EXP008d-3seed.md objective,seed 42,seed 43,seed 44 ---,---,---,--- fixed pointwise,p25-exp008b-curriculum-pointwise-s42,p26-exp008d-curriculum-pointwise-s43,p26-exp008d-curriculum-pointwise-s44 pointwise + ratio 0.02,p25-exp008c-curriculum-ratio002-s42,p26-exp008d-curriculum-ratio002-s43,p26-exp008d-curriculum-ratio002-s44 EXP008d-3seed.md run,best_val ---,---: pointwise-s43,0.3304 pointwise-s44,0.2963 ratio002-s43,0.3204 ratio002-s44,0.3066 EXP008d-3seed.md objective,order_acc,ratio_log10-MAE,head_log10-MAE,slope,render_log10-MAE ---,---:,---:,---:,---:,---: fixed pointwise,0.7449,0.2254,0.6412,0.2278,0.6379 ratio 0.02,0.7682,0.1565,0.4883,0.2761,0.4934 delta (ratio - pointwise),+0.0233,-0.0688,-0.1530,+0.0483,-0.1445 EXP008d-3seed.md metric,s42,s43,s44,result ---,---:,---:,---:,--- order_acc delta,+0.0108,+0.0516,+0.0076,3/3 better ratio_log10-MAE delta,-0.0099,-0.1825,-0.0141,3/3 better head_log10-MAE delta,-0.0986,-0.3457,-0.0146,3/3 better slope delta,-0.0465,+0.1579,+0.0334,"2/3 better, mean better" render_log10-MAE delta,-0.0886,-0.3267,-0.0183,3/3 better EXP008d-3seed.md objective,s42,s43,s44 ---,---:,---:,---: fixed pointwise,0.0000,0.0000,0.0000 ratio 0.02,0.0000,0.0000,0.0000 EXP008d-renderer-3seed.md split,run,variant,tolerant,log10-MAE,head_tol,head_log10-MAE,render_tol,render_log10-MAE,parse,skipped -------,-----,---------,----------,-----------,----------,----------------,------------,------------------,-------,--------- eval,p25-exp008b-curriculum-pointwise-s42,temporal_pointwise_curriculum,—,—,0.1900,0.3067,0.1800,0.3341,—,0 eval,p26-exp008d-curriculum-pointwise-s43,temporal_pointwise_curriculum,—,—,0.1650,0.4000,0.1750,0.3844,—,0 eval,p26-exp008d-curriculum-pointwise-s44,temporal_pointwise_curriculum,—,—,0.2900,0.2125,0.3350,0.2246,—,0 eval,p25-exp008c-curriculum-ratio002-s42,temporal_ratio002_curriculum,—,—,0.2900,0.2505,0.2700,0.2353,—,0 eval,p26-exp008d-curriculum-ratio002-s43,temporal_ratio002_curriculum,—,—,0.2400,0.2376,0.2650,0.2390,—,0 eval,p26-exp008d-curriculum-ratio002-s44,temporal_ratio002_curriculum,—,—,0.3500,0.1751,0.3600,0.1722,—,0 test_ood_primary,p25-exp008b-curriculum-pointwise-s42,temporal_pointwise_curriculum,—,—,0.0000,0.5662,0.0000,0.5690,—,0 test_ood_primary,p26-exp008d-curriculum-pointwise-s43,temporal_pointwise_curriculum,—,—,0.0000,0.8387,0.0000,0.8269,—,0 test_ood_primary,p26-exp008d-curriculum-pointwise-s44,temporal_pointwise_curriculum,—,—,0.0000,0.5188,0.0000,0.5179,—,0 test_ood_primary,p25-exp008c-curriculum-ratio002-s42,temporal_ratio002_curriculum,—,—,0.0000,0.4676,0.0000,0.4804,—,0 test_ood_primary,p26-exp008d-curriculum-ratio002-s43,temporal_ratio002_curriculum,—,—,0.0000,0.4930,0.0000,0.5002,—,0 test_ood_primary,p26-exp008d-curriculum-ratio002-s44,temporal_ratio002_curriculum,—,—,0.0000,0.5042,0.0000,0.4996,—,0 test_offset_trap,p25-exp008b-curriculum-pointwise-s42,temporal_pointwise_curriculum,—,—,0.1350,0.4091,0.1200,0.4202,—,0 