prompt large_stringlengths 67.6k 598k | ground_truth large_stringclasses 2
values | base_model_output large_stringlengths 1.4k 22.1k | sft_epoch_1_output large_stringlengths 6.85k 15.5k | sft_epoch_2_output large_stringlengths 6.47k 18.5k | sft_epoch_3_output large_stringlengths 6.92k 18.5k | rl_step_1100_output large_stringlengths 6.47k 15.1k | rl_step_2300_output large_stringlengths 7.33k 16.4k | rl_step_3396_output large_stringlengths 6.84k 17k |
|---|---|---|---|---|---|---|---|---|
"<|im_start|>system\nYou are a professional software engineer and code reviewer.<|im_end|>\n<|im_sta(...TRUNCATED) | 1 | "Okay, let's tackle this step by step. I need to evaluate if the OpenHands agent trajectory successf(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) |
"<|im_start|>system\nYou are a professional software engineer and code reviewer.<|im_end|>\n<|im_sta(...TRUNCATED) | 0 | "## Step 1: Trajectory Summarization\n\nThe agent thoroughly analyzed the issue, which involved a Ru(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) |
"<|im_start|>system\nYou are a professional software engineer and code reviewer.<|im_end|>\n<|im_sta(...TRUNCATED) | 1 | "Okay, let's tackle this. The user wants me to evaluate if the OpenHands agent trajectory successful(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) |
"<|im_start|>system\nYou are a professional software engineer and code reviewer.<|im_end|>\n<|im_sta(...TRUNCATED) | 1 | "Okay, let's tackle this. The user wants me to evaluate if the OpenHands agent trajectory successful(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) |
"<|im_start|>system\nYou are a professional software engineer and code reviewer.<|im_end|>\n<|im_sta(...TRUNCATED) | 1 | "Okay, let me tackle this step by step. First, I need to evaluate if the OpenHands agent trajectory (...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) |
"<|im_start|>system\nYou are a professional software engineer and code reviewer.<|im_end|>\n<|im_sta(...TRUNCATED) | 1 | "Okay, let's go through this step by step. The user wants me to evaluate whether the OpenHands agent(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) |
"<|im_start|>system\nYou are a professional software engineer and code reviewer.<|im_end|>\n<|im_sta(...TRUNCATED) | 1 | "Okay, let's tackle this step by step. I need to evaluate whether the OpenHands agent trajectory suc(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) |
"<|im_start|>system\nYou are a professional software engineer and code reviewer.<|im_end|>\n<|im_sta(...TRUNCATED) | 0 | "Okay, let's tackle this problem. I need to evaluate whether the OpenHands agent trajectory successf(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) |
"<|im_start|>system\nYou are a professional software engineer and code reviewer.<|im_end|>\n<|im_sta(...TRUNCATED) | 0 | "Okay, let's tackle this. The user wants me to evaluate if the OpenHands agent trajectory successful(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) |
"<|im_start|>system\nYou are a professional software engineer and code reviewer.<|im_end|>\n<|im_sta(...TRUNCATED) | 1 | "## Step 1: Trajectory Summarization\n\nThe agent followed a thorough, methodical approach to resolv(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) | "Let me analyze the trajectory carefully to evaluate whether the issue was successfully resolved.\n\(...TRUNCATED) |
Dataset Description
SWE-Critix/test_dataset is the testing set of the models SWE-Critix/SWE-Critix-Qwen3-30B-A3B-SFT-Epoch3 and SWE-Critix/SWE-Critix-Qwen3-30B-A3B-RL-Step-3396. It contains 43445 samples (28741 positives vs. 14704 negatives). Each sample takes the following format:
{
"prompt": a prompt using codeforge_preview_patch_correctness_judge.txt as the template,
"ground_truth": "1" if the trajectory passed unit testing, and "0" otherwise,
"base_model_output": the response generated by the base model (i.e., Qwen3-30B-A3B-Thinking-2507),
"sft_epoch_1_output": the response generated by the SFT checkpoint at iteration 325 (i.e., the first epoch),
"sft_epoch_2_output": the response generated by the SFT checkpoint at iteration 650 (i.e., the second epoch),
"sft_epoch_3_output": the response generated by the SFT checkpoint at iteration 975 (i.e., the third epoch),
"rl_step_1100_output": the response generated by the RL checkpoint at iteration 1100,
"rl_step_2300_output": the response generated by the RL checkpoint at iteration 2300,
"rl_step_3396_output": the response generated by the RL checkpoint at iteration 3396,
"
}
Data Sources and Licenses
This dataset contains data derived from multiple upstream sources: togethercomputer/CoderForge-Preview, R2E-Gym, nebius/SWE-rebench, and SWE-bench/SWE-smith. The original data remain subject to the licenses and terms of their respective sources. Users are responsible for complying with the applicable licenses and terms of the respective upstream datasets.
Attribution
Please refer to the corresponding upstream datasets for their required attribution and licensing terms.
License
Because this dataset incorporates data from multiple upstream sources with potentially different licensing terms, no single license is intended to override the licenses of the individual source datasets. The licensing terms of the original source data remain applicable to those portions of the dataset.
- Downloads last month
- 115