Source symbols: evals/old/hotpot_qa_24_2025/src/run_cross_benchmark_analysis.py

Deterministic, value-free symbol metadata extracted from public source. Implementations and literal values are not copied into this page.

• Revision: main@90b4acaac937dc1c0aeffaead8b707c896ebf3db · 2026-07-22T09:03:55Z
• Declarations: 11
• Referenced calls: 37

Declared symbols

• download_modal_volume — def at line 15; references print, Path, mkdir, getcwd, chdir, run, exit, exists, iterdir, is_dir, startswith, append, sorted, list, glob, len, str, check_evaluated_folder_exists, check_analysis_files_exist, analyze_single_benchmark_folder
• get_benchmark_folders — def at line 38; references Path, exists, print, iterdir, is_dir, startswith, append, sorted, list, glob, len, mkdir, str, check_evaluated_folder_exists, check_analysis_files_exist, analyze_single_benchmark_folder, max
• check_evaluated_folder_exists — def at line 55; references Path, exists, print, list, glob, len, mkdir, str, check_analysis_files_exist, analyze_single_benchmark_folder, max, get_benchmark_folders
• check_analysis_files_exist — def at line 72; references Path, exists, list, glob, len, mkdir, str, print, check_evaluated_folder_exists, analyze_single_benchmark_folder, max, get_benchmark_folders
• create_analysis_folder — def at line 84; references Path, mkdir, str, print, check_evaluated_folder_exists, check_analysis_files_exist, analyze_single_benchmark_folder, max, get_benchmark_folders
• process_single_benchmark — def at line 91; references Path, print, check_evaluated_folder_exists, check_analysis_files_exist, analyze_single_benchmark_folder, str, max, get_benchmark_folders
• print_progress_update — def at line 116; references max, print, get_benchmark_folders
• process_all_benchmarks — def at line 122; references get_benchmark_folders
• create_cross_benchmark_summary — def at line 147; references print, Path, exists, read_csv, len
• print_summary — def at line 208; references print
• main — def at line 229; references print, download_modal_volume, process_all_benchmarks, create_cross_benchmark_summary, print_summary

File-level call references

• print — line 17
• Path — line 20
• mkdir — line 20
• getcwd — line 22
• chdir — line 23
• run — line 27
• exit — line 33
• exists — line 42
• iterdir — line 47
• is_dir — line 48
• startswith — line 48
• append — line 49
• sorted — line 52
• list — line 63
• glob — line 63
• len — line 81
• str — line 88
• check_evaluated_folder_exists — line 98
• check_analysis_files_exist — line 102
• analyze_single_benchmark_folder — line 108
• max — line 118
• get_benchmark_folders — line 124
• enumerate — line 134
• print_progress_update — line 135
• process_single_benchmark — line 137
• read_csv — line 161
• mean — line 169
• DataFrame — line 183
• sort_values — line 191
• to_csv — line 195
• head — line 202
• iterrows — line 202
• download_modal_volume — line 240
• process_all_benchmarks — line 243
• create_cross_benchmark_summary — line 246
• print_summary — line 249
• main — line 255

Source: evals/old/hotpot_qa_24_2025/src/run_cross_benchmark_analysis.py