experiments: freeze Qwen V8 verification design - #4
Draft
atimics wants to merge 4 commits into
Draft
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
Why
V7 qualified preservation and native full-sequence C recurrence but deliberately did not test whether installed sidecar memory helps retrieval. V8 isolates that capability effect with BM25, shuffled-index, and typed-refusal controls. Formal inputs are still pending and cloud execution remains unauthorized.
The full suite also exposed platform-sensitive baseline assertions that prevented PR 31 from acting as a clean independent verification branch. The fixes preserve the underlying scientific contracts while removing BLAS, compiler, scheduler, and duplicate-basename accidents.
Impact
This is a design and verification change only. It launches no compute and does not authorize the one formal V8 attempt. A later stacked evidence PR must bind implementation and dataset identities through ilxyr admission.
Validation