H by rule (mean over the two training seeds; synthetic = mean of the 5 LODO datasets); delta vs HMM 0.998 of the same replicate [all4] fam AASD Carta2026 synthetic dAASD dCarta2026 dsynthetic rule HMM 0.95 0.1389 0.3197 0.5845 0.0331 0.0141 -0.0351 HMM 0.998 0.1058 0.3056 0.6196 0.0000 0.0000 0.0000 V1 0.1033 0.2553 0.2133 -0.0025 -0.0503 -0.4063 V2 0.1021 0.1421 0.6409 -0.0037 -0.1635 0.0213 [s01] fam AASD Carta2026 synthetic dAASD dCarta2026 dsynthetic rule HMM 0.95 0.1338 0.3238 0.5749 0.0356 0.0138 -0.0362 HMM 0.998 0.0981 0.3100 0.6111 0.0000 0.0000 0.0000 V1 0.0978 0.2501 0.2021 -0.0004 -0.0599 -0.4090 V2 0.0951 0.1362 0.6325 -0.0030 -0.1738 0.0214 [s23] fam AASD Carta2026 synthetic dAASD dCarta2026 dsynthetic rule HMM 0.95 0.1422 0.3070 0.5820 0.0353 0.0124 -0.0365 HMM 0.998 0.1069 0.2946 0.6185 0.0000 0.0000 0.0000 V1 0.1073 0.2599 0.1867 0.0004 -0.0347 -0.4318 V2 0.1048 0.1478 0.6406 -0.0021 -0.1467 0.0221 Per training seed (all4): H of AASD / Carta / synthetic fam AASD Carta2026 synthetic rule seed HMM 0.95 -1 0.1389 0.3197 0.5845 HMM 0.998 -1 0.1058 0.3056 0.6196 V1 0 0.1061 0.2623 0.2041 1 0.1005 0.2483 0.2225 V2 0 0.0975 0.1296 0.6431 1 0.1067 0.1546 0.6387 Per dataset (all4), V1 vs HMM 0.998 (H / Acc / SDT) H Acc SDT rule HMM 0.998 V1 HMM 0.998 V1 HMM 0.998 V1 ds AASD 0.106 0.103 52.805 52.737 4.875 5.257 AVGC 0.533 0.027 68.854 50.697 4.352 38.535 Carta2026 0.306 0.255 59.241 57.413 7.625 4.344 DTU 0.668 0.549 75.833 69.126 3.238 0.989 KUL 0.648 0.115 74.832 53.232 3.209 41.147 UHD 0.624 0.091 73.547 52.474 3.750 40.757 USTC 0.625 0.284 73.455 58.846 2.723 18.297 Per dataset (all4), V2 vs HMM 0.998 (H / Acc / SDT) H Acc SDT rule HMM 0.998 V2 HMM 0.998 V2 HMM 0.998 V2 ds AASD 0.106 0.102 52.805 52.702 4.875 5.029 AVGC 0.533 0.563 68.854 70.423 4.352 5.637 Carta2026 0.306 0.142 59.241 53.884 7.625 10.188 DTU 0.668 0.654 75.833 74.801 3.238 2.293 KUL 0.648 0.678 74.832 76.569 3.209 3.018 UHD 0.624 0.663 73.547 75.837 3.750 3.672 USTC 0.625 0.647 73.455 74.826 2.723 3.730