CHAIN START 2026-09-21T20:50:19Z === task cnb start 2026-09-21T20:50:19Z ANNOUNCE box benchbox · cards GPU-46890836-d8f, GPU-7aa0be10-974 · arm openjev-fp8-readout · task cnb · start 2026-09-21T20:50:19Z · expect ~5 min c-darwin-01-dessert-01 darwin -> darwin 0.34s c-darwin-01-dessert-01 darwin -> darwin 0.39s c-darwin-01-dessert-01 darwin -> darwin 0.30s c-darwin-01-dessert-02 darwin -> darwin 0.41s c-darwin-01-dessert-03 darwin -> darwin 0.41s c-darwin-01-dessert-03 darwin -> darwin 0.41s c-darwin-01-main-01 darwin -> darwin 0.32s c-darwin-01-main-02 darwin -> socrates 0.30s c-darwin-01-main-02 darwin -> darwin 0.37s c-darwin-01-main-02 darwin -> darwin 0.41s c-darwin-01-main-02 darwin -> hypatia 0.41s c-darwin-01-main-03 darwin -> darwin 0.41s c-darwin-01-starter-01 darwin -> sagan 0.23s c-darwin-01-starter-01 darwin -> darwin 0.27s c-darwin-01-starter-01 darwin -> darwin 0.30s c-darwin-01-starter-02 darwin -> darwin 0.27s c-darwin-01-starter-03 darwin -> darwin 0.41s c-darwin-01-starter-03 darwin -> darwin 0.39s c-einstein-01-dessert-01 einstein -> einstein 0.37s c-einstein-01-dessert-01 einstein -> einstein 0.39s c-einstein-01-dessert-02 einstein -> einstein 0.35s c-einstein-01-dessert-02 einstein -> hypatia 0.28s c-einstein-01-dessert-03 einstein -> einstein 0.41s c-einstein-01-main-01 einstein -> hypatia 0.30s c-einstein-01-main-01 einstein -> hypatia 0.35s c-einstein-01-main-02 einstein -> einstein 0.39s c-einstein-01-main-03 einstein -> einstein 0.34s c-einstein-01-main-03 einstein -> einstein 0.35s c-einstein-01-main-03 einstein -> einstein 0.36s c-einstein-01-main-03 einstein -> einstein 0.41s c-einstein-01-starter-01 einstein -> einstein 0.30s c-einstein-01-starter-02 einstein -> einstein 0.27s c-einstein-01-starter-02 einstein -> einstein 0.30s c-einstein-01-starter-03 einstein -> einstein 0.40s c-einstein-01-starter-03 einstein -> einstein 0.35s c-einstein-01-starter-03 einstein -> einstein 0.28s c-hypatia-01-dessert-01 hypatia -> ibn_sina 0.41s c-hypatia-01-dessert-02 hypatia -> ibn_sina 0.33s c-hypatia-01-dessert-02 hypatia -> hypatia 0.27s c-hypatia-01-dessert-03 hypatia -> hypatia 0.30s c-hypatia-01-main-01 hypatia -> hypatia 0.37s c-hypatia-01-main-01 hypatia -> hypatia 0.30s c-hypatia-01-main-01 hypatia -> hypatia 0.39s c-hypatia-01-main-01 hypatia -> hypatia 0.34s c-hypatia-01-main-01 hypatia -> hypatia 0.28s c-hypatia-01-main-02 hypatia -> hypatia 0.35s c-hypatia-01-main-03 hypatia -> hypatia 0.37s c-hypatia-01-main-03 hypatia -> hypatia 0.33s c-hypatia-01-main-03 hypatia -> hypatia 0.42s c-hypatia-01-starter-01 hypatia -> hypatia 0.27s c-hypatia-01-starter-01 hypatia -> socrates 0.33s c-hypatia-01-starter-02 hypatia -> hypatia 0.30s c-hypatia-01-starter-02 hypatia -> hypatia 0.27s c-hypatia-01-starter-02 hypatia -> hypatia 0.30s c-ibn_sina-01-dessert-01 ibn_sina -> ibn_sina 0.32s c-ibn_sina-01-dessert-02 ibn_sina -> ibn_sina 0.33s c-ibn_sina-01-dessert-02 ibn_sina -> ibn_sina 0.35s c-ibn_sina-01-dessert-02 ibn_sina -> ibn_sina 0.34s c-ibn_sina-01-dessert-03 ibn_sina -> ibn_sina 0.36s c-ibn_sina-01-dessert-03 ibn_sina -> ibn_sina 0.40s c-ibn_sina-01-main-02 