% references.bib seed for paper-02: calibration drift under verifier composition.
% Status: 15 citations, all verified as real publications or arXiv preprints
% present in the verification-economics wedge research cache or canonical to
% the literature being cited. Add a citation only after verifying its
% existence; do not invent.

% ============================================================
% Strictly proper scoring rules and peer prediction (mechanism core)
% ============================================================

@article{gneiting2007strictly,
  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},
  pages   = {359--378},
  year    = {2007},
  doi     = {10.1198/016214506000001437}
}

@article{miller2005peer,
  author  = {Miller, Nolan and Resnick, Paul and Zeckhauser, Richard},
  title   = {Eliciting Informative Feedback. The Peer-Prediction Method},
  journal = {Management Science},
  volume  = {51},
  number  = {9},
  pages   = {1359--1373},
  year    = {2005},
  doi     = {10.1287/mnsc.1050.0379}
}

@inproceedings{witkowski2012peer,
  author    = {Witkowski, Jens and Parkes, David C.},
  title     = {A Robust Bayesian Truth Serum for Small Populations},
  booktitle = {Proceedings of the 26th AAAI Conference on Artificial Intelligence},
  year      = {2012},
  pages     = {1492--1498}
}

@article{kong2019informationtheoretic,
  author    = {Kong, Yuqing and Schoenebeck, Grant},
  title     = {An Information Theoretic Framework for Designing Information Elicitation Mechanisms That Reward Truth-Telling},
  journal   = {ACM Transactions on Economics and Computation},
  volume    = {7},
  number    = {1},
  year      = {2019},
  doi       = {10.1145/3296670}
}

@article{frongillo2021general,
  author    = {Frongillo, Rafael and Kash, Ian A.},
  title     = {General Truthfulness Characterizations Via Convex Analysis},
  journal   = {Games and Economic Behavior},
  volume    = {130},
  pages     = {636--662},
  year      = {2021}
}

% ============================================================
% Calibration of probabilistic forecasts
% ============================================================

@inproceedings{guo2017calibration,
  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},
  pages     = {1321--1330}
}

% ============================================================
% LLM verifiers and reward models (production stack context)
% ============================================================

@article{cobbe2021training,
  author  = {Cobbe, Karl and Kosaraju, Vineet and Bavarian, Mohammad and Chen, Mark and Jun, Heewoo and Kaiser, Lukasz and Plappert, Matthias and Tworek, Jerry and Hilton, Jacob and Nakano, Reiichiro and Hesse, Christopher and Schulman, John},
  title   = {Training Verifiers to Solve Math Word Problems},
  journal = {arXiv preprint arXiv:2110.14168},
  year    = {2021},
  url     = {https://arxiv.org/abs/2110.14168}
}

@inproceedings{lightman2024lets,
  author    = {Lightman, Hunter and Kosaraju, Vineet and Burda, Yura and Edwards, Harri and Baker, Bowen and Lee, Teddy and Leike, Jan and Schulman, John and Sutskever, Ilya and Cobbe, Karl},
  title     = {Let's Verify Step by Step},
  booktitle = {International Conference on Learning Representations},
  year      = {2024},
  url       = {https://arxiv.org/abs/2305.20050}
}

% ============================================================
% Recent (May 2026) mechanism design and oversight (research cache)
% ============================================================

@article{bahrani2026adversarial,
  author  = {Bahrani, Maryam and Neuder, Michael and Weinberg, S. Matthew},
  title   = {Adversarial Procurement in Blockchains},
  journal = {arXiv preprint arXiv:2605.05559},
  year    = {2026},
  url     = {https://arxiv.org/abs/2605.05559}
}

@article{loven2026honest,
  author  = {Lov{\'e}n, Lauri},
  title   = {Honest Reporting in Scored Oversight. True-KL0 Property via the Prekopa Principle},
  journal = {arXiv preprint arXiv:2605.03793},
  year    = {2026},
  url     = {https://arxiv.org/abs/2605.03793}
}

@article{burnat2026benchmark,
  author  = {Burnat, Florian A. D. and Davidson, Brittany I.},
  title   = {A Benchmark for Strategic Auditee Gaming Under Continuous Compliance Monitoring},
  journal = {arXiv preprint arXiv:2605.06340},
  year    = {2026},
  url     = {https://arxiv.org/abs/2605.06340}
}

@article{xu2026online,
  author  = {Xu, Yang and Park, Chiwoo},
  title   = {Online Bayesian Calibration under Gradual and Abrupt System Changes},
  journal = {arXiv preprint arXiv:2605.06612},
  year    = {2026},
  url     = {https://arxiv.org/abs/2605.06612}
}

