Add RESULTS.md
Browse files- RESULTS.md +2 -0
RESULTS.md
CHANGED
|
@@ -49,3 +49,5 @@ Operation correct 11/14; decided at the fixed threshold 13/14, 2 wrong. The grou
|
|
| 49 |
## What went wrong along the way
|
| 50 |
- First run: replayed gen.py draws in the wrong order (assertion caught it; fixed). Second: operation names were not quoted in the JSON (0% valid; fixed). Third: the validator labelled valid UNSUPPORTED outputs with a failure reason (counts only) and the grammar could dead-end by skipping a required key; both fixed, grounded stencil added. Numbers above are from the final run only.
|
| 51 |
- Each re-run on MPS gives slightly different numbers (training is not bit-exact).
|
|
|
|
|
|
|
|
|
| 49 |
## What went wrong along the way
|
| 50 |
- First run: replayed gen.py draws in the wrong order (assertion caught it; fixed). Second: operation names were not quoted in the JSON (0% valid; fixed). Third: the validator labelled valid UNSUPPORTED outputs with a failure reason (counts only) and the grammar could dead-end by skipping a required key; both fixed, grounded stencil added. Numbers above are from the final run only.
|
| 51 |
- Each re-run on MPS gives slightly different numbers (training is not bit-exact).
|
| 52 |
+
|
| 53 |
+
- After execution, one self-check question in the closing markdown cell was reworded in both the clean and the executed notebook, without re-running. No code changed.
|