benchmarks},
  howpublished = {\url{https://github.com/AbdelStark/jev-benchmarks}},
  year         = {2026},
  note         = {Version 0.1.0; AG News, Banking77 and DAIR Emotion, $n = 100$ each}
}

@misc{jevbenchnibzard,
  author       = {{nibzard}},
  title        = {decision-model-benchmark},
  howpublished = {\url{https://github.com/nibzard/decision-model-benchmark}},
  year         = {2026}
}

@misc{typeddecisions,
  key          = {typed-decisions},
  title        = {typed-decisions},
  howpublished = {\url{https://huggingface.co/datasets/LocalLLaMA/typed-decisions}},
  year         = {2026},
  note         = {400 cases, 2,000 decisions, four workflows; test split}
}

@inproceedings{das2024timesfm,
  author       = {Das, Abhimanyu and Kong, Weihao and Sen, Rajat and Zhou, Yichen},
  title        = {A Decoder-Only Foundation Model for Time-Series Forecasting},
  booktitle    = {Proceedings of the 41st International Conference on Machine Learning},
  year         = {2024}
}

% TODO: full author list.
@article{ansari2024chronos,
  author       = {Ansari, Abdul Fatir and Stella, Lorenzo and Turkmen, Caner and others},
  title        = {Chronos: Learning the Language of Time Series},
  journal      = {Transactions on Machine Learning Research},
  year         = {2024}
}

@inproceedings{radford2023whisper,
  author       = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman,
                  Greg and McLeavey, Christine and Sutskever, Ilya},
  title        = {Robust Speech Recognition via Large-Scale Weak Supervision},
  booktitle    = {Proceedings of the 40th International Conference on Machine
                  Learning},
  year         = {2023}
}

@inproceedings{zhai2023siglip,
  author       = {Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and
                  Beyer, Lucas},
  title        = {Sigmoid Loss for Language Image Pre-Training},
  booktitle    = {Proceedings of the IEEE/CVF International Conference on
                  Computer Vision},
  year         = {2023}
}

% -- encoders

@misc{modernbert,
  author       = {Warner, Benjamin and Chaffin, Antoine and Clavi{\'e}, Benjamin
                  and Weller, Orion and Hallstr{\"o}m, Oskar and Taghadouini,
                  Said and Gallagher, Alexis and Biswas, Raja and Ladhak,
                  Faisal and Aarsen, Tom and Cooper, Nathan and Adams, Griffin
                  and Howard, Jeremy and Poli, Iacopo},
  title        = {Smarter, Better, Faster, Longer: A Modern Bidirectional
                  Encoder for Fast, Memory Efficient, and Long Context
                  Finetuning and Inference},
  howpublished = {arXiv:2412.13663},
  year         = {2024}
}

% TODO: full author list.
@misc{mmbert,
  author       = {Marone, Marc and Weller, Orion and others},
  title        = {{mmBERT}: A Modern Multilingual Encoder with Annealed
                  Language Learning},
  howpublished = {\url{https://huggingface.co/jhu-clsp/mmBERT-base}},
  year         = {2025}
}

@inproceedings{devlin2019,
  author       = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and
                  Toutanova, Kristina},
  title        = {{BERT}: Pre-training of Deep Bidirectional Transformers for
                  Language Understanding},
  booktitle    = {Proceedings of NAACL-HLT},
  year         = {2019}
}

@misc{nogueira2019,
  author       = {Nogueira, Rodrigo and Cho, Kyunghyun},
  title        = {Passage Re-ranking with {BERT}},
  howpublished = {arXiv:1901.04085},
  year         = {2019}
}

@inproceedings{yin2019,
  author       = {Yin, Wenpeng and Hay, Jamaal and Roth, Dan},
  title        = {Benchmarking Zero-shot Text Classification: Datasets,
                  Evaluation and Entailment Approach},
  booktitle    = {Proceedings of EMNLP-IJCNLP},
  year         = {2019}
}

% -- generation, agents, guards

@misc{willard2023,
  author       = {Willard, Brandon T. and Louf, R{\'e}mi},
  title        = {Efficient Guided Generation for Large Language Models},
  howpublished = {arXiv:2307.09702},
  year         = {2023}
}

@inproceedings{yao2023react,
  author       = {Yao, Shunyu and Zhao, Jeffrey and Yu, Dian and Du, Nan and
                  Shafran, Izhak and Narasimhan, Karthik and Cao, Yuan},
  title        = {{ReAct}: Synergizing Reasoning and Acting in Language Models},
  booktitle    = {International Conference on Learning Representations},
  year         = {2023}
}