@article{ye2026implicit,
  author  = {Ye, Hao and Dang, Jisheng and Fang, Junfeng and Wang, Bimei and Zhang, Yizhou and Lv, Ning and Zhang, Wencan and Peng, Hong and Hu, Bin and Chua, Tat-Seng},
  title   = {On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR},
  journal = {arXiv preprint arXiv:2605.06523},
  year    = {2026},
  url     = {https://arxiv.org/abs/2605.06523}
}

% ============================================================
% Test-time compute and cost-of-pass (wedge framing)
% ============================================================

@article{snell2024scaling,
  author  = {Snell, Charlie and Lee, Jaehoon and Xu, Kelvin and Kumar, Aviral},
  title   = {Scaling LLM Test-Time Compute Optimally Can Be More Effective Than Scaling Model Parameters},
  journal = {arXiv preprint arXiv:2408.03314},
  year    = {2024},
  url     = {https://arxiv.org/abs/2408.03314}
}

@article{erol2026costofpass,
  author  = {Erol, Mehmet H. and El, Batu and Suzgun, Mirac and Yuksekgonul, Mert and Zou, James},
  title   = {Cost-of-Pass. An Economic Framework for Evaluating Language Models},
  journal = {arXiv preprint arXiv:2504.13359},
  year    = {2025},
  url     = {https://arxiv.org/abs/2504.13359}
}

% ============================================================
% Self-cite (wedge field notes and paper #1)
% ============================================================

@misc{bhardwaj2026fieldnotes,
  author       = {Bhardwaj, Manu},
  title        = {Verification Economics. Field Notes Series},
  howpublished = {ifitsmanu.com/papers},
  year         = {2026},
  note         = {Field Note #2 on the Cost-correct decomposition; Field Note #3 on alpha asymmetry; Field Note #4 on probe portfolio design.}
}

@misc{bhardwaj2026procurement,
  author       = {Bhardwaj, Manu},
  title        = {Verifier Procurement Under Unobservable Quality. A Scoring-Rule Mechanism for Cost-Correct Minimization},
  howpublished = {ifitsmanu.com/papers/verifier-procurement},
  year         = {2026},
  note         = {Wedge Verification Economics, Paper \#1. Shipped Week 1.}
}

@book{cover2006elements,
  author    = {Cover, Thomas M. and Thomas, Joy A.},
  title     = {Elements of Information Theory},
  year      = {2006},
  edition   = {2nd},
  publisher = {Wiley-Interscience}
}

@book{grimmett2014probability,
  author    = {Grimmett, Geoffrey and Welsh, Dominic},
  title     = {Probability: An Introduction},
  year      = {2014},
  edition   = {2nd},
  publisher = {Oxford University Press}
}

@article{uesato2022solving,
  author    = {Uesato, Jonathan and Kushman, Nate and Kumar, Ramana and Song, Francis and Siegel, Noah and Wang, Lisa and Creswell, Antonia and Irving, Geoffrey and Higgins, Irina},
  title     = {Solving Math Word Problems With Process-and Outcome-Based Feedback},
  journal   = {arXiv preprint arXiv:2211.14275},
  year      = {2022},
  url       = {https://arxiv.org/abs/2211.14275}
}

@article{hoeffding1963probability,
  author    = {Hoeffding, Wassily},
  title     = {Probability Inequalities for Sums of Bounded Random Variables},
  journal   = {Journal of the American Statistical Association},
  volume    = {58},
  number    = {301},
  pages     = {13--30},
  year      = {1963},
  publisher = {Taylor \& Francis}
}

@article{lecam1973convergence,
  author    = {Le Cam, Lucien},
  title     = {Convergence of Estimates Under Dimensionality Restrictions},
  journal   = {Annals of Statistics},
  volume    = {1},
  number    = {1},
  pages     = {38--53},
  year      = {1973}
}

@book{tsybakov2009introduction,
  author    = {Tsybakov, Alexandre B.},
  title     = {Introduction to Nonparametric Estimation},
  year      = {2009},
  publisher = {Springer},
  series    = {Springer Series in Statistics}
}

@inproceedings{hendrycks2021measuring,
  author    = {Hendrycks, Dan and Burns, Collin and Kadavath, Saurav and Arora, Akul and Basart, Steven and Tang, Eric and Song, Dawn and Steinhardt, Jacob},
  title     = {Measuring Mathematical Problem Solving With the {MATH} Dataset},
  booktitle = {Advances in Neural Information Processing Systems 34, Track on Datasets and Benchmarks},
  year      = {2021}
}

@article{chen2021evaluating,
  author    = {Chen, Mark and Tworek, Jerry and Jun, Heewoo and Yuan, Qiming and others},
  title     = {Evaluating Large Language Models Trained on Code},
  journal   = {arXiv preprint arXiv:2107.03374},
  year      = {2021}
}

