docs(EXPERIMENTS): GKD rung registered/armed - #147
Merged
Conversation
…re any launch The last untested reading of the domain attribution; spec design, gate (4.5218), and prediction (4.30-4.65) pre-registered. Launch is the owner call. Also records the run-006 re-eval discrepancy (5.0821 vs canonical 4.8218) so the next verdict compares within one eval pass.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pre-registration for the GKD on-policy distillation rung (TODO.substantiate/03): hypothesis, control-verbatim design, gate <=4.5218, prediction 4.30-4.65, all registered BEFORE any launch (which is the owner call). Includes the run-006 canonical-vs-reeval note (4.8218 ledger vs 5.0821 auto-chain print) so the verdict compares within one eval pass.