These source descriptions are retained from the reader’s “Reading sources and review boundaries” chapter. Their selection does not admit every result in the source works.
Entries follow the retained bibliography source. Citation keys keep references stable without relying on older generated bibliography numbering. These links do not establish what a cited source proves.
GA
Komorebi P. Grounded Abstraction: Identifiability, Representation Change, and the Limits of Learning. Version 1.0.0, 9 October 2026. Exact source archive identified in core 0.1, whose source-suite replay receipts are retained historically.
MU
Komorebi P. Machine Understanding: Representation, Explanation, and Transfer. Version 1.0.0, 8 October 2026. Exact source archive identified in core 0.1, whose source-suite replay receipts are retained historically.
SII
Komorebi P. Self-Improving Intelligence: Representation, Discovery, and Recursive Revision. Version 1.0.0, 8 October 2026. Exact source archive identified in core 0.1, whose source-suite replay receipts are retained historically.
MS
Komorebi P. Machine Societies: A Theory of Persistent Plural Computational Organization. Version 1.0.0, 8 October 2026. Exact source archive identified in core 0.1, whose source-suite replay receipts are retained historically.
SR
Komorebi P. Sufficient Resolution. Standardized traditional paper, 8 October 2026. Selected split, hidden-return, and factorization arguments reviewed from the source text and reproved here. Their selected formal counterparts are identified in the companion.
SRWT
Komorebi P. Stratified Relational Workspace Theory. Collected source manuscript as identified in the original compendium catalogue. Only the elementary reconstruction relationship used here is admitted. Full dynamics, emergence, persistence, and identity claims are not re-audited by this selection.
LSM
Large Signal Model Foundations, edition 0.4.0. Selected packet-positivity, joint finite closure, and whole-law/conditioning arguments: Propositions 9, 12, 30, 43 and 44. Exact source PDF and selected-page hashes are in the admission record. This book does not import the full observable-learning, cone-discovery, or software claims.
PRIQ
Hypergraph Lumpability and Bayesian Refinement, version 0.1.4. Selected positive normalization and finite filtering composition: Theorems 5.2, 5.5–5.6, 6.1 and 6.3, plus the posterior-error context in Section 9. The nonlinear analytic and hyperedge results are outside this admission.
AVOC
AVOC: Artifact Value, Guarded Operations, and Calibrated Planning. Traditional publication edition based on formal v0.41.0. Selected conditioning, projected stochastic value, and finite planning proof mechanisms: Theorems 3.6, 4.5 and 9.2. Their use here is a selected finite specialization. The formal companion identifies the corresponding core results; it does not claim a theorem-level refinement of the complete host implementation.
KLC
Classical partially observed planning. Leslie Pack Kaelbling, Michael L. Littman and Anthony R. Cassandra. Planning and acting in partially observable stochastic domains. Artificial Intelligence 101 (1998), 99–134. Author-hosted manuscript and publisher record checked for the belief-state and finite-policy context. This reference locates the established planning framework, not a novelty claim for the recursions here.