ibn_sina -> ibn_sina 0.33s c-ibn_sina-01-main-02 ibn_sina -> ibn_sina 0.36s c-ibn_sina-01-main-02 ibn_sina -> ibn_sina 0.37s c-ibn_sina-01-main-03 ibn_sina -> ibn_sina 0.40s c-ibn_sina-01-main-03 ibn_sina -> ibn_sina 0.37s c-ibn_sina-01-main-03 ibn_sina -> ibn_sina 0.40s c-ibn_sina-01-starter-01 ibn_sina -> ibn_sina 0.30s c-ibn_sina-01-starter-02 ibn_sina -> socrates 0.32s c-ibn_sina-01-starter-03 ibn_sina -> ibn_sina 0.37s c-ibn_sina-01-starter-03 ibn_sina -> ibn_sina 0.35s c-ibn_sina-01-starter-03 ibn_sina -> ibn_sina 0.37s c-ibn_sina-01-starter-03 ibn_sina -> ibn_sina 0.35s c-sagan-01-dessert-01 sagan -> sagan 0.41s c-sagan-01-dessert-01 sagan -> sagan 0.30s c-sagan-01-dessert-01 sagan -> sagan 0.29s c-sagan-01-dessert-03 sagan -> sagan 0.33s c-sagan-01-dessert-03 sagan -> sagan 0.41s c-sagan-01-dessert-03 sagan -> sagan 0.33s c-sagan-01-dessert-03 sagan -> sagan 0.36s c-sagan-01-dessert-03 sagan -> sagan 0.40s c-sagan-01-main-01 sagan -> sagan 0.34s c-sagan-01-main-02 sagan -> sagan 0.36s c-sagan-01-main-02 sagan -> einstein 0.32s c-sagan-01-main-03 sagan -> sagan 0.41s c-sagan-01-main-03 sagan -> sagan 0.40s c-sagan-01-starter-01 sagan -> sagan 0.28s c-sagan-01-starter-02 sagan -> sagan 0.41s c-sagan-01-starter-02 sagan -> sagan 0.30s c-sagan-01-starter-03 sagan -> darwin 0.30s c-sagan-01-starter-03 sagan -> einstein 0.35s c-socrates-01-dessert-01 socrates -> socrates 0.41s c-socrates-01-dessert-01 socrates -> socrates 0.29s c-socrates-01-dessert-01 socrates -> socrates 0.36s c-socrates-01-dessert-02 socrates -> socrates 0.35s c-socrates-01-dessert-02 socrates -> socrates 0.37s c-socrates-01-dessert-02 socrates -> socrates 0.30s c-socrates-01-main-01 socrates -> socrates 0.33s c-socrates-01-main-02 socrates -> socrates 0.41s c-socrates-01-main-02 socrates -> ibn_sina 0.30s c-socrates-01-main-02 socrates -> socrates 0.37s c-socrates-01-main-02 socrates -> ibn_sina 0.30s c-socrates-01-main-03 socrates -> ibn_sina 0.35s c-socrates-01-main-03 socrates -> hypatia 0.39s c-socrates-01-starter-01 socrates -> socrates 0.27s c-socrates-01-starter-02 socrates -> socrates 0.32s c-socrates-01-starter-03 socrates -> socrates 0.34s c-socrates-01-starter-03 socrates -> socrates 0.36s c-socrates-01-starter-03 socrates -> socrates 0.33s {"n": 108, "n_reached": 108, "n_labelled": 108, "refused": 0, "refused_by_reason": {}, "correct": 91, "errors": 0, "brier": 0.20553572172992318, "reliability": [{"lo": 0.0, "hi": 0.1, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.1, "hi": 0.2, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.2, "hi": 0.3, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.3, "hi": 0.4, "n": 2, "sum_p": 0.7455075699051901, "correct": 0, "mean_p": 0.37275378495259504, "accuracy": 0 ANNOUNCE box benchbox · cards GPU-46890836-d8f, GPU-7aa0be10-974 · arm openjev-fp8-generate · task cnb · start 2026-09-21T20:51:07Z · expect ~5 min c-darwin-01-dessert-01 darwin -> darwin 0.31s c-darwin-01-dessert-01 darwin -> darwin 0.43s c-darwin-01-dessert-01 darwin -> darwin 0.34s c-darwin-01-dessert-02 darwin -> darwin 0.45s c-darwin-01-dessert-03 darwin -> darwin 0.46s