RES — H2 is NOT REJECTED: the best estimation config (7B, MAE=1.86 SP) does not…
H2 is NOT REJECTED: the best estimation config (7B, MAE=1.86 SP) does not significantly beat the historical-mean baseline (2.03 SP; delta=0.17 SP; Wilcoxon p=0.104; r=-0.16; N=100); the improvement is below the 0.5 SP relevance threshold and the CI includes zero.
Source: PUMA project documentation · Traceability: corpus unit
MEM-047· Confidence: verified-at-primary-source