Skip to content

docs: d768 verdict — width-cut closure complete #102

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ronaldtse merged 1 commit into from
Aug 31, 2026
Merged

docs: d768 verdict — width-cut closure complete #102

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions docs/RESULTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,3 +412,14 @@ monotone: 33M/74.7 - 29M/83.0 - 190M/7.4 - 300M/5.3 - 300M/4.8
(teacher 2.28-2.58). Browser-tier decision (user): ship
layerdrop-int4 (~95MB, ~7.5 DER with int4 flip risk ungated) as the
lite rung, or hold the tier at 2.0-int8 (264MB, 4.82).

## ara-diac-small-d768 — gentle stitch fails too: the width-cut closure is complete (2026-08-31)

The untested 2x ratio (d1472->d768, ~105M, Muon, same r7 labels,
10,995 steps, train CE recovered to 0.95): 300-subset DER 78.23
(teacher in-run 1.2887). SVD width-stitching now fails at BOTH tested
ratios (3.8x: 82.96; 2x: 78.23) while the depth cut works (7.44).
The law sharpens: the pretrained WIDTH is load-bearing - projection
destroys the representation at any compression; depth is the
compressible axis. First verdict carrying the label-provenance hash
(labels sha256 e70ce991..., 137.2MB recorded in final_eval.json).
Loading