c-darwin-01-dessert-03 darwin -> darwin 0.46s c-darwin-01-main-01 darwin -> darwin 0.36s c-darwin-01-main-02 darwin -> socrates 0.34s c-darwin-01-main-02 darwin -> darwin 0.41s c-darwin-01-main-02 darwin -> darwin 0.45s c-darwin-01-main-02 darwin -> hypatia 0.45s c-darwin-01-main-03 darwin -> darwin 0.45s c-darwin-01-starter-01 darwin -> sagan 0.28s c-darwin-01-starter-01 darwin -> darwin 0.31s c-darwin-01-starter-01 darwin -> darwin 0.34s c-darwin-01-starter-02 darwin -> darwin 0.31s c-darwin-01-starter-03 darwin -> darwin 0.45s c-darwin-01-starter-03 darwin -> darwin 0.43s c-einstein-01-dessert-01 einstein -> einstein 0.41s c-einstein-01-dessert-01 einstein -> einstein 0.43s c-einstein-01-dessert-02 einstein -> einstein 0.39s c-einstein-01-dessert-02 einstein -> hypatia 0.33s c-einstein-01-dessert-03 einstein -> einstein 0.45s c-einstein-01-main-01 einstein -> hypatia 0.34s c-einstein-01-main-01 einstein -> hypatia 0.39s c-einstein-01-main-02 einstein -> einstein 0.44s c-einstein-01-main-03 einstein -> einstein 0.38s c-einstein-01-main-03 einstein -> einstein 0.39s c-einstein-01-main-03 einstein -> einstein 0.40s c-einstein-01-main-03 einstein -> einstein 0.45s c-einstein-01-starter-01 einstein -> einstein 0.35s c-einstein-01-starter-02 einstein -> einstein 0.31s c-einstein-01-starter-02 einstein -> einstein 0.34s c-einstein-01-starter-03 einstein -> einstein 0.44s c-einstein-01-starter-03 einstein -> einstein 0.39s c-einstein-01-starter-03 einstein -> einstein 0.32s c-hypatia-01-dessert-01 hypatia -> ibn_sina 0.45s c-hypatia-01-dessert-02 hypatia -> ibn_sina 0.37s c-hypatia-01-dessert-02 hypatia -> hypatia 0.31s c-hypatia-01-dessert-03 hypatia -> hypatia 0.34s c-hypatia-01-main-01 hypatia -> hypatia 0.41s c-hypatia-01-main-01 hypatia -> hypatia 0.34s c-hypatia-01-main-01 hypatia -> hypatia 0.43s c-hypatia-01-main-01 hypatia -> hypatia 0.38s c-hypatia-01-main-01 hypatia -> hypatia 0.32s c-hypatia-01-main-02 hypatia -> hypatia 0.39s c-hypatia-01-main-03 hypatia -> hypatia 0.41s c-hypatia-01-main-03 hypatia -> hypatia 0.38s c-hypatia-01-main-03 hypatia -> hypatia 0.46s c-hypatia-01-starter-01 hypatia -> hypatia 0.32s c-hypatia-01-starter-01 hypatia -> socrates 0.37s c-hypatia-01-starter-02 hypatia -> hypatia 0.35s c-hypatia-01-starter-02 hypatia -> hypatia 0.32s c-hypatia-01-starter-02 hypatia -> hypatia 0.35s c-ibn_sina-01-dessert-01 ibn_sina -> ibn_sina 0.36s c-ibn_sina-01-dessert-02 ibn_sina -> ibn_sina 0.37s c-ibn_sina-01-dessert-02 ibn_sina -> ibn_sina 0.39s c-ibn_sina-01-dessert-02 ibn_sina -> ibn_sina 0.38s c-ibn_sina-01-dessert-03 ibn_sina -> ibn_sina 0.40s c-ibn_sina-01-dessert-03 ibn_sina -> ibn_sina 0.45s c-ibn_sina-01-main-02 ibn_sina -> ibn_sina 0.37s c-ibn_sina-01-main-02 ibn_sina -> ibn_sina 0.40s c-ibn_sina-01-main-02 ibn_sina -> ibn_sina 0.41s c-ibn_sina-01-main-03 ibn_sina -> ibn_sina 0.44s c-ibn_sina-01-main-03 ibn_sina -> ibn_sina 0.42s c-ibn_sina-01-main-03 ibn_sina -> ibn_sina 0.45s c-ibn_sina-01-starter-01 ibn_sina -> ibn_sina 0.34s c-ibn_sina-01-starter-02 ibn_sina -> socrates 0.36s c-ibn_sina-01-starter-03 ibn_sina -> ibn_sina 0.42s c-ibn_sina-01-starter-03 