RES — gemma3:4b · triage (Phase-B cell)
Phase-B sweep cell — gemma3:4b on the triage scenario (N=100, seed=42, temp=0.0, single strategy).
F1-macro = 0.6021 (parse_failure_rate = 0.0).
Source: PUMA project documentation + raw benchmark results · Traceability: PUMA-023,PUMA-026 · Confidence: verified-at-primary-source