{ "flow80k_drawsprobe_draws10_freshnoise": { "label": "flow80k_drawsprobe_draws10_freshnoise", "n_frames": 2458, "core": 2458, "n_draws": 10, "no_triplet_fallback_rows": 28, "ladder_chunk": { "single_draw_avg": 6.6661, "ensemble_mean_of_n": 5.4113, "jerk_pick": 6.7313, "oracle_best_of_n": 3.8597 }, "first_mae": { "ensemble": 1.3975, "jerk_pick": 1.9075, "oracle": 1.5588 }, "diagnostics": { "oracle_agreement": 0.1049, "expected_agreement_null": 0.1, "spearman_jerk_vs_mae": 0.1278, "oracle_gap_recovered": -0.0232 }, "record_only": true }, "flow80k_drawsprobe_ticket64": { "label": "flow80k_drawsprobe_ticket64", "n_frames": 2458, "core": 2458, "n_draws": 64, "no_triplet_fallback_rows": 28, "ladder_chunk": { "single_draw_avg": 6.744, "ensemble_mean_of_n": 5.2817, "jerk_pick": 7.6865, "oracle_best_of_n": 2.9632 }, "first_mae": { "ensemble": 1.3374, "jerk_pick": 1.9303, "oracle": 1.3983 }, "diagnostics": { "oracle_agreement": 0.0152, "expected_agreement_null": 0.0156, "spearman_jerk_vs_mae": 0.1262, "oracle_gap_recovered": -0.2493 }, "record_only": true }, "ar100k_q4_draws10_t0.5": { "label": "ar100k_q4_draws10_t0.5", "n_frames": 4301, "core": 4301, "n_draws": 10, "no_triplet_fallback_rows": 0, "ladder_chunk": { "single_draw_avg": 7.3116, "ensemble_mean_of_n": 6.5004, "jerk_pick": 7.1622, "oracle_best_of_n": 4.6348 }, "first_mae": { "ensemble": 1.7606, "jerk_pick": 2.2458, "oracle": 1.9562 }, "diagnostics": { "oracle_agreement": 0.1302, "expected_agreement_null": 0.1, "spearman_jerk_vs_mae": 0.3549, "oracle_gap_recovered": 0.0558 }, "record_only": true }, "ar100k_q4_draws10_t0.7": { "label": "ar100k_q4_draws10_t0.7", "n_frames": 4301, "core": 4301, "n_draws": 10, "no_triplet_fallback_rows": 0, "ladder_chunk": { "single_draw_avg": 7.652, "ensemble_mean_of_n": 6.5668, "jerk_pick": 7.4169, "oracle_best_of_n": 4.5247 }, "first_mae": { "ensemble": 1.7959, "jerk_pick": 2.406, "oracle": 2.1018 }, "diagnostics": { "oracle_agreement": 0.1239, "expected_agreement_null": 0.1, "spearman_jerk_vs_mae": 0.3632, "oracle_gap_recovered": 0.0752 }, "record_only": true }, "ar100k_q4_draws10_t1.3": { "label": "ar100k_q4_draws10_t1.3", "n_frames": 4301, "core": 4301, "n_draws": 10, "no_triplet_fallback_rows": 0, "ladder_chunk": { "single_draw_avg": 9.2153, "ensemble_mean_of_n": 7.1843, "jerk_pick": 8.2782, "oracle_best_of_n": 4.7202 }, "first_mae": { "ensemble": 2.297, "jerk_pick": 3.246, "oracle": 2.7022 }, "diagnostics": { "oracle_agreement": 0.1516, "expected_agreement_null": 0.1, "spearman_jerk_vs_mae": 0.3693, "oracle_gap_recovered": 0.2085 }, "record_only": true }, "molmo2_40k_panel_draws10_t1": { "label": "molmo2_40k_panel_draws10_t1", "n_frames": 25800, "core": 17204, "n_draws": 10, "no_triplet_fallback_rows": 1107, "ladder_chunk": { "single_draw_avg": 7.5098, "ensemble_mean_of_n": 5.8492, "jerk_pick": 7.2499, "oracle_best_of_n": 4.2616 }, "first_mae": { "ensemble": 1.9736, "jerk_pick": 2.8599, "oracle": 2.4142 }, "diagnostics": { "oracle_agreement": 0.1213, "expected_agreement_null": 0.1, "spearman_jerk_vs_mae": 0.5453, "oracle_gap_recovered": 0.08 }, "record_only": true } }