ibn_sina -> ibn_sina 0.40s c-ibn_sina-01-starter-03 ibn_sina -> ibn_sina 0.42s c-ibn_sina-01-starter-03 ibn_sina -> ibn_sina 0.39s c-sagan-01-dessert-01 sagan -> sagan 0.45s c-sagan-01-dessert-01 sagan -> sagan 0.34s c-sagan-01-dessert-01 sagan -> sagan 0.33s c-sagan-01-dessert-03 sagan -> sagan 0.37s c-sagan-01-dessert-03 sagan -> sagan 0.46s c-sagan-01-dessert-03 sagan -> sagan 0.38s c-sagan-01-dessert-03 sagan -> sagan 0.41s c-sagan-01-dessert-03 sagan -> sagan 0.45s c-sagan-01-main-01 sagan -> sagan 0.38s c-sagan-01-main-02 sagan -> sagan 0.41s c-sagan-01-main-02 sagan -> einstein 0.37s c-sagan-01-main-03 sagan -> sagan 0.45s c-sagan-01-main-03 sagan -> sagan 0.45s c-sagan-01-starter-01 sagan -> sagan 0.33s c-sagan-01-starter-02 sagan -> sagan 0.45s c-sagan-01-starter-02 sagan -> sagan 0.34s c-sagan-01-starter-03 sagan -> darwin 0.35s c-sagan-01-starter-03 sagan -> einstein 0.40s c-socrates-01-dessert-01 socrates -> socrates 0.46s c-socrates-01-dessert-01 socrates -> socrates 0.33s c-socrates-01-dessert-01 socrates -> socrates 0.41s c-socrates-01-dessert-02 socrates -> socrates 0.39s c-socrates-01-dessert-02 socrates -> socrates 0.42s c-socrates-01-dessert-02 socrates -> socrates 0.35s c-socrates-01-main-01 socrates -> socrates 0.37s c-socrates-01-main-02 socrates -> socrates 0.45s c-socrates-01-main-02 socrates -> ibn_sina 0.34s c-socrates-01-main-02 socrates -> socrates 0.41s c-socrates-01-main-02 socrates -> ibn_sina 0.34s c-socrates-01-main-03 socrates -> ibn_sina 0.39s c-socrates-01-main-03 socrates -> hypatia 0.44s c-socrates-01-starter-01 socrates -> socrates 0.31s c-socrates-01-starter-02 socrates -> socrates 0.37s c-socrates-01-starter-03 socrates -> socrates 0.38s c-socrates-01-starter-03 socrates -> socrates 0.40s c-socrates-01-starter-03 socrates -> socrates 0.37s {"n": 108, "n_reached": 108, "n_labelled": 108, "refused": 0, "refused_by_reason": {}, "correct": 91, "errors": 0, "brier": 0.3148148148148148, "reliability": [{"lo": 0.0, "hi": 0.1, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.1, "hi": 0.2, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.2, "hi": 0.3, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.3, "hi": 0.4, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.4, RC=0 task cnb end 2026-09-21T20:52:00Z === task f start 2026-09-21T20:52:00Z ANNOUNCE box benchbox · cards GPU-46890836-d8f, GPU-7aa0be10-974 · arm openjev-fp8-readout · task f · start 2026-09-21T20:52:00Z · expect ~3 min t1-01 yes -> yes 0.31s t1-02 yes -> yes 0.27s t1-03 yes -> yes 0.28s t1-04 yes -> yes 0.27s t1-05 yes -> yes 0.28s t1-06 yes -> yes 0.28s t1-07 yes -> yes 0.28s t1-08 yes -> yes 0.28s t1-09 yes -> yes 0.29s t1-10 yes -> yes 0.26s t1-11 yes -> yes 0.28s t1-12 yes -> yes 0.26s t1-13 yes -> yes 0.27s t1-14 yes -> yes 0.29s t1-15 yes -> yes 0.29s t1-16 yes -> yes 0.30s t1-17 yes -> yes 0.26s t1-18 yes -> yes 0.29s t1-19 yes -> yes 0.26s t1-20 yes -> yes 0.28s t2-01 no -> no 0.27s t2-02 no -> no 0.27s t2-03 no -> no 0.28s t2-04 no -> no 0.28s t2-05 no -> no 0.29s t2-06 no -> no 0.27s t2-07 no -> no 0.27s t2-08 no -> no 0.29s t2-09 no -> no 0.28s