docs: complete English reproduction card

README.md

@@ -10,17 +10,19 @@ library_name: pytorch
 
 # LiNO
 
-## Model
+## Model and experiment
 
-This package reproduces the one-dimensional viscous Burgers final-state prediction experiment. The trained checkpoint is `weight/best_model.pth`; model code, configuration, training, inference, and visualization scripts are included. The package was trained once; reported numbers are not guarantees for another run.
+This package reproduces the one-dimensional viscous Burgers final-state prediction experiment from the [paper](https://arxiv.org/abs/2606.03262). LiNO uses eight light-inspired propagation modules with width 128 and efficient scattering. Initial field and spatial coordinates on a 256-point grid are mapped to the final Burgers field.
+
+The package includes model code, `config/config.yaml`, training, inference and visualization scripts, the recorded `results/`, and the selected `weight/best_model.pth` checkpoint.
 
 ## Data
 
 Download only the needed file from [OneScience/fno](https://www.modelscope.cn/datasets/OneScience/fno) with `modelscope download OneScience/fno data/burgers_data_R10.mat --repo-type dataset --local_dir ./data`. The model reads `data/data/burgers_data_R10.mat`.
 
-Data provenance: [https://www.modelscope.cn/datasets/OneScience/fno](https://www.modelscope.cn/datasets/OneScience/fno).
+Original dataset: https://www.modelscope.cn/datasets/OneScience/fno Download the dataset before running inference where an external dataset is required. The release configuration uses relative paths, not SCNet personal-directory paths.
 
-## Usage
+## Installation and usage
 
 ```bash
 hf download OneScience-Group/LiNO --local-dir ./LiNO
@@ -30,8 +32,16 @@ python scripts/inference.py
 python scripts/result.py
 ```
 
-For training, run `python scripts/train.py` after installing the appropriate accelerator-enabled PyTorch environment and downloading the data above. See `config/config.yaml` for experiment parameters. Preserve the included checkpoint before retraining.
+For a fresh training run, use an allocated GPU/DCU compute node with a compatible PyTorch build, keep a separate copy of the supplied checkpoint, then run `python scripts/train.py` from the package root. The full budget is specified in `config/config.yaml`. Cluster-specific Slurm scripts, if present, need adaptation outside the original cluster.
+
+## Training and reported result
+
+The run completed 500 epochs with AdamW and a batch size of four. The best checkpoint was selected on 448 validation samples at epoch 495; no independent test split is claimed.
+
+Validation relative L2 was 0.00816638 versus the paper Table 1 value of 0.0109, about 25.1% lower. This is a validation result, not an independent test score. See `results/` for the recorded metrics and visualizations. The supplied checkpoint comes from a completed run; another run may differ.
 
-## Result and citation
+## Source and license
 
-validation relative L2: 0.00816638; paper Table 1: 0.0109. See `results/` for the recorded outputs and the [original paper or data page](https://arxiv.org/abs/2606.03262) for the research context. The dataset license, where not separately stated by its author, must not be inferred from the code license.
+- Paper: https://arxiv.org/abs/2606.03262.
+- Dataset source: https://www.modelscope.cn/datasets/OneScience/fno.
+- This model package uses the license indicated in the card metadata. Dataset redistribution terms, where not separately stated, must not be inferred from the code license.