{
 "deposited_utc": "2026-10-07T07:16:08Z",
 "code_commit_before_deposit": "2b88f05516ec9c741d87ce52db3682338386e0c3",
 "source": "Alexandria phonon and electron-phonon release of 2025-08-11, PBEsol, 3D, 93 files, CC BY 4.0",
 "label": "h = S_top / rho_H at a smearing of 0.030 Ry, for hydrides whose 3 n_H highest branches each carry at least 90% of their eigenvector weight on hydrogen at every stored wavevector",
 "compounds_with_spectrum": 27151,
 "hydrides_with_h": 4619,
 "prototypes": 2301,
 "splits": {
  "top": "prototypes ranked by their largest h; the leading ones are held out with all their members until a tenth of the labelled hydrides are held out",
  "a2mh6": "every compound of prototype 225_1a_2c_6e (space group 225, cubic A2MH6) is held out",
  "grouped": "five folds of whole prototypes, shuffled with seed 0",
  "random": "five folds of compounds, shuffled with seed 0; reported without a mark"
 },
 "counts": {
  "top": {
   "train_hydrides": 4103,
   "test_hydrides": 516,
   "test_prototypes": 14
  },
  "a2mh6": {
   "train_hydrides": 4551,
   "test_hydrides": 68,
   "test_prototypes": 1
  },
  "grouped_0": {
   "train_hydrides": 3028,
   "test_hydrides": 1591,
   "test_prototypes": 190
  },
  "random_0": {
   "train_hydrides": 3708,
   "test_hydrides": 911,
   "test_prototypes": 309
  },
  "grouped_1": {
   "train_hydrides": 4007,
   "test_hydrides": 612,
   "test_prototypes": 176
  },
  "random_1": {
   "train_hydrides": 3662,
   "test_hydrides": 957,
   "test_prototypes": 323
  },
  "grouped_2": {
   "train_hydrides": 3956,
   "test_hydrides": 663,
   "test_prototypes": 152
  },
  "random_2": {
   "train_hydrides": 3692,
   "test_hydrides": 927,
   "test_prototypes": 311
  },
  "grouped_3": {
   "train_hydrides": 3441,
   "test_hydrides": 1178,
   "test_prototypes": 168
  },
  "random_3": {
   "train_hydrides": 3724,
   "test_hydrides": 895,
   "test_prototypes": 309
  },
  "grouped_4": {
   "train_hydrides": 4044,
   "test_hydrides": 575,
   "test_prototypes": 151
  },
  "random_4": {
   "train_hydrides": 3690,
   "test_hydrides": 929,
   "test_prototypes": 288
  }
 },
 "baselines": {
  "gas": "36.6 eV A for every compound",
  "dos": "a constant fitted on the training side times the total density of states at the Fermi level per unit volume. The paper specifies the hydrogen-projected density of states, which the release does not store",
  "const": "the geometric mean of h on the training side"
 },
 "mark": "mean absolute error in ln h at most half that of the best baseline, with the 95% interval of the ratio, from resampling held-out prototypes, below one",
 "amendments": [
  "The training-side geometric mean is added as a third baseline and the estimator is judged against the best of the three. The paper fixed two baselines. A code test on nine of the 93 files, run on 2026-10-06 before this deposit, showed both to be far from the labels (mean absolute errors of 1.80 and 1.11 in ln h, against 0.66 for the training mean), so a mark against them alone would be met without skill. The result against the two original baselines is reported as well.",
  "Two code tests on those nine files preceded this deposit: both estimators on five grouped folds, 15 epochs for the graph network (output kept in model/results/smoke/), and the hold-out-the-top split with 2 epochs (output discarded). No estimator had been trained on the full release when this deposit was written."
 ],
 "not_run": [
  "Hold out pressure and megabar to one atmosphere: the release holds no calculation at megabar pressure.",
  "Calibration against a reference set of dense calculations: no such set exists yet.",
  "Closure of the spectrum and the end-to-end check on the transition temperature: not part of this deposit."
 ],
 "checksums": {
  "labels.csv": "1c16759a7fe5daff5a2b73a1735993613c0664f22c27e7424f4e5c7e91427b9c",
  "splits.csv": "8b642fecc62c40a21251be214b9d2f42eac4176f1da7b099c0118aee9595ebe1",
  "baselines.csv": "7bc456ad1f513b7fc37c9206666eb04463cd85acbdbee8efbeb73da4c4887b6a"
 }
}