I noticed that the files train_model_noah.py , train_model_ssf.py , train_model_fact.py , and train_model_sct.py contain exactly the same code. I manually compared them side by side, and there are no functional or structural differences between them.
This seems to be a clear case of code duplication. If this is an oversight, it needs to be rectified immediately to maintain the integrity of the benchmark and avoid confusion in the community. Many researchers are building their projects on top of this benchmark, and such inconsistencies could lead to incorrect assumptions or faulty experiments.
I noticed that the files train_model_noah.py , train_model_ssf.py , train_model_fact.py , and train_model_sct.py contain exactly the same code. I manually compared them side by side, and there are no functional or structural differences between them.
This seems to be a clear case of code duplication. If this is an oversight, it needs to be rectified immediately to maintain the integrity of the benchmark and avoid confusion in the community. Many researchers are building their projects on top of this benchmark, and such inconsistencies could lead to incorrect assumptions or faulty experiments.