Sources

Sources

These works supply inspiration, mathematical tools, or nearby prior art. They do not establish this program's claims unless a page says exactly what is inherited.

Normative pragmatics and dialogue

• Robert B. Brandom. Making It Explicit: Reasoning, Representing, and Discursive Commitment. Harvard University Press, 1994. Author-hosted Part One. Used for commitment/entitlement, perspectival scorekeeping, and default-and-challenge structure.
• Paul Lorenzen and Kuno Lorenz. Dialogische Logik. Wissenschaftliche Buchgesellschaft, 1978. Bibliographic record. Nearby dialogue-logic background; not a source of the program's scorekeeping construction.
• John Martin Fischer and Mark Ravizza. Responsibility and Control: A Theory of Moral Responsibility. Cambridge University Press, 1998. Publisher page and DOI. Background for reasons-responsive mechanisms.

Learning and bounded reasoning

• Scott Garrabrant, Tsvi Benson-Tilsen, Andrew Critch, Nate Soares, and Jessica Taylor. “Logical Induction.” 2016. arXiv:1609.03543. Source for logical inductors, markets, traders, and self-trust results used by the deference line.
• Caspar Oesterheld, Abram Demski, and Vincent Conitzer. “A Theory of Bounded Inductive Rationality.” In Proceedings of TARK 2023, EPTCS 379 (2023): 421–440. Published paper and DOI. Supplies the estimating-agent setting, the no-overestimation and hypothesis-coverage criterion, and the guaranteed-payoff consequence the decision-theory-bill round reads on a gated decision-problem sequence; its myopia is the recorded obstacle to endogenous admissibility, and nothing from it is re-proved here.
• Kevin Dorst, Benjamin A. Levinstein, Bernhard Salow, Brooke E. Husic, and Branden Fitelson. “Deference Done Better.” Philosophical Perspectives 35, no. 1 (2021): 99–150. Publisher page and DOI. Source for the decision-based account of epistemic deference and the Total Trust/Value target inherited by the deference line.
• Avrim Blum and Yishay Mansour. “From External to Internal Regret.” Journal of Machine Learning Research 8 (2007): 1307–1324. Official JMLR page. Source for the modification-regret reduction used by the finite learning interface.
• Yossi Azar, Ashish Chiplunkar, Shay Kutten, and Noam Touitou. “Set Cover with Delay—Clairvoyance Is Not Required.” LIPIcs 173 (ESA 2020), Article 8. Published paper and DOI. Supplies the repeated-purchase request, action-cost, and delay scheduler class for the restricted dynamic inquiry embedding; it supplies no normative or certified-service semantics.
• Sungjin Im, Viswanath Nagarajan, and Ruben van der Zwaan. “Minimum Latency Submodular Cover.” ACM Transactions on Algorithms 13, no. 1 (2016), Article 13. Publisher page and DOI. Supplies the metric path, multiple submodular objectives, and sum of cover times for fixed dockets.
• Daniel Golovin and Andreas Krause. “Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization.” Journal of Artificial Intelligence Research 42 (2011): 427–486. Primary paper. Supplies adaptive coverage, self-certification, and diminishing-returns tractability conditions under a fixed realization model and prior; adaptive submodularity is not treated as legitimacy.
• Andrew Guillory and Jeff Bilmes. “Interactive Submodular Set Cover.” In Proceedings of ICML 2010, 415–422. Primary paper. Supplies a worst-case finite query/response coverage class with pointwise-submodular objectives; it does not validate the hypothesis class or service objective.

Corrigibility

• Nate Soares, Benja Fallenstein, Eliezer Yudkowsky, and Stuart Armstrong. “Corrigibility.” In AAAI Workshops: Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, TX, January 2015. Author-hosted PDF. Source for the four informal requirements of §1.1, the five shutdown desiderata of §2, and the utility-indifference failures (Theorems 1, 2 and 6, and “managing the news”) the corrigibility note maps against; nothing of its utility-mixing formalism is inherited.
• Max Harms. CAST: Corrigibility as Singular Target, a sequence, June 2024, with the update “Serious Flaws in CAST”, November 2025. Sequence. Source for the working definition (“robustly acts to empower the principal to freely fix flaws”), the singular-target and attractor-basin claims, and the scalar power formalism whose failure the corrigibility note reproduces in a two-value world; the order-valued authority profile is a different object, not a repair of it.

Reason maintenance and default reasons

• Jon Doyle. “A Truth Maintenance System.” Artificial Intelligence 12 (1979): 231–272. Publisher page and DOI90008-0). Supplies the justification/node architecture, in/out statuses, non-monotonic justifications, and dependency-directed backtracking that the reason-state work compares against; its conflation of dependency recording with belief choice is what that work rejects.
• Johan de Kleer. “An Assumption-based TMS.” Artificial Intelligence 28 (1986): 127–162. Publisher page and DOI90080-9). Supplies assumption environments, labels over multiple simultaneous contexts, and nogood recording, read here as cached hypothetical-support queries under a fixed incompatibility structure.
• John F. Horty. Reasons as Defaults. Draft #2, August 16, 2006. Author page. Supplies triggered/conflicted/defeated defaults, reasons as premises of triggered defaults, and variable-priority default theories with priorities in the object language; its proper-scenario theory occupies the stance-selection seat this program assigns to the normative learner.

Imprecise probability and argumentation

• Peter M. Williams. “Notes on Conditional Previsions.” Technical report, University of Sussex, 1975; revised in International Journal of Approximate Reasoning 44, no. 3 (2007): 366–383. DOI. Background for coherent conditional previsions and desirable-gamble readings.
• Peter Walley. Statistical Reasoning with Imprecise Probabilities. Chapman & Hall, 1991. Publisher series catalog. Background for lower previsions and imprecise probability.
• Henry Prakken. “Probabilistic Strength of Arguments with Structure.” In Proceedings of the Sixteenth International Conference on Principles of Knowledge Representation and Reasoning, 158–167. AAAI Press, 2018. Author paper. Nearby prior art for structured probabilistic support and attack.
• Anthony Hunter, Sylwia Polberg, and Matthias Thimm. “Epistemic Graphs for Representing and Reasoning with Positive and Negative Influences of Arguments.” Artificial Intelligence 281 (2020): 103236. arXiv:1802.07489. Nearby prior art for graded epistemic support and attack graphs.