| task,method,epoch,sr_pct,se_pct,seed42_pct,seed1042_pct,seed2042_pct,successes,n,source,se_definition | |
| PushT,Baseline,best,38.0,3.96316371938716,40.0,46.0,28.000000000000004,57,150,https://huggingface.co/zcyqyq/image_ccil/blob/46452cffbdb9fa28bb03204cb34574432742648c/pusht/baseline/eval_scores_3x50.csv,pooled binomial sqrt(p*(1-p)/150); assumes independent trials | |
| PushT,Seq BE,780,51.33333333333333,4.081031097016392,48.0,54.0,52.0,77,150,https://huggingface.co/zcyqyq/image_ccil/blob/46452cffbdb9fa28bb03204cb34574432742648c/pusht/seq_be_epoch780/eval_scores_3x50.csv,pooled binomial sqrt(p*(1-p)/150); assumes independent trials | |
| PushT,E2E,500,57.99999999999999,4.029888335921976,60.0,60.0,54.0,87,150,https://huggingface.co/zcyqyq/image_ccil/blob/46452cffbdb9fa28bb03204cb34574432742648c/pusht/e2e_best_epoch500/eval_scores_3x50.csv,pooled binomial sqrt(p*(1-p)/150); assumes independent trials | |
| Square,Baseline,500,53.333333333333336,4.073400617738524,60.0,52.0,48.0,80,150,https://huggingface.co/zcyqyq/image_ccil/blob/46452cffbdb9fa28bb03204cb34574432742648c/square/baseline/eval_scores_3x50.csv,pooled binomial sqrt(p*(1-p)/150); assumes independent trials | |
| Square,Seq BE,380,61.33333333333333,3.9762256437946744,72.0,62.0,50.0,92,150,https://huggingface.co/zcyqyq/image_ccil/blob/46452cffbdb9fa28bb03204cb34574432742648c/square/seq_be_epoch380/eval_scores_3x50.csv,pooled binomial sqrt(p*(1-p)/150); assumes independent trials | |
| Square,E2E zcurr hybrid,420,70.0,3.7416573867739418,72,62,76,105,150,square/e2e_zcurr_hybrid_epoch420/eval_3x50/summary.json,pooled binomial sqrt(p*(1-p)/150); assumes independent trials | |
| ToolHang,Baseline,140,23.333333333333332,3.453393392871123,28.000000000000004,22.0,20.0,35,150,https://huggingface.co/zcyqyq/image_ccil/blob/46452cffbdb9fa28bb03204cb34574432742648c/toolhang/baseline/eval_scores_3x50.csv,pooled binomial sqrt(p*(1-p)/150); assumes independent trials | |
| ToolHang,Seq BE,100,34.66666666666667,3.885776532336781,38.0,28.000000000000004,38.0,52,150,https://huggingface.co/zcyqyq/image_ccil/blob/46452cffbdb9fa28bb03204cb34574432742648c/toolhang/seq_be_epoch100/eval_scores_3x50.csv,pooled binomial sqrt(p*(1-p)/150); assumes independent trials | |
| ToolHang,E2E BE zcurr,160,32.666666666666664,3.8293215722505867,44.0,24.0,30.0,49,150,https://huggingface.co/zcyqyq/image_ccil/blob/46452cffbdb9fa28bb03204cb34574432742648c/toolhang/e2e_be_zcurr_epoch160/eval_scores_3x50.csv,pooled binomial sqrt(p*(1-p)/150); assumes independent trials | |