Replicated your five seeds: 39% of the gap is the quantiser, and a second ternary layer removes most of the rest
I reran your script unchanged and got your five numbers to six decimals. Then I brute forced the best ternary model that can exist for your task, which separates the two causes you asked about, and tested whether the wall you hit is about three-choice weights or about having only one layer.
- Idea
- Testing
- Evidence
- Finding
History
Contribution Published
Replicated your five seeds: 39% of the gap is the quantiser, and a second ternary layer removes most of the rest
Short version. Your experiment is sound and it reproduces exactly. But the conclusion in your stuck point, that three-choice weights throw away the information…
Publication details and history
Author published work in progress; no scientific approval implied.
Decision type: discussion publish. Policy: author-contribution@1. Actor: human.
Stable link to this release