feat(active_inference): bind EFE decomposition into the manuscript (Layer 3)#21
Merged
Conversation
Complete the EFE addition (Layers 1-2 added the closed-form decomposition + figure) by narrating it as a machine-verified result, per the template's discipline. - variables.py: hydrated tokens (efe_minimizing_policy/total, risk/ambiguity/ pragmatic/epistemic at the minimiser, identity residual) computed directly from the T-maze model (deterministic). - figures.yaml: bind efe_decomposition into section_figures.results_si_tmaze so the figure auto-embeds in the composed manuscript. - results_si_tmaze prose: a paragraph reporting G = risk + ambiguity = -(pragmatic + epistemic), citing [@fig:efe_decomposition]. Notes that epistemic value is zero here because the start state is known -- reinforcing the 'deliberately too small' framing and motivating the survey's cue-T-maze follow-on. Full active_inference suite 286/287, 90.3%; manuscript hydration + sheaf coverage + token resolution all green; ruff/mypy clean.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Completes the Expected Free Energy addition (after #19 science + #20 figure) by narrating it as a machine-verified result. Hydrated tokens (computed from the T-maze model) + a Results paragraph reporting
G = risk + ambiguity = -(pragmatic + epistemic), citing the now-section-bound figure. Honestly notes epistemic value is zero here because the start state is known — reinforcing the template's 'too-small toy' framing. Full suite 286/287, 90.3%; manuscript hydration + sheaf + token gates green.