newsrex/LSTUR-PYTORCH-MIND-small

NewsReX LSTUR — PYTORCH — MIND-small

LSTUR news recommendation model trained on MIND-small using the NewsReX framework (PYTORCH).

Test Results

Seed	AUC	MRR	NDCG@5	NDCG@10
123	0.6503	0.3030	0.3341	0.3982
42	0.6590	0.3101	0.3433	0.4057
456 *	0.6592	0.3095	0.3423	0.4058
mean ± std	0.6561±0.0041	0.3075±0.0032	0.3399±0.0041	0.4032±0.0036

* Best seed (weights at repo root)

Repository Structure

newsrex/LSTUR-PYTORCH-MIND-small/
├── model.safetensors          ← best seed (456)
├── test_results.json
├── training_run_summary.json
├── seed_123/model.safetensors
├── seed_42/model.safetensors
├── seed_456/model.safetensors
└── README.md

Usage

git clone https://github.com/igor17400/NewsReX.git
cd NewsReX && uv sync

# Run evaluation with best seed weights
uv run python src/eval.py \
    experiment=mind/lstur \
    framework=pytorch \
    weights=hf://newsrex/LSTUR-PYTORCH-MIND-small/model.safetensors

# Run evaluation with a specific seed
uv run python src/eval.py \
    experiment=mind/lstur \
    framework=pytorch \
    weights=hf://newsrex/LSTUR-PYTORCH-MIND-small/seed_42/model.safetensors

Citation

@misc{newsrex2026,
  title={NewsReX: An Open-Source Multi-Framework for Neural News Recommendation},
  author={Igor L. R. Azevedo and Toyotaro Suzumura and Yuichiro Yasui},
  year={2025},
  eprint={2508.21572},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2508.21572},
}