Machine-Native ReasoningReading edition

Result and source map

Reading tools
Reading libraryFind statementsInspect Lean
Switch work

Saved reading

Read side by side

Start reading

Resources & source

Read and explore

Proofs and implementation

About this work

Other resources

Original TeX with line links · Download TeX

The wording and mathematics follow the retained manuscript. This reading format does not add a proof review or extend Lean coverage.

Skip contents and start reading

Result and source map

The following map gives the role of each admitted formal result. Exact source anchors, excerpts, hashes, and detailed hypothesis review are in the accompanying machine-readable ledger and review files. Source relationships do not imply that every source page is admitted.

ResultPreserved objectSource relationship
1.1A target determined by an available recordGA; shared fibre criterion.
1.2Every declared finite continuationGA and MU, consolidated.
2.1Exact split encoding and named composition lossSR, split and hidden-return identities.
2.3Source operations and matched readoutsMU; OSL and Neuralese use the same conditional principle.
2.4One output method across candidate dynamicsGA, common observable quotient.
2.5Probability interpretation of a complete packet familyLSM, positive packet criterion.
3.1Every admitted future set correctionGA, correction-signature theorem.
3.2Exact partition-evidence memory cardinalityGA, occupancy corollary.
3.4All posterior updates in the actual reporting chainMU, finite channel factorization.
3.5Coarsest partition closed for prediction and updateLSM and PRIQ, finite closure.
3.6Joint next-state/report law, posteriors and feedbackPRIQ and AVOC, selected composition.
3.8Whole-history error and conditioning costLSM, law and normalization bounds.
4.1One bounded-loss decision calculationGA and MU, specialized common-risk bound.
4.2One artifact under fixed recipient proceduresMU, intersection and covering criterion.
5.1One executable tree under all declared budgetsMU and SII, finite Pareto synthesis.
5.3A complete optimality claim for a checked treeSII, binary singleton-repair scope.
5.4One optimal finite-horizon expected-cost inquiryAVOC, projected values and finite plans.
5.6Uniform policy evaluation before selectionLSM/AVOC, common-law specialization.
6.1Exact finite candidate rejection and acceptanceSII, finite counterexample refinement.
6.2The same proposed ASTs and teacher transcriptSII, sound equations and ordered quotient.
6.4The same completed ordered diagnostic searchSII, capacity and streaming arguments.
7.1Applicability of dependency-bound witnessesSII, complete declared dependency graph.
7.3Gains under one complete additive ledgerSII, price-relative dominance.
7.4Conditional false-acceptance controlSII, adaptive lineage error budget.
8.1A target from jointly accessible linear recordsSR and SRWT, target-relative specialization.
8.2Legal action availability and label historiesMS, exact governance quotient.
8.3Continued operation with an ending policyMS, fully observed finite specialization.
Source and conversion record

Source SHA-256: c2ef44767a242021cc573bbba7bb0c95df74a704c99cf992d2eff0a396838593

Unsupported prose commands stop the build. The mathematical expression sequence is checked against the source, with manuscript macros expanded for display.

Conversion records

Notation in Machine-Native Reasoning

Look up a symbol without leaving this chapter. Select text before opening help to search for it.

Search this work’s notation.

    Symbols can have different meanings in different passages. Read each result in its own context.

    Open the full notation index