| { |
| "metrics": { |
| "bpd_val": 2.6107561223037, |
| "bpd_per_tier": { |
| "0": 2.2038232899707055, |
| "1": 2.3735981695328294, |
| "2": 2.6973096096747566, |
| "3": 3.006890315533517 |
| }, |
| "bpd_tier_ge1": 2.656977891677827, |
| "n": 2000, |
| "delta_c": 0.24781480995112007, |
| "caption_swap_win_frac": 0.25, |
| "b0_bpd": 6.28435796590519, |
| "tree": { |
| "visible_cut_f1": 0.7648812746568768, |
| "leaf_ari": 0.5688396790527814, |
| "recall_per_tier": { |
| "0": 0.19008264462809918, |
| "3": 0.4357142857142857, |
| "1": 0.20238095238095238, |
| "2": 0.22413333333333335 |
| }, |
| "recall_tier1": 0.20238095238095238, |
| "recall_tier2": 0.22413333333333335 |
| }, |
| "prompt_swap": { |
| "per_pair": { |
| "a red circle -> a blue circle": 0.0625, |
| "a green square -> a purple square": 0.015625, |
| "a yellow diamond -> a cyan diamond": 0.921875, |
| "an orange ring -> a magenta ring": 0.078125, |
| "a red circle to the left of a blue square -> a red circle to the right of a blue square": 0.0, |
| "a green circle above a yellow square -> a green circle below a yellow square": 0.0, |
| "a small purple square -> a large purple square": 1.0, |
| "a red circle -> a red square": 0.15625 |
| }, |
| "attribute_move": 0.3723958333333333, |
| "relation_accuracy": 0.0 |
| }, |
| "holdout_probe_acc": 0.01171875, |
| "heldout_per_combo": { |
| "a blue triangle": 0.03125, |
| "a red ring": 0.015625, |
| "a green star": 0.0, |
| "a yellow cross": 0.0 |
| }, |
| "health": { |
| "S": 1024, |
| "T_v": 256, |
| "s_eff": 968.4937738012005, |
| "alive_texel_frac": 0.4296875, |
| "node_entropy": 0.13297630846500397 |
| } |
| }, |
| "gates": { |
| "1_likelihood": { |
| "status": "PASS", |
| "detail": "bpd(tier>=1)=2.657 vs B0=6.284 (need margin >= 0.15); delta_c=0.248 (need >= 0.05)" |
| }, |
| "2_parses": { |
| "status": "FAIL", |
| "detail": "recall t1=0.20 (>= 0.7), t2=0.22 (>= 0.5), cut F1=0.76 (>= 0.6)" |
| }, |
| "3_prompt_control": { |
| "status": "FAIL", |
| "detail": "attribute-move=0.37 (>= 0.8), relation=0.00 (>= 0.7)" |
| }, |
| "4_compositional": { |
| "status": "FAIL", |
| "detail": "held-out combo probe acc=0.01 (>= 0.6)" |
| }, |
| "5_health": { |
| "status": "FAIL", |
| "detail": "S_eff=968 (>= 256), alive texels=43% (>= 50%)" |
| } |
| } |
| } |
