Dataset Viewer
Auto-converted to Parquet Duplicate
task_id
stringlengths
20
23
difficulty
int64
1
4
difficulty_tier
stringclasses
3 values
n_turns
int64
2
20
source_agent
stringclasses
2 values
messages
listlengths
7
43
tools
listlengths
1
1
0032_386_32386426_qa_2
3
medium
7
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0079_726_79726462_qa_1
2
medium
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0058_272_58272349_qa_4
1
easy
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0108_986_108986276_qa_3
2
medium
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0135_720_135720396_qa_1
3
medium
6
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0130_285_130285411_qa_1
1
easy
4
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0123_500_123500011_qa_3
1
easy
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0096_784_96784965_qa_2
2
medium
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0043_591_43591690_qa_2
2
medium
4
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0001_733_1733851_qa_3
2
medium
12
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0069_399_69399288_qa_4
4
hard
4
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0035_303_35303628_qa_1
3
medium
4
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0028_054_28054736_qa_2
1
easy
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0089_604_89604836_qa_4
2
medium
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0053_910_53910928_qa_5
4
hard
8
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0041_193_41193082_qa_3
2
medium
4
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0056_687_56687302_qa_2
3
medium
5
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0127_535_127535783_qa_4
1
easy
7
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0115_972_115972863_qa_1
2
medium
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0017_339_17339042_qa_3
3
medium
5
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0102_923_102923439_qa_3
1
easy
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0112_804_112804674_qa_4
3
medium
5
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0057_778_57778333_qa_1
2
medium
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0083_238_83238182_qa_2
2
medium
4
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
0024_251_24251009_qa_3
1
easy
3
bash
[ { "role": "system", "content": "You are an autonomous data-analysis agent operating in a sandboxed Linux container. Your only tool is `bash`. The dataset files are in /home/user/input/. Python 3 + pandas + numpy + scikit-learn + scipy are pre-installed.\n\nWork the problem step-by-step: first inspect the da...
[ { "type": "function", "function": { "name": "bash", "description": "Run a shell command in the sandbox and return its combined stdout+stderr. The shell is non-stateful between calls (each call is a fresh `bash -c`). Use it to explore files (ls, head, cat), run Python (`python3 -c ...`), and writ...
End of preview. Expand in Data Studio

data_agent_harbor_train_sft

4677 verified agent trajectories (SFT) for the data_agent_harbor_train environments. TRL-ready tool-calling format: messages + tools columns.

Each row is a reward=1 rollout — instruction -> bash tool calls (shell commands) -> final answer — graded deterministically (no LLM judge). Single bash tool throughout.

Columns

  • messages: OpenAI/TRL chat format (system, user, assistant+tool_calls, tool, ...). tool_calls[].function.arguments are JSON objects; tool messages carry name.
  • tools: the bash tool JSON schema (for apply_chat_template(..., tools=...)).
  • task_id, difficulty (1-5), n_turns, source_agent (bash|seta).

Usage

from datasets import load_dataset
ds = load_dataset('AdithyaSK/data_agent_harbor_train_sft', split='train')
Downloads last month
46