References

Bibliography

1. [1]

   John C. Baez, Kenny Courser. Coarse-Graining Open Markov Processes. Theory and Applications of Categories. Volume 33. Number 39. Pages 1223–1268. 2018. arXiv:1710.11343.

2. [2]

   Nix Barnett, James P. Crutchfield. Computational Mechanics of Input–Output Processes: Structured Transformations and the $\epsilon$-Transducer. Journal of Statistical Physics. Volume 161. Number 2. Pages 404–451. 2015. doi:10.1007/s10955-015-1327-5. arXiv:1412.2690.

3. [3]

   Leonard E. Baum, Ted Petrie, George Soules, Norman Weiss. A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains. The Annals of Mathematical Statistics. Volume 41. Number 1. Pages 164–171. 1970. doi:10.1214/aoms/1177697196.

4. [4]

   Yoshua Bengio, Paolo Frasconi. Diffusion of Context and Credit Information in Markovian Models. Journal of Artificial Intelligence Research. Volume 3. Pages 249–270. 1995. arXiv:cs/9510101.

5. [5]

   Byron Boots, Sajid M. Siddiqi, Geoffrey J. Gordon. Closing the Learning-Planning Loop with Predictive State Representations. 2009. arXiv:0912.2385. Inspected author-deposited preprint, version 1.

6. [6]

   Gavin C. Cawley, Nicola L. C. Talbot. On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation. Journal of Machine Learning Research. Volume 11. Pages 2079–2107. 2010. https://www.jmlr.org/papers/v11/cawley10a.html.

7. [7]

   DES-Lab. AALpy: Stochastic Passive Learning Source Code. https://github.com/DES-Lab/AALpy/tree/master/aalpy/learning_algs/stochastic_passive. Accessed 2026-09-29. Alergia.py and CompatibilityChecker.py. Methodological reference; the study executed a local adaptation, not the upstream package.

8. [8]

   Cynthia Dwork, Vitaly Feldman, Moritz Hardt, Toniann Pitassi, Omer Reingold, Aaron Roth. Generalization in Adaptive Data Analysis and Holdout Reuse. 2015. doi:10.48550/arXiv.1506.02629. arXiv:1506.02629.

9. [9]

   Daniel Gebler, Simone Tini. Compositionality of Approximate Bisimulation for Probabilistic Systems. Electronic Proceedings in Theoretical Computer Science. Volume 120. Pages 32–46. 2013. doi:10.4204/EPTCS.120.4. arXiv:1307.7442.

10. [10]

    Daniel Hsu, Sham M. Kakade, Tong Zhang. A Spectral Algorithm for Learning Hidden Markov Models. Journal of Computer and System Sciences. Volume 78. Number 5. Pages 1460–1480. 2012. arXiv:0811.4413.

11. [11]

    Michael L. Littman, Richard S. Sutton, Satinder Singh. Predictive Representations of State. Advances in Neural Information Processing Systems. Volume 14. 2001. https://proceedings.neurips.cc/paper_files/paper/2001/file/1e4d36177d71bbb3558e43af9577d70e-Paper.pdf. NIPS 2001; author list verified against the paper PDF.

12. [12]

    Hua Mao, Yingke Chen, Manfred Jaeger, Thomas D. Nielsen, Kim G. Larsen, Brian Nielsen. Learning Markov Decision Processes for Model Checking. Electronic Proceedings in Theoretical Computer Science. Volume 103. Pages 49–63. 2012. doi:10.4204/EPTCS.103.6. arXiv:1212.3873.

13. [13]

    Hua Mao, Manfred Jaeger. Learning and Model-Checking Networks of I/O Automata. Proceedings of the Asian Conference on Machine Learning. Series Proceedings of Machine Learning Research. Volume 25. Pages 285–300. 2012. https://proceedings.mlr.press/v25/mao12.html.

14. [14]

    Jeremy Rodgers. Identifying Binary Realizations from Intervention Laws: Certificates, Recoding Obstructions, and a Bounded SPC-2/IIT Comparison. Zenodo. Version 1.1-RC1. 2026-09-30. doi:10.5281/zenodo.23075828. Companion preprint, Paper 4.

15. [15]

    Jeremy Rodgers. Paper 3 Evidence, Attribution, and Claim Freeze. 2026-09-29. Versioned source snapshot containing RRI and OII-1–4 evidence, protocols, scores and claim ledgers. Preserved unchanged in the manuscript supplement; archive hash in SOURCE_INPUT_MANIFEST.json.

16. [16]

    Jeremy Rodgers. Relational Boundaries and Awareness Localization: Robustness, Composition, and Identification Limits. Zenodo. Version 1.0. 2026-09-29. doi:10.5281/zenodo.23075822. Companion preprint, Paper 2; supplied source snapshot retained in the present supplement.

17. [17]

    Jeremy Rodgers. Shadow Theory and Consciousness: Awareness, Perspectival Realization, and the Source-to-Experience Problem. Zenodo. Version 2. 2026-09-20. doi:10.5281/zenodo.22853774. https://www.everythingequation.com/consciousness/monograph. Publication edition.

18. [18]

    Brendan van Rooyen, Robert C. Williamson. Le Cam meets LeCun: Deficiency and Generic Feature Learning. 2014. doi:10.48550/arXiv.1402.4884. arXiv:1402.4884.

19. [19]

    Paul K. Rubenstein, Sebastian Weichwald, Stephan Bongers, Joris M. Mooij, Dominik Janzing, Moritz Grosse-Wentrup, Bernhard Schölkopf. Causal Consistency of Structural Equation Models. 2017. arXiv:1707.00819. Proceedings of UAI 2017.

20. [20]

    Junya Shijubo, Masaki Waga, Kohei Suenaga. Probabilistic Black-Box Checking via Active MDP Learning. 2023. doi:10.48550/arXiv.2308.07930. arXiv:2308.07930. Preprint accepted to EMSOFT 2023.

21. [21]

    Satinder Singh, Michael R. James, Matthew R. Rudary. Predictive State Representations: A New Theory for Modeling Dynamical Systems. Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence. Pages 512–519. 2004. arXiv:1207.4167. UAI 2004; author-deposited repository version uploaded in 2012.

22. [22]

    Martin Tappler, Bernhard K. Aichernig, Giovanni Bacci, Maria Eichlseder, Kim G. Larsen. L*-Based Learning of Markov Decision Processes (Extended Version). 2019. doi:10.48550/arXiv.1906.12239. arXiv:1906.12239.