Dataset Viewer
Auto-converted to Parquet Duplicate
images
images listlengths
1
1
data_source
stringclasses
5 values
prompt
listlengths
2
2
reward_model
dict
agent_name
stringclasses
1 value
extra_info
dict
carbon
[ { "content": "You are a helpful assistant.", "role": "system" }, { "content": "<image>\nAnalyze the provided spectrum to determine if it is a **Carbon Star (C-type)**.\n\n- **Key Visual Indicators of Carbon Star:**\n - **(Primary):** Strong molecular absorption from **C₂ (diatomic carbon) \"Swan ...
{ "ground_truth": "YES", "type": "rule" }
tool_agent
{ "index": "6e4af1e1-3f6d-4085-a352-7e57fba11f34", "name": "spec-56414-HD161547N531412F01_sp07-098.fits.gz", "tools_kwargs": { "spectral_visualization_tool": { "create_kwargs": { "flux": [ 531.5101928710938, 609.1881103515625, 589.1961669921875, 513.059448...
[{"src":"https://datasets-server.huggingface.co/assets/Maxwell-Jia/SpecVI-Bench/--/{dataset_git_revi(...TRUNCATED)
carbon
[{"content":"You are a helpful assistant.","role":"system"},{"content":"<image>\nAnalyze the provide(...TRUNCATED)
{ "ground_truth": "YES", "type": "rule" }
tool_agent
{"index":"244cbc7f-52b2-42b5-9b66-438a20ede226","name":"spec-56647-GAC085N22V2_sp09-152.fits.gz","to(...TRUNCATED)
[{"src":"https://datasets-server.huggingface.co/assets/Maxwell-Jia/SpecVI-Bench/--/{dataset_git_revi(...TRUNCATED)
carbon
[{"content":"You are a helpful assistant.","role":"system"},{"content":"<image>\nAnalyze the provide(...TRUNCATED)
{ "ground_truth": "YES", "type": "rule" }
tool_agent
{"index":"e4c37b2c-3b32-4044-8aa9-2b51781c8e3a","name":"spec-60050-HD095844N060652V03_sp12-065.fits.(...TRUNCATED)
[{"src":"https://datasets-server.huggingface.co/assets/Maxwell-Jia/SpecVI-Bench/--/{dataset_git_revi(...TRUNCATED)
carbon
[{"content":"You are a helpful assistant.","role":"system"},{"content":"<image>\nAnalyze the provide(...TRUNCATED)
{ "ground_truth": "YES", "type": "rule" }
tool_agent
{"index":"0ebc3797-a382-44d2-8d30-a55248494185","name":"spec-56804-HD173550N120249V01_sp15-173.fits.(...TRUNCATED)
[{"src":"https://datasets-server.huggingface.co/assets/Maxwell-Jia/SpecVI-Bench/--/{dataset_git_revi(...TRUNCATED)
carbon
[{"content":"You are a helpful assistant.","role":"system"},{"content":"<image>\nAnalyze the provide(...TRUNCATED)
{ "ground_truth": "YES", "type": "rule" }
tool_agent
{"index":"2857eb64-7492-443f-ab84-263ee762f2fa","name":"spec-56389-HD134427N004207M01_sp14-100.fits.(...TRUNCATED)
[{"src":"https://datasets-server.huggingface.co/assets/Maxwell-Jia/SpecVI-Bench/--/{dataset_git_revi(...TRUNCATED)
carbon
[{"content":"You are a helpful assistant.","role":"system"},{"content":"<image>\nAnalyze the provide(...TRUNCATED)
{ "ground_truth": "YES", "type": "rule" }
tool_agent
{"index":"49c0a80b-25ec-4b09-81a3-fb4adb47365d","name":"spec-56228-GAC102N27B1_sp07-116.fits.gz","to(...TRUNCATED)
[{"src":"https://datasets-server.huggingface.co/assets/Maxwell-Jia/SpecVI-Bench/--/{dataset_git_revi(...TRUNCATED)
carbon
[{"content":"You are a helpful assistant.","role":"system"},{"content":"<image>\nAnalyze the provide(...TRUNCATED)
{ "ground_truth": "YES", "type": "rule" }
tool_agent
{"index":"3b5c73da-7e8e-498e-a5a6-6dec01a32a0d","name":"spec-57535-HD160722N214921B01_sp02-184.fits.(...TRUNCATED)
[{"src":"https://datasets-server.huggingface.co/assets/Maxwell-Jia/SpecVI-Bench/--/{dataset_git_revi(...TRUNCATED)
carbon
[{"content":"You are a helpful assistant.","role":"system"},{"content":"<image>\nAnalyze the provide(...TRUNCATED)
{ "ground_truth": "YES", "type": "rule" }
tool_agent
{"index":"f57af524-0d32-4688-b2ce-82d554fb63d3","name":"spec-57319-HD213312N533525B01_sp16-202.fits.(...TRUNCATED)
[{"src":"https://datasets-server.huggingface.co/assets/Maxwell-Jia/SpecVI-Bench/--/{dataset_git_revi(...TRUNCATED)
carbon
[{"content":"You are a helpful assistant.","role":"system"},{"content":"<image>\nAnalyze the provide(...TRUNCATED)
{ "ground_truth": "YES", "type": "rule" }
tool_agent
{"index":"b72f3e88-a4bf-4fd0-8f54-a2f4a93fb3e9","name":"spec-56393-HD094551N184100M01_sp12-160.fits.(...TRUNCATED)
[{"src":"https://datasets-server.huggingface.co/assets/Maxwell-Jia/SpecVI-Bench/--/{dataset_git_revi(...TRUNCATED)
carbon
[{"content":"You are a helpful assistant.","role":"system"},{"content":"<image>\nAnalyze the provide(...TRUNCATED)
{ "ground_truth": "YES", "type": "rule" }
tool_agent
{"index":"0738edc7-2642-4a96-b343-d607803cd332","name":"spec-56581-GAC081N30B1_sp14-014.fits.gz","to(...TRUNCATED)
End of preview. Expand in Data Studio

