Upload README.md

Upload results/filtered_problems.json with huggingface_hub

Upload results/accuracy_by_n.json with huggingface_hub

Upload results/bon_results.json with huggingface_hub

Upload plots/plot4_prm_scores.png with huggingface_hub

Upload plots/plot3_per_problem.png with huggingface_hub

Upload plots/plot2_accuracy_vs_n.png with huggingface_hub

Upload plots/plot1_accuracy_comparison.png with huggingface_hub

Upload code/step5_push_dataset.py with huggingface_hub

Upload code/step4_analysis.py with huggingface_hub

Upload code/step3_best_of_n.py with huggingface_hub

Upload code/step2_sample_and_score.py with huggingface_hub

Upload code/step1_filter_and_greedy.py with huggingface_hub

Upload code/run_all.py with huggingface_hub

Upload code/run_all.py

initial commit