Raw outputs for Simulation Study 2: Error Rate

The folders contain all the raw output of the second simulation study from the paper:<br>"Generalization in neural posterior estimation: Case studies with the racing diffusion model".<br>The structure of the folders is as follows:<br><br>- `experiment_*`: Study folder<br> - `rdm_*`: Study condition folder (e.g., rdm_simple refers to the default settings)<br> - `flow_matching`: Output related to neural posterior estimation (NPE)<br> - `checkpoints`: Includes a `model.keras` file that contains the checkpoint of the NPE<br> for this condition<br> - `metrics`: Aggregated metrics based on posterior samples from NPE and MCMC<br> - `npe_samples`: Raw posterior samples from NPE<br> - `mcmc_samples`: Raw posterior samples obtained from Markov chain Monte Carlo (MCMC)<br> - `test_data`: Test datasets<br>The names of the study conditions are as follows:<br><br>- `experiment_2`:<br> - `rdm_simple`: Default settings with `mu_v_slope=1.5` and `beta_b=0.15` (condition medium-fixed)<br> - `rdm_simple_lower`: Default settings with `mu_v_slope=2.5` and `beta_b=0.25` (condition lower-fixed)<br> - `rdm_simple_meta`: Default settings with `mu_v_slope~U(0.5, 2.5)` and `beta_b~U(0.05, 0.25)` (condition full-varying)<br> - `rdm_simple_lower`: Default settings with `mu_v_slope~U(0.5, 1.5)` and `beta_b~U(0.05, 0.15)` (condition lower-varying)<br> - `rdm_simple_upper`: Default settings with `mu_v_slope~U(1.5, 2.5)` and `beta_b~U(0.15, 0.25)` (condition upper-varying)<br> - `rdm_simple_upper`: Default settings with `mu_v_slope=0.5` and `beta_b=0.05` (condition upper-fixed)<br><br>All datasets and posterior samples are stored in HDF5 files. Aggregated statistics are stored in CSV format.