Parsec v6 heatmap — v6_g2_e1 (sealed test split)

66 held-out test tasks, never shown to the optimizer across all 6 iterations · seed (unmodified prompt bundle) vs. the run's final champion cand_0005, n=10 trials/task, scored exactly once after the champion was fixed by iteration 5's acceptance on the hidden confirm split. Unlike v4/v5's heatmaps, there is no per-candidate column here: only the seed and the final champion were ever scored on test — scoring an intermediate, later-superseded candidate would have burned the one-time test seal for no purpose. For the per-ITERATION view (every candidate's F-split screen and C-split decision), see summary.md.
Categories are never pooled across the F/C/test boundary. This page is test-split only. The optimizer never saw these 66 tasks' ids or scores during the run — F (feedback, 67 tasks) and C (confirm, 67 tasks, hidden from the optimizer but used for the accept/reject gate) are separate, non-overlapping splits with no per-task ledger of their own (see summary.md for why).
0.0 0.5 1.0 cloud cost icinga platform Click a column header to sort.