t2-10 no -> no 0.28s t2-11 no -> no 0.25s t2-12 no -> no 0.28s t2-13 no -> no 0.28s t2-14 no -> no 0.27s t2-15 no -> no 0.28s t2-16 no -> no 0.26s t2-17 no -> no 0.27s t2-18 no -> no 0.28s t2-19 no -> no 0.27s t2-20 no -> no 0.28s {"n": 40, "n_reached": 40, "n_labelled": 40, "refused": 0, "refused_by_reason": {}, "correct": 40, "errors": 0, "brier": 0.005712504248065705, "reliability": [{"lo": 0.0, "hi": 0.1, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.1, "hi": 0.2, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.2, "hi": 0.3, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.3, "hi": 0.4, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.4, " ANNOUNCE box benchbox · cards GPU-46890836-d8f, GPU-7aa0be10-974 · arm openjev-fp8-generate · task f · start 2026-09-21T20:52:22Z · expect ~3 min t1-01 yes -> yes 0.32s t1-02 yes -> yes 0.31s t1-03 yes -> yes 0.32s t1-04 yes -> yes 0.31s t1-05 yes -> yes 0.32s t1-06 yes -> yes 0.33s t1-07 yes -> yes 0.33s t1-08 yes -> yes 0.33s t1-09 yes -> yes 0.33s t1-10 yes -> yes 0.30s t1-11 yes -> yes 0.32s t1-12 yes -> yes 0.30s t1-13 yes -> yes 0.31s t1-14 yes -> yes 0.33s t1-15 yes -> yes 0.33s t1-16 yes -> yes 0.34s t1-17 yes -> yes 0.30s t1-18 yes -> yes 0.33s t1-19 yes -> yes 0.30s t1-20 yes -> yes 0.32s t2-01 no -> no 0.31s t2-02 no -> no 0.31s t2-03 no -> no 0.32s t2-04 no -> no 0.32s t2-05 no -> no 0.33s t2-06 no -> no 0.31s t2-07 no -> no 0.31s t2-08 no -> no 0.33s t2-09 no -> no 0.32s t2-10 no -> no 0.32s t2-11 no -> no 0.30s t2-12 no -> no 0.32s t2-13 no -> no 0.32s t2-14 no -> no 0.31s t2-15 no -> no 0.33s t2-16 no -> no 0.30s t2-17 no -> no 0.31s t2-18 no -> no 0.32s t2-19 no -> no 0.31s t2-20 no -> no 0.33s {"n": 40, "n_reached": 40, "n_labelled": 40, "refused": 0, "refused_by_reason": {}, "correct": 40, "errors": 0, "brier": 8.349285404260098e-05, "reliability": [{"lo": 0.0, "hi": 0.1, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.1, "hi": 0.2, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.2, "hi": 0.3, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.3, "hi": 0.4, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.4, RC=0 task f end 2026-09-21T20:52:45Z === task j start 2026-09-21T20:52:45Z ANNOUNCE box benchbox · cards GPU-46890836-d8f, GPU-7aa0be10-974 · arm openjev-fp8-readout · task j · start 2026-09-21T20:52:45Z · expect ~8 min j-001 grounded -> grounded 1.04s j-002 grounded -> grounded 1.02s j-003 not_grounded -> not_grounded 0.15s j-004 not_grounded -> not_grounded 0.15s j-005 off_page|not_grounded -> off_page 1.07s j-006 grounded -> grounded 1.17s j-007 grounded -> grounded 0.29s j-008 not_grounded -> not_grounded 0.29s j-009 not_grounded -> not_grounded 0.29s j-010 off_page|not_grounded -> off_page 0.31s j-011 grounded -> grounded 0.83s j-012 grounded -> grounded 0.83s j-013 not_grounded -> not_grounded 0.83s j-014 not_grounded -> not_grounded 0.83s j-015 off_page|not_grounded -> off_page 0.82s j-016 grounded -> grounded 0.99s j-017 grounded -> grounded 0.93s j-018 not_grounded -> not_grounded 0.93s j-019 not_grounded -> not_grounded 0.93s j-020 off_page|not_grounded -> off_page 