test_offset_trap,p26-exp008d-curriculum-pointwise-s43,temporal_pointwise_curriculum,—,—,0.0800,0.5675,0.0750,0.5761,—,0 test_offset_trap,p26-exp008d-curriculum-pointwise-s44,temporal_pointwise_curriculum,—,—,0.1500,0.3936,0.1450,0.4065,—,0 test_offset_trap,p25-exp008c-curriculum-ratio002-s42,temporal_ratio002_curriculum,—,—,0.1700,0.4435,0.1800,0.4387,—,0 test_offset_trap,p26-exp008d-curriculum-ratio002-s43,temporal_ratio002_curriculum,—,—,0.1250,0.4626,0.1100,0.4751,—,0 test_offset_trap,p26-exp008d-curriculum-ratio002-s44,temporal_ratio002_curriculum,—,—,0.2050,0.2882,0.2100,0.2880,—,0 test_same_offset_diff_answer,p25-exp008b-curriculum-pointwise-s42,temporal_pointwise_curriculum,—,—,0.3100,0.1500,0.2950,0.1467,—,0 test_same_offset_diff_answer,p26-exp008d-curriculum-pointwise-s43,temporal_pointwise_curriculum,—,—,0.1900,0.2844,0.1850,0.2926,—,0 test_same_offset_diff_answer,p26-exp008d-curriculum-pointwise-s44,temporal_pointwise_curriculum,—,—,0.3100,0.1603,0.2900,0.1687,—,0 test_same_offset_diff_answer,p25-exp008c-curriculum-ratio002-s42,temporal_ratio002_curriculum,—,—,0.4200,0.1292,0.3700,0.1267,—,0 test_same_offset_diff_answer,p26-exp008d-curriculum-ratio002-s43,temporal_ratio002_curriculum,—,—,0.3300,0.1648,0.2900,0.1752,—,0 test_same_offset_diff_answer,p26-exp008d-curriculum-ratio002-s44,temporal_ratio002_curriculum,—,—,0.4400,0.1128,0.3950,0.1226,—,0 test_same_answer_diff_offset,p25-exp008b-curriculum-pointwise-s42,temporal_pointwise_curriculum,—,—,0.4500,0.1214,0.4000,0.1761,—,0 test_same_answer_diff_offset,p26-exp008d-curriculum-pointwise-s43,temporal_pointwise_curriculum,—,—,0.1500,0.2996,0.1300,0.1761,—,0 test_same_answer_diff_offset,p26-exp008d-curriculum-pointwise-s44,temporal_pointwise_curriculum,—,—,0.6300,0.0629,0.5650,0.0000,—,0 test_same_answer_diff_offset,p25-exp008c-curriculum-ratio002-s42,temporal_ratio002_curriculum,—,—,0.5300,0.0896,0.4350,0.1761,—,0 test_same_answer_diff_offset,p26-exp008d-curriculum-ratio002-s43,temporal_ratio002_curriculum,—,—,0.5900,0.0717,0.5150,0.0000,—,0 test_same_answer_diff_offset,p26-exp008d-curriculum-ratio002-s44,temporal_ratio002_curriculum,—,—,0.6150,0.0640,0.5650,0.0000,—,0 EXP008d-chronoscale-3seed.md split,run,variant,n,pairs,order_acc,ratio_log10-MAE,anchor_log10-MAE,slope -------,-----,---------,---:,------:,----------:,----------------:,-----------------:,------: eval,p25-exp008b-curriculum-pointwise-s42,temporal_pointwise_curriculum,200,5000,0.8790,0.5784,0.3067,0.9736 eval,p26-exp008d-curriculum-pointwise-s43,temporal_pointwise_curriculum,200,5000,0.8312,0.7009,0.4000,1.0102 eval,p26-exp008d-curriculum-pointwise-s44,temporal_pointwise_curriculum,200,5000,0.8850,0.5233,0.2125,1.0567 eval,p25-exp008c-curriculum-ratio002-s42,temporal_ratio002_curriculum,200,5000,0.8806,0.5352,0.2505,0.9948 eval,p26-exp008d-curriculum-ratio002-s43,temporal_ratio002_curriculum,200,5000,0.8882,0.5188,0.2376,1.0595 eval,p26-exp008d-curriculum-ratio002-s44,temporal_ratio002_curriculum,200,5000,0.9148,0.3860,0.1751,1.0825 