@inproceedings{zheng2023judging,
  author    = {Zheng, Lianmin and Chiang, Wei-Lin and Sheng, Ying and Zhuang, Siyuan and Wu, Zhanghao and Zhuang, Yonghao and Lin, Zi and Li, Zhuohan and Li, Dacheng and Xing, Eric P. and Zhang, Hao and Gonzalez, Joseph E. and Stoica, Ion},
  title     = {Judging {LLM}-as-a-Judge with {MT-Bench} and {Chatbot Arena}},
  booktitle = {Advances in Neural Information Processing Systems 36},
  year      = {2023}
}

@article{guan2025rstar,
  author    = {Guan, Xinyu and Zhang, Li Lyna and Liu, Yifei and Shang, Ning and Sun, Youran and Zhu, Yi and Yang, Fan and Yang, Mao},
  title     = {{rStar-Math}: Small {LLM}s Can Master Math Reasoning with Self-Evolved Deep Thinking},
  journal   = {arXiv preprint arXiv:2501.04519},
  year      = {2025},
  url       = {https://arxiv.org/abs/2501.04519}
}

@misc{bhardwaj2026fieldnote2,
  author    = {Bhardwaj, Manu},
  title     = {Cost-correct as the Binding Optimization Target},
  year      = {2026},
  howpublished = {\url{https://ifitsmanu.com/papers/verification-economics-2026}},
  note      = {Field Notes \#2}
}

@misc{bhardwaj2026fieldnote3,
  author    = {Bhardwaj, Manu},
  title     = {The $\alpha$ Asymmetry. {W}hy Verifiers Can Be Smaller Than Generators},
  year      = {2026},
  howpublished = {\url{https://ifitsmanu.com/papers/the-alpha-asymmetry}},
  note      = {Field Notes \#3}
}

@misc{myerson1981optimal,
  author    = {Myerson, Roger B.},
  title     = {Optimal Auction Design},
  journal   = {Mathematics of Operations Research},
  volume    = {6},
  number    = {1},
  pages     = {58--73},
  year      = {1981},
  publisher = {INFORMS}
}

@misc{euaiact2024,
  author    = {{European Parliament and Council}},
  title     = {Regulation (EU) 2024/1689 on Artificial Intelligence (AI Act)},
  year      = {2024},
  howpublished = {Official Journal of the European Union, 12 July 2024},
  note      = {Articles 9, 13, 14, 15. High-risk obligations apply from 2 August 2026}
}

% ============================================================
% Added during paper-02 drafting (verified entries)
% ============================================================

@inproceedings{dasgupta2013crowdsourced,
  author    = {Dasgupta, Anirban and Ghosh, Arpita},
  title     = {Crowdsourced Judgement Elicitation with Endogenous Proficiency},
  booktitle = {Proceedings of the 22nd International Conference on World Wide Web},
  pages     = {319--330},
  year      = {2013},
  publisher = {ACM},
  series    = {WWW '13}
}

@article{holmstrom1979moral,
  author    = {Holmstr{\"o}m, Bengt},
  title     = {Moral Hazard and Observability},
  journal   = {The Bell Journal of Economics},
  volume    = {10},
  number    = {1},
  pages     = {74--91},
  year      = {1979},
  publisher = {RAND Corporation}
}

@inproceedings{karnin2013almost,
  author    = {Karnin, Zohar and Koren, Tomer and Somekh, Oren},
  title     = {Almost Optimal Exploration in Multi-Armed Bandits},
  booktitle = {Proceedings of the 30th International Conference on Machine Learning},
  pages     = {1238--1246},
  year      = {2013},
  series    = {ICML '13}
}

@article{myerson1983efficient,
  author    = {Myerson, Roger B. and Satterthwaite, Mark A.},
  title     = {Efficient Mechanisms for Bilateral Trading},
  journal   = {Journal of Economic Theory},
  volume    = {29},
  number    = {2},
  pages     = {265--281},
  year      = {1983},
  publisher = {Elsevier}
}

@inproceedings{wang2022selfconsistency,
  author    = {Wang, Xuezhi and Wei, Jason and Schuurmans, Dale and Le, Quoc and Chi, Ed and Narang, Sharan and Chowdhery, Aakanksha and Zhou, Denny},
  title     = {Self-Consistency Improves Chain of Thought Reasoning in Language Models},
  booktitle = {International Conference on Learning Representations},
  year      = {2023},
  url       = {https://arxiv.org/abs/2203.11171},
  note      = {arXiv preprint posted 2022.}
}

@article{bhattarai2026rubric,
  author    = {Bhattarai, Manish and Boureima, Ismael and Ranasinghe, Nishath Rajiv and Pakin, Scott and O'Malley, Dan},
  title     = {Rubric-Grounded {RL}. {S}tructured Judge Rewards for Generalizable Reasoning},
  journal   = {arXiv preprint arXiv:2605.08061},
  year      = {2026},
  url       = {https://arxiv.org/abs/2605.08061}
}