1name: baselines2description: Baseline specifications (matched information set = completed bars at the origin; tuned on the training/validation periods only).3naive_rw: {window: 390, distribution: gaussian}4seasonal_vol: {n_days: 20, level_adjustment: trailing-30-min RV ratio clipped to [0.25, 4]}5ewma: {lambda: 0.97, nu: 5, history_days: 3}6har_rv: {regressors: [log RV 30 min, log RV 390 min, log RV 5 days, time of day, time of day squared, log H], fit: OLS on training origins per horizon, nu: method of moments on standardised training residuals, clipped [2.5, 50]}7garch_t: {model: GARCH(1,1) Student-t on 5-minute training returns per instrument (arch 8), forecast: analytic term structure over ceil(H/5) steps, filter: last 400 five-minute returns}8ridge: {alpha: 1.0, features: 19 origin features (src/chronos_x/baselines/trees.py), targets: scaled cumulative return and log scaled RV}9elastic_net: {alpha: 1.0e-3, l1_ratio: 0.5}10lightgbm: {n_estimators: 400, learning_rate: 0.03, num_leaves: 31, subsample: 0.8, colsample_bytree: 0.8}11mlp: {inputs: last 60 one-minute bars + global features, hidden: 256x2, head: Student-t, loss: masked NLL}12tcn: {channels: 96, blocks: 6 dilated causal, kernel: 3, head: Student-t, loss: masked NLL}13not_run: {chronos_timesfm: "pretrained foundation models not evaluated: weights are not available offline on the compute node, their tokenisation assumes univariate real-valued series without missingness masks and their licenses/terms were not reviewed within this project (docs/MODEL_CARD.md)", egarch: "simulation-based multi-step forecasts too slow for 2M evaluation origins; GARCH(1,1)-t is reported", patchtst_itransformer: "the 1m-only MRPT variant is the equal-parameter patch-transformer baseline; iTransformer not implemented"}14