---
dataset_info:
  features:
  - name: question
    dtype: string
  - name: answer
    dtype: string
  - name: articles
    list: string
  - name: instruction_full
    dtype: string
  - name: metadata
    list: string
  - name: instruction_proxy
    dtype: string
  splits:
  - name: train
    num_bytes: 2238614312
    num_examples: 7290
  - name: val
    num_bytes: 128577788
    num_examples: 413
  - name: test
    num_bytes: 261686916
    num_examples: 840
  download_size: 2617958231
  dataset_size: 2628879016
configs:
- config_name: default
  data_files:
  - split: train
    path: data/train-*
  - split: val
    path: data/val-*
  - split: test
    path: data/test-*
license: apache-2.0
language:
- en
tags:
- long-context
pretty_name: proxycot-scitrek
size_categories:
- 1K<n<10K
---

This is the SciTrek data that we used in the ProxyCoT project, and it is based on long-context reasoning (32K-128K tokens).

SciTrek is originally from https://arxiv.org/abs/2509.21028.

To use our dataset, please follow the code below.

```python
train_samples = load_dataset("oaimli/proxycot-scitrek", split="train")
dev_samples = load_dataset("oaimli/proxycot-scitrek", split="val")
test_samples = load_dataset("oaimli/proxycot-scitrek", split="test")

for sample in train_samples:
    question = sample["question"]
    answer = sample["answer"]
    metadata = sample["metadata"]
    articles = sample["articles"]
    instruction_proxy = sample["instruction_proxy"]
    instruction_full = sample["instruction_full"]

    instruction_proxy = instruction_proxy.replace("<question>", question)
    instruction_proxy = instruction_proxy.replace("<articles>", "\n\n\n".join(metadata))
    conversation_proxy = [{"role": "user", "content": instruction_proxy}]

    instruction_full = instruction_full.replace("<question>", question)
    instruction_full = instruction_full.replace("<articles>", "\n\n\n".join(articles))
    conversation_full = [{"role": "user", "content": instruction_full}]
```