test_ood_primary,p25-exp008b-curriculum-pointwise-s42,temporal_pointwise_curriculum,200,5000,0.7952,0.1593,0.5662,0.3640 test_ood_primary,p26-exp008d-curriculum-pointwise-s43,temporal_pointwise_curriculum,200,5000,0.6992,0.3371,0.8387,0.0760 test_ood_primary,p26-exp008d-curriculum-pointwise-s44,temporal_pointwise_curriculum,200,5000,0.7402,0.1797,0.5188,0.2434 test_ood_primary,p25-exp008c-curriculum-ratio002-s42,temporal_ratio002_curriculum,200,5000,0.8060,0.1494,0.4676,0.3175 test_ood_primary,p26-exp008d-curriculum-ratio002-s43,temporal_ratio002_curriculum,200,5000,0.7508,0.1546,0.4930,0.2339 test_ood_primary,p26-exp008d-curriculum-ratio002-s44,temporal_ratio002_curriculum,200,5000,0.7478,0.1656,0.5042,0.2768 test_offset_trap,p25-exp008b-curriculum-pointwise-s42,temporal_pointwise_curriculum,200,5000,0.8088,0.7308,0.4091,0.9235 test_offset_trap,p26-exp008d-curriculum-pointwise-s43,temporal_pointwise_curriculum,200,5000,0.7646,0.9034,0.5675,0.8920 test_offset_trap,p26-exp008d-curriculum-pointwise-s44,temporal_pointwise_curriculum,200,5000,0.8166,0.7008,0.3936,1.0621 test_offset_trap,p25-exp008c-curriculum-ratio002-s42,temporal_ratio002_curriculum,200,5000,0.8168,0.7165,0.4435,0.9583 test_offset_trap,p26-exp008d-curriculum-ratio002-s43,temporal_ratio002_curriculum,200,5000,0.8022,0.7685,0.4626,1.0465 test_offset_trap,p26-exp008d-curriculum-ratio002-s44,temporal_ratio002_curriculum,200,5000,0.8526,0.6323,0.2882,1.0109 test_same_offset_diff_answer,p25-exp008b-curriculum-pointwise-s42,temporal_pointwise_curriculum,200,5000,0.9590,0.1839,0.1500,0.9381 test_same_offset_diff_answer,p26-exp008d-curriculum-pointwise-s43,temporal_pointwise_curriculum,200,5000,0.8828,0.4173,0.2844,0.6270 test_same_offset_diff_answer,p26-exp008d-curriculum-pointwise-s44,temporal_pointwise_curriculum,200,5000,0.9472,0.1991,0.1603,0.9399 test_same_offset_diff_answer,p25-exp008c-curriculum-ratio002-s42,temporal_ratio002_curriculum,200,5000,0.9584,0.1676,0.1292,0.8703 test_same_offset_diff_answer,p26-exp008d-curriculum-ratio002-s43,temporal_ratio002_curriculum,200,5000,0.9400,0.2696,0.1648,0.6925 test_same_offset_diff_answer,p26-exp008d-curriculum-ratio002-s44,temporal_ratio002_curriculum,200,5000,0.9814,0.1702,0.1128,1.2047 test_same_answer_diff_offset,p25-exp008b-curriculum-pointwise-s42,temporal_pointwise_curriculum,200,0,-,-,0.1214,0.0000 test_same_answer_diff_offset,p26-exp008d-curriculum-pointwise-s43,temporal_pointwise_curriculum,200,0,-,-,0.2996,0.0000 test_same_answer_diff_offset,p26-exp008d-curriculum-pointwise-s44,temporal_pointwise_curriculum,200,0,-,-,0.0629,0.0000 test_same_answer_diff_offset,p25-exp008c-curriculum-ratio002-s42,temporal_ratio002_curriculum,200,0,-,-,0.0896,0.0000 test_same_answer_diff_offset,p26-exp008d-curriculum-ratio002-s43,temporal_ratio002_curriculum,200,0,-,-,0.0717,0.0000 test_same_answer_diff_offset,p26-exp008d-curriculum-ratio002-s44,temporal_ratio002_curriculum,200,0,-,-,0.0640,0.0000