@inproceedings{schick2023toolformer,
  author       = {Schick, Timo and Dwivedi-Yu, Jane and Dess{\`i}, Roberto and
                  Raileanu, Roberta and Lomeli, Maria and Zettlemoyer, Luke and
                  Cancedda, Nicola and Scialom, Thomas},
  title        = {Toolformer: Language Models Can Teach Themselves to Use Tools},
  booktitle    = {Advances in Neural Information Processing Systems},
  year         = {2023}
}

@misc{inan2023llamaguard,
  author       = {Inan, Hakan and others},
  title        = {Llama Guard: {LLM}-based Input-Output Safeguard for
                  Human-{AI} Conversations},
  howpublished = {arXiv:2312.06674},
  year         = {2023}
}

% -- calibration, abstention, scoring

@inproceedings{guo2017,
  author       = {Guo, Chuan and Pleiss, Geoff and Sun, Yu and Weinberger,
                  Kilian Q.},
  title        = {On Calibration of Modern Neural Networks},
  booktitle    = {Proceedings of the 34th International Conference on Machine
                  Learning},
  year         = {2017}
}

@article{chow1970,
  author       = {Chow, C. K.},
  title        = {On Optimum Recognition Error and Reject Tradeoff},
  journal      = {IEEE Transactions on Information Theory},
  volume       = {16},
  number       = {1},
  year         = {1970}
}

@inproceedings{geifman2017,
  author       = {Geifman, Yonatan and El-Yaniv, Ran},
  title        = {Selective Classification for Deep Neural Networks},
  booktitle    = {Advances in Neural Information Processing Systems},
  year         = {2017}
}

@article{gneiting2007,
  author       = {Gneiting, Tilmann and Raftery, Adrian E.},
  title        = {Strictly Proper Scoring Rules, Prediction, and Estimation},
  journal      = {Journal of the American Statistical Association},
  volume       = {102},
  number       = {477},
  year         = {2007}
}

% -- authority

@article{denning1976,
  author       = {Denning, Dorothy E.},
  title        = {A Lattice Model of Secure Information Flow},
  journal      = {Communications of the ACM},
  volume       = {19},
  number       = {5},
  year         = {1976}
}

@techreport{anderson1972,
  author       = {Anderson, James P.},
  title        = {Computer Security Technology Planning Study},
  institution  = {U.S. Air Force Electronic Systems Division},
  number       = {ESD-TR-73-51},
  year         = {1972}
}

% -- decision analysis

@book{keeney1976,
  author       = {Keeney, Ralph L. and Raiffa, Howard},
  title        = {Decisions with Multiple Objectives: Preferences and Value
                  Tradeoffs},
  publisher    = {Wiley},
  year         = {1976}
}

@article{howard1966,
  author       = {Howard, Ronald A.},
  title        = {Information Value Theory},
  journal      = {IEEE Transactions on Systems Science and Cybernetics},
  volume       = {2},
  number       = {1},
  year         = {1966}
}

@article{triantaphyllou1997,
  author       = {Triantaphyllou, Evangelos and S{\'a}nchez, Alfonso},
  title        = {A Sensitivity Analysis Approach for Some Deterministic
                  Multi-Criteria Decision-Making Methods},
  journal      = {Decision Sciences},
  volume       = {28},
  number       = {1},
  year         = {1997}
}

@book{saltelli2008,
  author       = {Saltelli, Andrea and Ratto, Marco and Andres, Terry and
                  Campolongo, Francesca and Cariboni, Jessica and Gatelli, Debora
                  and Saisana, Michaela and Tarantola, Stefano},
  title        = {Global Sensitivity Analysis: The Primer},
  publisher    = {Wiley},
  year         = {2008}
}

@book{kahneman2011,
  author       = {Kahneman, Daniel},
  title        = {Thinking, Fast and Slow},
  publisher    = {Farrar, Straus and Giroux},
  year         = {2011}
}

% -- factorized scoring, ordinal answers, parallel refinement

@inproceedings{humeau2020poly,
  author       = {Humeau, Samuel and Shuster, Kurt and Lachaux, Marie-Anne and
                  Weston, Jason},
  title        = {Poly-encoders: Architectures and Pre-training Strategies for
                  Fast and Accurate Multi-sentence Scoring},
  booktitle    = {International Conference on Learning Representations},
  year         = {2020}
}

