xiangyi-li
/
OS-World
mirrored 4 minutes ago
0
Benchmark CardFiles and versionsLeaderboard
timothyxxxEnhance PPTX comparison logic and update evaluation examples - Introduced a new helper function `nonempty_runs` to filter out formatting-only runs in PPTX comparisons, improving accuracy in slide evaluations. - Updated the logic for comparing runs in paragraphs to handle cases where both paragraphs are empty, ensuring consistent evaluation results. - Revised JSON examples to clarify instructions and enhance evaluator configurations, including adding post-execution commands for script downloads and permissions. These changes improve the robustness of the PPTX file comparison and ensure that evaluation examples are more precise and functional. 0e92af6
Raw
-
{
  "id": "5c1075ca-bb34-46a3-a7a0-029bd7463e79",
  "snapshot": "os",
  "instruction": "Copy all files matching \"*failed.ipynb\" in the current directory tree to \"./fails\" preserving the directory hierarchy",
  "source": "NL2Bash",
  "config": [
    {
      "type": "download",
      "parameters": {
        "files": [
          {
            "url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/5c1075ca-bb34-46a3-a7a0-029bd7463e79/setup.sh",
            "path": "setup.sh"
          }
        ]
      }
    },
    {
      "type": "execute",
      "parameters": {
        "command": "chmod +x setup.sh",
        "shell": true
      }
    },
    {
      "type": "execute",
      "parameters": {
        "command": "./setup.sh",
        "shell": true
      }
    },
    {
      "type": "execute",
      "parameters": {
        "command": [
          "python",
          "-c",
          "import pyautogui; import time; pyautogui.click({SCREEN_WIDTH_HALF}, {SCREEN_HEIGHT_HALF}); time.sleep(0.5); pyautogui.hotkey('ctrl', 'alt', 't'); time.sleep(0.5)"
        ]
      }
    },
    {
      "type": "activate_window",
      "parameters": {
        "window_name": "Terminal"
      }
    },
    {
      "type": "execute",
      "parameters": {
        "command": [
          "python",
          "-c",
          "import pyautogui; import time; time.sleep(0.5); pyautogui.write('cd test_environment'); time.sleep(0.5); pyautogui.press('enter')"
        ]
      }
    }
  ],
  "trajectory": "trajectories/",
  "related_apps": [
    "os"
  ],
  "evaluator": {
    "postconfig": [
      {
        "type": "download",
        "parameters": {
          "files": [
            {
              "url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/5c1075ca-bb34-46a3-a7a0-029bd7463e79/eval.sh",
              "path": "eval.sh"
            }
          ]
        }
      },
      {
        "type": "execute",
        "parameters": {
          "command": "chmod +x eval.sh",
          "shell": true
        }
      }
    ],
    "func": "check_include_exclude",
    "result": {
      "type": "vm_command_line",
      "command": "bash eval.sh",
      "shell": true
    },
    "expected": {
      "type": "rule",
      "rules": {
        "include": [
          "Evaluation successful."
        ],
        "exclude": []
      }
    }
  },
  "proxy": false,
  "fixed_ip": false,
  "possibility_of_env_change": "low"
}