{"assigned": 1120, "present": 1120, "missing": 0, "infra_scored_zero": 0} == claude-opus-5-5 [log1p] problems 28: none 1.046, show_all 0.864, opus_self_gating 0.842, opus_digest_calibrated 0.999, predictor_calibrated 1.043 show_all - none -0.182 [-0.327, -0.074] up/down/tie 6/22/0 opus_self_gating - none -0.204 [-0.361, -0.080] up/down/tie 7/21/0 opus_digest_calibrated - none -0.047 [-0.125, +0.026] up/down/tie 8/19/1 predictor_calibrated - none -0.003 [-0.066, +0.055] up/down/tie 15/12/1 none - show_all +0.182 [+0.074, +0.327] up/down/tie 22/6/0 opus_self_gating - show_all -0.023 [-0.074, +0.019] up/down/tie 13/15/0 opus_digest_calibrated - show_all +0.135 [+0.038, +0.250] up/down/tie 19/9/0 predictor_calibrated - show_all +0.179 [+0.080, +0.295] up/down/tie 22/6/0 == claude-opus-5-5 [score] problems 28: none 2.332, show_all 1.665, opus_self_gating 1.579, opus_digest_calibrated 2.155, predictor_calibrated 2.257 show_all - none -0.667 [-1.298, -0.234] up/down/tie 6/22/0 opus_self_gating - none -0.753 [-1.428, -0.248] up/down/tie 7/21/0 opus_digest_calibrated - none -0.177 [-0.528, +0.108] up/down/tie 8/19/1 predictor_calibrated - none -0.075 [-0.352, +0.142] up/down/tie 15/12/1 none - show_all +0.667 [+0.234, +1.298] up/down/tie 22/6/0 opus_self_gating - show_all -0.086 [-0.279, +0.040] up/down/tie 13/15/0 opus_digest_calibrated - show_all +0.489 [+0.153, +0.902] up/down/tie 18/9/1 predictor_calibrated - show_all +0.592 [+0.231, +1.039] up/down/tie 23/5/0 == claude-opus-4-8 [log1p] problems 28: none 0.457, show_all 0.675, opus_self_gating 0.667, opus_digest_calibrated 0.661, predictor_calibrated 0.661 show_all - none +0.218 [+0.149, +0.291] up/down/tie 24/4/0 opus_self_gating - none +0.210 [+0.143, +0.283] up/down/tie 24/4/0 opus_digest_calibrated - none +0.204 [+0.131, +0.282] up/down/tie 23/5/0 predictor_calibrated - none +0.204 [+0.136, +0.276] up/down/tie 24/4/0 none - show_all -0.218 [-0.291, -0.149] up/down/tie 4/24/0 opus_self_gating - show_all -0.007 [-0.022, +0.004] up/down/tie 18/10/0 opus_digest_calibrated - show_all -0.014 [-0.034, +0.001] up/down/tie 17/11/0 predictor_calibrated - show_all -0.013 [-0.035, +0.002] up/down/tie 17/11/0 == claude-opus-4-8 [score] problems 28: none 0.662, show_all 0.986, opus_self_gating 0.978, opus_digest_calibrated 0.965, predictor_calibrated 0.967 show_all - none +0.324 [+0.219, +0.437] up/down/tie 24/4/0 opus_self_gating - none +0.316 [+0.210, +0.430] up/down/tie 24/4/0 opus_digest_calibrated - none +0.304 [+0.191, +0.424] up/down/tie 23/5/0 predictor_calibrated - none +0.305 [+0.199, +0.419] up/down/tie 24/4/0 none - show_all -0.324 [-0.437, -0.219] up/down/tie 4/24/0 opus_self_gating - show_all -0.008 [-0.030, +0.009] up/down/tie 18/10/0 opus_digest_calibrated - show_all -0.021 [-0.052, +0.004] up/down/tie 17/11/0 predictor_calibrated - show_all -0.019 [-0.050, +0.003] up/down/tie 17/11/0 P1 (5.5 digest − show_all, log1p): {'est': (0.1350157209498031, 0.03845928551707699, 0.25012416636419116, 19, 9, 0), 'met': True} P2 (4.8 digest − none, log1p): {'est': (0.20373202998766943, 0.13097193379770478, 0.28188848187230886, 23, 5, 0), 'met': True}