Archive readout-aligned geometry finding (CLOSED, not shipped) - #114
Merged
Conversation
…alsified finding PR #113's readout-aligned geometry profile is not shipped — the behavioural head-to-head FALSIFIED its premise (readout-alignment HURTS the co-firing Spearman 0.640 -> 0.27; full rank just recovers baseline; co-firing is encoder-side, the readout subspace is decode-side -> vindicates the raw-decoder geometry). Archive the proposal + spec as a research record (spec delta NOT applied to canonical specs; implementation stays on the closed PR branch) and keep the head-to-head result in behavioural-scaleup-probe.md so the finding is on main. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Archives the closed PR #113 (readout-aligned geometry) as a research record — proposal + spec moved to
openspec/changes/archive/, and the head-to-head result kept inbehavioural-scaleup-probe.md. No implementation code, no behaviour change (the spec delta is NOT applied to canonical specs; the implementation stays on the closed #113 branch).Finding: readout-alignment HURTS the co-firing Spearman (0.640 → 0.27; full-rank recovers 0.640 because it's a rotation) — co-firing is encoder-side, the readout subspace is decode-side. This vindicates Polygram's raw-decoder geometry for the co-firing claim.
🤖 Generated with Claude Code