Dataset Viewer
Auto-converted to Parquet Duplicate
messages
listlengths
8
16
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
[ { "role": "user", "content": "You are an expert software engineer solving a coding task with the ReAct pattern\n(Thought → Action → Observation).\n\n## Repository files\nsolution.py\n\n## Problem statement\nSolve the following programming problem in `solution.py`. Your program must read input from STDIN and...
End of preview. Expand in Data Studio

DiDPO-SFT-Data

Multi-turn SFT trajectories for code-editing agents (APPS / CodeRL+), for verl multiturn SFT.

Protocol

  • Granularity: episode (one row = full trajectory)
  • Layout: react_chat — turn-1 user is full initial prompt; later user turns are observation-only
  • Actions: <execute_bash>, <edit>, <finish> (ReAct · exec · think OFF)
  • Filter: won only, 3023 unique episodes (dedup by instance_id)

Stats

Split Episodes
train 2872
val 151

Sources

APPS train, CodeRL+ prime_extra (Qwen/GLM collect), synthetic teacher wrap. Easy pool excluded.

Files

  • train.parquet / val.parquet — verl SFT (messages column)
  • train.meta.json — build metadata
  • sft_won_format_report.json — pre-pack validation

Usage

# verl: data.multiturn.enable=true, messages_key=messages
# train_files=data/sft/apps_mt8_mix/train.parquet
Downloads last month
55