experiment:
  name: E3
  model: MP-PDE
  paper: https://arxiv.org/abs/2202.03376
  evidence_priority: paper_then_official_repo_for_missing_details
  ambiguity_policy: paper_strict  # paper_strict: omega=[-0.4,-0.4]; official_consistency: [-0.4,0.4]

paths:
  data: data/e3.h5
  checkpoint: weight/best_model.pth
  results: results
  train_history: results/train_history.json
  predictions: results/predictions.npz
  metrics: results/metrics.json

data:
  domain_length: 16.0
  final_time: 4.0
  num_time_points: 250  # E3 Table 1; nearby prose says 200
  high_resolution_nx: 200
  resolution: 100
  supported_resolutions: [100, 50, 40]
  sample_fraction: 0.3333333333333333  # user-authorized reduced run, 784/2352 trajectories exactly
  full_experiment_samples:
    train: 2096  # paper; official README says 2048
    valid: 128   # paper missing; official README reference
    test: 128    # paper missing; official README reference
  train_samples: 698
  valid_samples: 43
  test_samples: 43
  seed: 0
  equation:
    alpha_range: [0.0, 3.0]
    beta_range: [0.0, 0.4]
    gamma_range: [0.0, 1.0]
  forcing:
    terms: 5
    amplitude_range: [-0.5, 0.5]
    paper_omega_range: [-0.4, -0.4]
    official_consistency_omega_range: [-0.4, 0.4]
    modes: [1, 2, 3]
    phase_range: [0.0, 6.283185307179586]
  generation:
    cfl: 0.2
    min_dt: 1.0e-8
    max_substeps: 10000
    weno_epsilon: 1.0e-6
    compression: gzip
    compression_level: 4
  parallel_generation:
    workers: 8
    max_in_flight: 16
    flush_every: 8
    resume_partial: true

model:
  time_window: 25  # paper missing; official training command reference
  hidden_dim: 164
  message_passing_layers: 6
  neighbor_offsets: [-3, -2, -1, 1, 2, 3]
  aggregation: sum
  instance_norm_affine: false
  decoder:
    middle_channels: 8
    kernel_sizes: [16, 26]
    strides: [3, 1]
  scaling:
    coordinates: true
    parameters: true
    solution: none

training:
  epochs: 20
  batch_size: 16
  num_workers: 0
  optimizer: AdamW
  learning_rate: 1.0e-4
  weight_decay: 1.0e-8
  loss: rmse
  loss_epsilon: 1.0e-12
  max_no_grad_pushes: 1
  scheduler:
    enabled: true
    milestones: [1, 5, 10, 15]
    gamma: 0.4
  precision: float32
  amp: false
  gradient_clip: null
  seed: 0
  deterministic: true
  device: auto
  print_interval: 10
  validation_rollout_samples: null
  test_rollout_samples: null

inference:
  batch_size: 16
  split: test
  max_samples: null
  device: auto
  forecast_start_index: 25

visualization:
  sample_index: 0
  time_indices: [25, 75, 150, 249]
  dpi: 160

paper_reference:
  metric: forecast_accumulated_mse
  values:
    100: 4.26
    50: 3.74
    40: 3.70
  note: provenance_only_not_an_assertion