docs(RESULTS): engram verdict — 4.6679, not separated - #223
Merged
Merged
Conversation
added 3 commits
September 29, 2026 16:31
The vanilla loader drops _engram.* (the PKM lesson: injected parameters need the injected loader) — the first eval of run-013 was scoring a backbone missing a component it trained with. That number stands as the no-memory CONTROL; the gate needs the table in the forward pass. load_student_with_engram attaches first, loads the full state strictly except fresh-zero engram params (loud on anything else); evaluate_der uses it for engram specs.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The lexical-memory run completed its gate: 4.6679 full-set (n=1200, canonical labels sha e70ce991, with-table eval via load_student_with_engram after the dropped-table catch). Delta vs 2.1 (+0.10pp) does not separate under the paired bootstrap — FLAT. The architecture ledger closes: every student-side lever (depth, memory, routing, soup, on-policy) is now measured and recorded; 2.1 (4.5701) stands as the frontier.