Clarify partial EnMAP pretraining, intended research use, and performance limitations

README.md

@@ -23,6 +23,16 @@ working `AutoModel` interface. No project checkout is required.
 - [Project website and updated manuscript](https://uiuctml.github.io/LESSViT/)
 - [Source repository](https://github.com/uiuctml/LESSViT)
 
+## Intended Use and Limitations
+
+**This checkpoint was pretrained on a partial subset of EnMAP data, not the complete EnMAP corpus.** It is released primarily to investigate whether explicit, efficient spatial–spectral modeling can improve representation robustness under changes in spectral configuration, including band sampling, channel count, and simulated sensor responses.
+
+**This release should not be interpreted as a fully optimized EnMAP foundation model or as evidence of universally superior downstream performance.** Its training coverage, pretraining scale, and optimization settings reflect the scope of an architectural study. The reported experiments support conclusions under the evaluated protocols; they do not establish optimal performance on the full EnMAP dataset, unseen geographic distributions, or arbitrary downstream tasks.
+
+Performance depends on the target data, preprocessing, spectral configuration, and adaptation procedure. In particular, robustness to spectral changes does not imply the highest accuracy under every fixed spectral configuration. Comparisons should account for differences in pretraining data coverage, training budget, spatial resolution, and fine-tuning protocol.
+
+Users should independently validate this checkpoint for their intended application. Broader pretraining and task-specific adaptation may be necessary, and no guarantee is made regarding accuracy, generalization, or fitness for operational use.
+
 ## Install
 
 Reference environment: Python 3.11.

SHA256SUMS

@@ -1,4 +1,4 @@
-a10bcd03f32b2dd16557b340dfe7ed2bab268a51d45488bc240c077de3710e29  README.md
+ab5614a0f5d5f155884494b457af789a4d231f9012a19003f276f008ee4a534a  README.md
 d6fcf9ed303752ba5ea7792d3fa00e16ac35cd561b6df23e5a19f4d219be6aac  attention_ops.py
 5aee6c840ac260cde0131ba16ac4c637da27cbe63f94aa0cd5d72f6171436e5d  config.json
 0e049d15e1a8229824e4b87f0d3312f55e58c0a2985bd36a69fa5f7790d024de  hyperspectral_patch_embed.py