rufimelo's picture
Update Space to n=5 run (2026-07-19): ranking-led report, /30 scores, 30 runs, appendix at bottom
3dd0b08 verified
|
Raw
History Blame Contribute Delete
331 Bytes

Off-vs-on context experiment — acceptance by budget

Cell = pass-rate (accepted / trials), mean of mean_score.

budget off (no PDF) on (with PDF)
200 4/5 pass, mean 3.91 4/5 pass, mean 3.73
300 2/5 pass, mean 3.57 1/5 pass, mean 3.57
400 3/5 pass, mean 3.69 2/5 pass, mean 3.85