### 1. los datos: 2.189 días de observaciones reales (Open-Meteo)
  filas: 2189  reparto: {'si': 1388, 'no': 801}

### 2. entrenar
Training OK: 587b5bf2
Best epoch: 11
Best validation loss: 0.533861
Accuracy: 0.762557
Artifacts: runs/v1

### 3. exportar
Bundle OK: paquete
Files: README.md, example_input.json, expected_output.json, export_manifest.json, inference_spec.json, model.mxai, model.mxtrain, model.onnx, model_manifest.json, params.best.json, predict.py, reproduce.json, requirements.txt, space/README.md, space/app.py, space/requirements.txt
Equivalence PASS: max_abs_diff=7.45e-08
Self-usable: yes (predict.py + inference_spec.json included)
Reproducible: no — Not reproducible: this model has no data recipe, so its dataset cannot be regenerated and compared; why there is none is not recorded in the package; the dataset generation seed is unknown.

### 4. predecir un día concreto, sin MatrixAI
  día húmedo y con presión cayendo -> {"no":0.05672343820333481,"si":0.9432765245437622}
  día seco y anticiclónico         -> {"no":0.7396246790885925,"si":0.26037532091140747}

### 5. verificar: aquí NO hay receta, y el informe lo dice
manifest  PASS
R1        INCOMPARABLE  — the package itself declares R1 is not possible: "Cannot regenerate the dataset from the recipe and compare its full sha256: this model has no data recipe, so its dataset cannot be regenerated and compared; why there is none is not recorded in the package; the dataset generation seed is unknown."
training  INCOMPARABLE  — the dataset could not be regenerated, so there is nothing to train on
R3        NOT_RUN  — the retraining run did not complete, so there is no fresh value to contrast: the dataset could not be regenerated, so there is nothing to train on