Summary

This dataset contains spectral classification tasks built for tool-using models. Each example includes a full-spectrum image, a chat-style prompt, and ground-truth labels for binary decisions. The metadata also provides the underlying spectral arrays (wavelength and flux) to support visualization or custom feature extraction.

Data Files

All files are under benchmark/data and share the same schema. File suffixes correspond to target classes:

  • cc -> Carbon Star (C-type) (data_source: carbon)
  • cv -> Cataclysmic Variable (CV)
  • gm -> M-type Giant (gM)
  • ss -> S-type Star
  • wd -> White Dwarf (WD)

Splits and Sizes

split file rows
train train_cc.parquet 671
train train_cv.parquet 711
train train_gm.parquet 658
train train_ss.parquet 706
train train_wd.parquet 618
test test_cc.parquet 1321
test test_cv.parquet 1458
test test_gm.parquet 1321
test test_ss.parquet 1442
test test_wd.parquet 1212

Totals: train 3364, test 6754.

Data Structure

Each example contains the following fields:

  • images: list with a single image object
  • data_source: class key string, e.g. carbon, cv, gm, ss, wd
  • prompt: list of chat messages
    • role: message role (system, user, etc.)
    • content: message text (the user message includes an <image> placeholder)
  • reward_model: struct with ground-truth labels
    • ground_truth: string label (typically YES or NO)
    • type: label source (e.g. rule)
  • agent_name: string identifier for the agent configuration
  • extra_info: metadata
    • index: unique id string
    • name: spectrum file name
    • tools_kwargs.spectral_visualization_tool.create_kwargs:
      • flux: list of floats (length ~3909)
      • wavelength: list of floats (length ~3909)
      • redshift: float

Notes

  • images contains the full-spectrum overview image for the example.
  • extra_info provides raw arrays to recreate spectrum plots.

Citation

@misc{Jia2026SpecO3,
  author       = {Minghui Jia and Qichao Zhang and Ali Luo and Linjing Li and Shuo Ye and Hailing Lu and Wen Hou and Dongbin Zhao},
  title        = {Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection},
  eprint       = {2601.06498},
  archivePrefix= {arXiv},
  primaryClass = {cs.CL},
  year         = {2026},
  url          = {https://arxiv.org/abs/2601.06498},
  doi          = {10.48550/arXiv.2601.06498}
}
Downloads last month
41

Collection including Maxwell-Jia/SpecVI-Bench

Paper for Maxwell-Jia/SpecVI-Bench