RES — gemma4:e2b · prioritization (Phase-B cell)
Phase-B sweep cell — gemma4:e2b on the prioritization scenario (N=100, seed=42, temp=0.0, single strategy).
Invalid result: parse_failure_rate = 1.0 (≥0.98) — the model did not produce usable parseable output; this cell is the sunk-cost example, not a real score.
Source: PUMA project documentation + raw benchmark results · Traceability: PUMA-023,PUMA-026 · Confidence: verified-at-primary-source