# Training splits These files rebuild `/train.npz` and `val.npz` from the source datasets. | System | Source | Pool | Train / val / test | | --- | --- | --- | --- | | AL2 | Köhler et al. (2021), [AImplicitUnconstrained.tgz](https://ftp.mi.fu-berlin.de/pub/cmb-data/bgmol/datasets/minipeptides/AImplicitUnconstrained.tgz), `traj0.h5` `coordinates` | 1,000,000 frames in file order | 800k / 100k / 100k | | AL4 | Tan et al. (2025), `Ace-AAA-Nme_300K` | train ++ val ++ test, 700,000 frames | 560k / 70k / 70k | | AL6 | Tan et al. (2025), `AAAAAA_310K` | train ++ val ++ test, 300,000 frames | 240k / 30k / 30k | Download the sources (AL2: extract `traj0.h5` from the archive above; AL4, AL6: the Sequential Boltzmann Generators data of Tan et al., [Hugging Face dataset](https://huggingface.co/datasets/transferable-samplers/sequential-boltzmann-generators-data), under `Ace-AAA-Nme_300K/` and `AAAAAA_310K/`), then, with `KCMAPS_DATA` the parent `data` directory, which contains `splits/`: ```bash hf download transferable-samplers/sequential-boltzmann-generators-data --repo-type dataset --include "Ace-AAA-Nme_300K/*" --local-dir sbg ``` ```bash python -m kcmaps.training.data AL2 AImplicitUnconstrained/traj0.h5 python -m kcmaps.training.data AL4 Ace-AAA-Nme_300K/Ace-AAA-Nme_300K_{train,val,test}.npy python -m kcmaps.training.data AL6 AAAAAA_310K/AAAAAA_310K_{train,val,test}.npy ``` Each command checks the sha256 of the split indices and of the Tan et al. files against `splits.json`, builds the pool in the order above, takes the train and val slices of `pool[_split_indices.npy]` and writes `$KCMAPS_DATA//train.npz` and `val.npz` (`positions`, `(frames, atoms, 3)` float32 nm). `--splits` and `--out` override the two directories. The indices are ```python import jax, jax.numpy as jnp, numpy as np jax.config.update("jax_threefry_partitionable", True) # JAX 0.9.2 idx = np.asarray(jax.random.permutation(jax.random.PRNGKey(42), jnp.arange(N))) assert np.array_equal(idx, np.load("AL2_split_indices.npy")) ``` `splits.json` lists per system the source files, checksums and counts; the slices follow the counts in train, val, test order.