Fix senkin_tmp predictions check

CHANGELOG.md

@@ -112,6 +112,8 @@
 
 * `senkin_tmp_train`, `senkin_tmp_predict`: Store the model bundle (the test predictions, as the solution is transductive) as an h5ad file in a directory instead of a pickle. The train image is built from `nvidia/cuda` with the current pandas 3, the predict image `openproblems/base_pytorch_nvidia:1` ships pandas 2, and unpickling the bundled `var` DataFrame raised `NotImplementedError` in `NDArrayBacked.__setstate__`, so senkin_tmp finished both CITE training runs of run_2026-09-23 but never produced a prediction. The predict step still reads the old pickle until the test resources are regenerated (PR #73).
 
+* `senkin_tmp_predict`: Compare the cell and protein names of the stored predictions as lists. The train and predict images run different pandas versions, so the same names were read back with a different index dtype and `Index.equals()` failed on every dataset (PR #75).
+
 * `scipenn`: Exit 99 (non-applicable) instead of raising a `ValueError` on anything other than GEX -> ADT (PR #77).
 
 # task_predict_modality 0.1.1

src/methods/senkin_tmp/senkin_tmp_predict/script.py

@@ -46,8 +46,8 @@ def read_predictions(model_dir):
 logger.info("Loading the predictions of the train step...")
 adata_predictions = read_predictions(par["input_model"])
 # The train step predicted the test cells of input_test_mod1 in their order; make sure nothing changed
-assert adata_predictions.obs_names.equals(adata_rna_test.obs_names), "test cells do not match the trained model"
-assert adata_predictions.var_names.equals(adata_prot_train.var_names), "proteins do not match the trained model"
+assert adata_predictions.obs_names.tolist() == adata_rna_test.obs_names.tolist(), "test cells do not match the trained model"
+assert adata_predictions.var_names.tolist() == adata_prot_train.var_names.tolist(), "proteins do not match the trained model"
 
 logger.info("Writing predictions...")
 adata_out = ad.AnnData(