@inproceedings{khattab2020colbert,
  author       = {Khattab, Omar and Zaharia, Matei},
  title        = {{ColBERT}: Efficient and Effective Passage Search via
                  Contextualized Late Interaction over {BERT}},
  booktitle    = {Proceedings of the 43rd International ACM SIGIR Conference on
                  Research and Development in Information Retrieval},
  year         = {2020}
}

@article{mccullagh1980,
  author       = {McCullagh, Peter},
  title        = {Regression Models for Ordinal Data},
  journal      = {Journal of the Royal Statistical Society: Series B},
  volume       = {42},
  number       = {2},
  pages        = {109--142},
  year         = {1980}
}

@inproceedings{austin2021d3pm,
  author       = {Austin, Jacob and Johnson, Daniel D. and Ho, Jonathan and
                  Tarlow, Daniel and van den Berg, Rianne},
  title        = {Structured Denoising Diffusion Models in Discrete
                  State-Spaces},
  booktitle    = {Advances in Neural Information Processing Systems},
  year         = {2021}
}

@inproceedings{ghazvininejad2019,
  author       = {Ghazvininejad, Marjan and Levy, Omer and Liu, Yinhan and
                  Zettlemoyer, Luke},
  title        = {Mask-Predict: Parallel Decoding of Conditional Masked
                  Language Models},
  booktitle    = {Proceedings of EMNLP-IJCNLP},
  year         = {2019}
}

@inproceedings{chang2022maskgit,
  author       = {Chang, Huiwen and Zhang, Han and Jiang, Lu and Liu, Ce and
                  Freeman, William T.},
  title        = {{MaskGIT}: Masked Generative Image Transformer},
  booktitle    = {Proceedings of the IEEE/CVF Conference on Computer Vision and
                  Pattern Recognition},
  year         = {2022}
}

@book{vovk2005,
  author       = {Vovk, Vladimir and Gammerman, Alexander and Shafer, Glenn},
  title        = {Algorithmic Learning in a Random World},
  publisher    = {Springer},
  year         = {2005}
}

@misc{douillard2023diloco,
  author       = {Douillard, Arthur and Feng, Qixuan and Rusu, Andrei A. and
                  Chhaparia, Rachita and Donchev, Yani and Kuncoro, Adhiguna and
                  Ranzato, Marc'Aurelio and Szlam, Arthur and Shen, Jiajun},
  title        = {{DiLoCo}: Distributed Low-Communication Training of Language
                  Models},
  howpublished = {arXiv:2311.08105},
  year         = {2023}
}

@inproceedings{seide2014onebit,
  author       = {Seide, Frank and Fu, Hao and Droppo, Jasha and Li, Gang and
                  Yu, Dong},
  title        = {1-Bit Stochastic Gradient Descent and its Application to
                  Data-Parallel Distributed Training of Speech {DNNs}},
  booktitle    = {Interspeech},
  year         = {2014}
}

@inproceedings{karimireddy2019ef,
  author       = {Karimireddy, Sai Praneeth and Rebjock, Quentin and Stich,
                  Sebastian U. and Jaggi, Martin},
  title        = {Error Feedback Fixes {SignSGD} and other Gradient Compression
                  Schemes},
  booktitle    = {International Conference on Machine Learning},
  year         = {2019}
}

@inproceedings{micikevicius2018mixed,
  author       = {Micikevicius, Paulius and Narang, Sharan and Alben, Jonah and
                  Diamos, Gregory and Elsen, Erich and Garcia, David and
                  Ginsburg, Boris and Houston, Michael and Kuchaiev, Oleksii and
                  Venkatesh, Ganesh and Wu, Hao},
  title        = {Mixed Precision Training},
  booktitle    = {International Conference on Learning Representations},
  year         = {2018}
}

@inproceedings{broder1997resemblance,
  author       = {Broder, Andrei Z.},
  title        = {On the Resemblance and Containment of Documents},
  booktitle    = {Compression and Complexity of Sequences},
  year         = {1997},
  pages        = {21--29}
}

@inproceedings{lee2022dedup,
  author       = {Lee, Katherine and Ippolito, Daphne and Nystrom, Andrew and
                  Zhang, Chiyuan and Eck, Douglas and Callison-Burch, Chris and
                  Carlini, Nicholas},
  title        = {Deduplicating Training Data Makes Language Models Better},
  booktitle    = {Annual Meeting of the Association for Computational
                  Linguistics},
  year         = {2022}
}