v3 coverage
All original required sections remain in MANUSCRIPT.md. Section 19.9 adds C1-C6; 29.7-29.9 add E10-E11; 30.2 states the new research opportunity; 33 gives current status. The map below describes the retained foundational sections.
Coverage of the 41 research directives
All required topics are addressed; coverage is not equivalent to experimental completion. Sections refer to MANUSCRIPT.md and the PDF.
| User directive | Sections | Evidence boundary |
|---|---|---|
| I Central research question | 2, 4, 5 | Formal sufficiency; compact real-time implementation open. |
| II State contents | 5, 8 | Explicit typed logical belief and ownership. |
| III World-space memory | 5, 8, 9, 29 | Atlas witness; no general 3D runtime. |
| IV Scene-state sufficiency | 4, 5, 15 | Exact abstract/linear results. |
| V Totality input | 15, 25, 29 | Channel economics and correlated-signal witness. |
| VI Chronoscopic training | 11, 22 | Correct objective and causal limit; neural training unexecuted. |
| VII Counterfactual cameras | 12, 24, 25 | Design and linear identifiability; full experiment proposed. |
| VIII Unified decoding | 10, 18, 27 | Shared objective and contracts; no full task validation. |
| IX Continuous-time model | 10, 19, 21 | Hybrid model; causal limits explicit. |
| X Object permanence | 8, 9, 29 | Canonical identity witness; uncertain identity open. |
| XI Consolidation | 7, 8, 16 | Evidence-statistic rules; bounded storage. |
| XII Plasticity | 7, 16 | Covariance/Riccati mechanism and change reopening. |
| XIII Dormant pathways | 17, 25 | Optional trained specialists; no speculative automatic benefit. |
| XIV Phase routing | 17 | Smooth admissible mixture; deep manifold claim not required. |
| XV Active loop | 13, 21, 23 | Exact local score; closed-loop control design. |
| XVI Long-horizon sample value | 13, 29, 30 | Local derivation and linear witness, policy assumptions. |
| XVII Physics constraints | 14, 19 | Validity, passivity, uncertainty, and limitations. |
| XVIII Optical G-closure | 14 | Definition, outer relaxation, restricted realizable inner family. |
| XIX Transport modes | 14.3 | Fixed-transport linearity; changing geometry limitations. |
| XX State consistency | 10, 19 | Conditional bounds; real visibility discontinuities retained. |
| XXI Anti-hallucination | 8, 19, 24 | Reliability/fallback contract, calibration protocol. |
| XXII Belief correction | 7, 8, 26 | Local invalidation, provenance, contradiction hypotheses. |
| XXIII Compute budget | 20, 21 | Explicit estimates; no measured GPU throughput. |
| XXIV Multirate system | 16 | Restricted optimal periodic interval and event override. |
| XXV Formal theory | 5, 11-14, 18, 19 | Ten scoped propositions with proofs. |
| XXVI Information economics | 13, 15, 30 | Common future-loss value, not a first-in-history claim. |
| XXVII Pipeline comparison | 3, 27 | Includes joint-network and world-cache baselines. |
| XXVIII Failure modes | 26, 29 | Full matrix and measured adverse stale-memory result. |
| XXIX Curriculum | 22 | Staged protocol plus matched-compute curriculum ablation. |
| XXX Dataset/simulation | 24 | Executed toy generator and full-renderer dataset specification. |
| XXXI Ablations | 25 | Fifteen decisive comparisons and oracle-access controls. |
| XXXII Metrics | 24 | Perception, time, identity, uncertainty, cost, latency. |
| XXXIII Target advance | 2, 27, 28, 33 | Falsifiable hypothesis; not claimed achieved universally. |
| XXXIV Minimal architecture | 5, 6, 30 | Query closure and authoritative engine ownership. |
| XXXV Second-order advance | 30 | Joint evidence/retention/refresh allocation interface. |
| XXXVI All 33 output categories | 1-33 | Complete standalone specification and limited executed core. |
| XXXVII Novelty discipline | 3, references | Primary sources including close 2026 antecedents. |
| XXXVIII Rigor labels | 2, 29, 33 | Proof / assumptions / hypothesis / prediction / speculation. |
| XXXIX Multi-objective priorities | 4, 25, 27 | Matched-budget Pareto tests, no average-only claim. |
| XL Final conceptual attack | 5.3, 13.3-13.4, 30.1 | Nuisance closure, retention/covariance distinction, query synergy. |
| XLI Status and completeness | 33, STATUS.json | Eleven separate subjective progress estimates. |
Version 2 evidence update
All 33 output categories and 41 research directives remain covered in the full manuscript. The implemented scope now includes a trained visibility prior, a finite-light physical renderer, corrected persistent memory and an active-revision follow-up. See Sections 19.4-19.8 and 29.4-29.6. Coverage is not empirical completion: the original chronoscopic, counterfactual, full task-sharing, continuous-time and GPU comparisons remain unexecuted.