0.96s j-021 grounded -> grounded 1.30s j-022 grounded -> grounded 0.43s j-023 not_grounded -> not_grounded 0.43s j-024 not_grounded -> not_grounded 0.42s j-025 off_page|not_grounded -> off_page 0.44s j-026 grounded -> grounded 1.04s j-027 grounded -> grounded 1.04s j-028 not_grounded -> not_grounded 0.16s j-029 not_grounded -> not_grounded 0.16s j-030 off_page|not_grounded -> off_page 1.09s j-031 grounded -> grounded 1.86s j-032 grounded -> grounded 1.89s j-033 not_grounded -> not_grounded 1.01s j-034 not_grounded -> not_grounded 1.01s j-035 off_page|not_grounded -> off_page 0.98s j-036 grounded -> grounded 1.91s j-037 grounded -> grounded 1.93s j-038 not_grounded -> not_grounded 0.17s j-039 not_grounded -> not_grounded 0.17s j-040 off_page|not_grounded -> off_page 1.08s j-041 grounded -> grounded 1.00s j-042 grounded -> not_grounded 1.00s j-043 not_grounded -> not_grounded 1.00s j-044 not_grounded -> not_grounded 0.99s j-045 off_page|not_grounded -> off_page 1.00s j-046 grounded -> grounded 0.78s j-047 grounded -> grounded 0.79s j-048 not_grounded -> not_grounded 0.79s j-049 not_grounded -> not_grounded 0.78s j-050 off_page|not_grounded -> off_page 0.81s j-051 grounded -> grounded 0.79s j-052 grounded -> grounded 0.78s j-053 not_grounded -> not_grounded 0.78s j-054 not_grounded -> not_grounded 0.79s j-055 off_page|not_grounded -> off_page 0.78s j-056 grounded -> grounded 1.16s j-057 grounded -> grounded 0.28s j-058 not_grounded -> not_grounded 0.28s j-059 not_grounded -> not_grounded 0.28s j-060 off_page|not_grounded -> off_page 0.28s j-061 grounded -> grounded 1.18s j-062 grounded -> grounded 0.29s j-063 not_grounded -> not_grounded 0.30s j-064 not_grounded -> not_grounded 0.31s j-065 off_page|not_grounded -> off_page 0.27s j-066 grounded -> grounded 0.75s j-067 grounded -> grounded 0.75s j-068 not_grounded -> not_grounded 0.75s j-069 not_grounded -> not_grounded 0.75s j-070 off_page|not_grounded -> off_page 0.72s j-071 grounded -> grounded 0.79s j-072 grounded -> grounded 0.81s j-073 not_grounded -> not_grounded 0.81s j-074 not_grounded -> not_grounded 0.79s j-075 off_page|not_grounded -> off_page 0.81s j-076 grounded -> grounded 0.95s j-077 grounded -> grounded 0.95s j-078 not_grounded -> not_grounded 0.95s j-079 not_grounded -> not_grounded 0.95s j-080 off_page|not_grounded -> off_page 0.96s j-081 grounded -> grounded 0.81s j-082 grounded -> grounded 0.81s j-083 not_grounded -> not_grounded 0.81s j-084 not_grounded -> not_grounded 0.81s j-085 off_page|not_grounded -> off_page 0.81s j-086 grounded -> grounded 0.48s j-087 grounded -> grounded 0.48s j-088 not_grounded -> not_grounded 0.48s j-089 not_grounded -> not_grounded 0.48s j-090 off_page|not_grounded -> off_page 0.51s j-091 grounded -> grounded 1.17s j-092 grounded -> grounded 0.29s j-093 not_grounded -> not_grounded 0.29s j-094 not_grounded -> not_grounded 0.29s j-095 off_page|not_grounded -> off_page 0.30s j-096 grounded -> grounded 0.57s j-097 grounded -> grounded 0.58s j-098 not_grounded -> not_grounded 0.58s j-099 not_grounded -> not_grounded 0.57s j-100 off_page|not_grounded -> off_page 0.61s j-101 grounded -> grounded 1.93s j-102 grounded -> grounded 0.49s j-103 grounded -> grounded 0.83s j-104 grounded -> grounded 0.55s j-105 grounded -> grounded 0.65s j-106 grounded -> grounded 1.06s j-107 grounded -> grounded 1.26s j-108 grounded -> grounded 2.44s j-109 grounded -> grounded 1.01s j-110 grounded -> grounded 0.81s j-111 grounded -> grounded 0.83s j-112 grounded -> grounded 2.36s j-113 grounded -> grounded 0.88s j-114 grounded -> grounded 1.17s j-115 grounded -> grounded 0.75s j-116 grounded -> grounded 0.72s j-117 grounded -> grounded 0.84s j-118 grounded -> grounded 1.03s j-119 grounded -> grounded 1.43s {"n": 119, "n_reached": 119, "n_labelled": 119, "refused": 0, "refused_by_reason": {}, "correct": 98, "errors": 0, "brier": 0.16112082570449382, "reliability": [{"lo": 0.0, "hi": 0.1, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.1, "hi": 0.2, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.2, "hi": 0.3, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.3, "hi": 0.4, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.4, ANNOUNCE box benchbox · cards GPU-46890836-d8f, GPU-7aa0be10-974 · arm openjev-fp8-generate · task j · start 2026-09-21T20:54:31Z · expect ~8 min j-001 grounded -> grounded 0.18s j-002 grounded -> grounded 0.19s j-003 not_grounded -> not_grounded 0.19s j-004 not_grounded -> not_grounded 0.19s j-005 off_page|not_grounded -> off_page 0.24s j-006 grounded -> grounded 0.33s j-007 grounded -> grounded 0.33s j-008 not_grounded -> not_grounded 0.33s j-009 not_grounded -> not_grounded 0.33s j-010 off_page|not_grounded -> off_page 0.35s j-011 grounded -> grounded 0.87s j-012 grounded -> grounded 0.87s j-013 not_grounded -> not_grounded 0.87s j-014 not_grounded -> not_grounded 0.87s j-015 off_page|not_grounded -> off_page 0.86s j-016 grounded -> grounded 0.12s j-017 grounded -> grounded 0.12s j-018 not_grounded -> not_grounded 0.12s j-019 not_grounded -> not_grounded 0.12s j-020 off_page|not_grounded -> off_page 0.13s j-021 grounded -> grounded 0.47s j-022 grounded -> grounded 0.47s j-023 not_grounded -> not_grounded 0.47s j-024 not_grounded -> not_grounded 0.46s j-025 off_page|not_grounded -> off_page 0.48s j-026 grounded -> grounded 0.20s j-027 grounded -> grounded 0.20s j-028 not_grounded -> not_grounded 0.20s j-029 not_grounded -> not_grounded 0.20s j-030 off_page|not_grounded -> off_page 0.26s j-031 grounded -> grounded 0.17s j-032 grounded -> grounded 0.17s j-033 not_grounded -> not_grounded 0.17s j-034 not_grounded -> not_grounded 0.17s j-035 off_page|not_grounded -> off_page 0.14s j-036 grounded -> grounded 0.21s j-037 grounded -> grounded 0.21s j-038 not_grounded -> not_grounded 0.21s j-039 not_grounded -> not_grounded 0.21s j-040 off_page|not_grounded -> off_page 0.24s j-041 grounded -> grounded 0.16s j-042 grounded -> not_grounded 0.17s j-043 not_grounded -> not_grounded 0.17s j-044 not_grounded -> not_grounded 0.16s j-045 off_page|not_grounded -> off_page 0.16s j-046 grounded -> grounded 0.83s j-047 grounded -> grounded 0.83s j-048 not_grounded -> not_grounded 0.83s j-049 not_grounded -> not_grounded 0.82s j-050 off_page|not_grounded -> off_page 0.85s j-051 grounded -> grounded 0.83s j-052 grounded -> grounded 0.82s j-053 not_grounded -> not_grounded 0.82s j-054 not_grounded -> not_grounded 0.83s j-055 off_page|not_grounded -> off_page 0.82s j-056 grounded -> grounded 0.32s j-057 grounded -> grounded 0.32s j-058 not_grounded -> not_grounded 0.32s j-059 not_grounded -> not_grounded 0.32s j-060 off_page|not_grounded -> off_page 0.31s j-061 grounded -> grounded 0.34s j-062 grounded -> grounded 0.33s j-063 not_grounded -> not_grounded 0.33s j-064 not_grounded -> not_grounded 0.35s j-065 off_page|not_grounded -> off_page 0.30s j-066 grounded -> grounded 0.79s j-067 grounded -> grounded 0.79s j-068 not_grounded -> not_grounded 0.79s j-069 not_grounded -> not_grounded 0.79s j-070 off_page|not_grounded -> off_page 0.76s j-071 grounded -> grounded 0.83s j-072 grounded -> grounded 0.85s j-073 not_grounded -> not_grounded 0.85s j-074 not_grounded -> not_grounded 0.83s j-075 off_page|not_grounded -> off_page 0.85s j-076 grounded -> grounded 0.12s j-077 grounded -> grounded 0.12s j-078 not_grounded -> not_grounded 0.12s j-079 not_grounded -> not_grounded 0.12s j-080 off_page|not_grounded -> off_page 0.12s j-081 grounded -> grounded 0.85s j-082 grounded -> grounded 0.85s j-083 not_grounded -> not_grounded 0.85s j-084 not_grounded -> not_grounded 0.85s j-085 off_page|not_grounded -> off_page 0.85s j-086 grounded -> grounded 0.52s j-087 grounded -> grounded 0.52s j-088 not_grounded -> not_grounded 0.52s j-089 not_grounded -> not_grounded 0.52s j-090 off_page|not_grounded -> off_page 0.55s j-091 grounded -> grounded 0.33s j-092 grounded -> grounded 0.33s j-093 not_grounded -> not_grounded 0.33s j-094 not_grounded -> not_grounded 0.33s j-095 off_page|not_grounded -> off_page 0.34s j-096 grounded -> grounded 0.61s j-097 grounded -> grounded 0.62s j-098 not_grounded -> not_grounded 0.62s j-099 not_grounded -> not_grounded 0.61s j-100 off_page|not_grounded -> off_page 0.65s j-101 grounded -> grounded 0.23s j-102 grounded -> grounded 0.53s j-103 grounded -> grounded 0.87s j-104 grounded -> grounded 0.59s j-105 grounded -> grounded 0.69s j-106 grounded -> grounded 0.23s j-107 grounded -> grounded 0.42s j-108 grounded -> grounded 0.74s j-109 grounded -> grounded 0.17s j-110 grounded -> grounded 0.85s j-111 grounded -> grounded 0.87s j-112 grounded -> grounded 0.66s j-113 grounded -> grounded 0.93s j-114 grounded -> grounded 0.33s j-115 grounded -> grounded 0.79s j-116 grounded -> grounded 0.76s j-117 grounded -> grounded 0.88s j-118 grounded -> grounded 0.19s j-119 grounded -> grounded 0.59s {"n": 119, "n_reached": 119, "n_labelled": 119, "refused": 0, "refused_by_reason": {}, "correct": 98, "errors": 0, "brier": 0.18487394957983194, "reliability": [{"lo": 0.0, "hi": 0.1, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.1, "hi": 0.2, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.2, "hi": 0.3, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.3, "hi": 0.4, "n": 0, "sum_p": 0.0, "correct": 0, "mean_p": null, "accuracy": null, "gap": null}, {"lo": 0.4, RC=0 task j end 2026-09-21T20:55:39Z CHAIN END 2026-09-21T20:55:40Z