1name: baselines2description: Baseline specifications (matched information set = completed bars at the origin; tuned on the training/validation periods only).3naive_rw:4 window: 390 one-minute bars5 distribution: Gaussian, zero mean, scale = trailing RMS one-minute return x sqrt(H)6seasonal_vol:7 profile: past-20-session mean squared return per slot (past only)8 level_adjustment: trailing 30-minute RV over the seasonal counterpart, clipped to [0.25, 4]9ewma:10 lambda: 0.97 per minute11 nu: 512 history: last 3 sessions of one-minute returns13har_rv:14 regressors: log RV 30 min, log RV 390 min, log RV 5 days, time of day, time of day squared, log H15 fit: OLS on training origins, one regression per horizon16 nu: method of moments on standardised training residuals, clipped to [2.5, 50]17garch_t:18 model: GARCH(1,1) with Student-t innovations on 5-minute training returns, one fit per instrument (arch 8)19 forecast: analytic variance term structure over ceil(H/5) steps; own filter over the last 400 five-minute returns20ridge:21 alpha: 1.022 features: 19 origin features (src/chronos_x/baselines/features.py)23 targets: scaled cumulative return (location) and log scaled realised variance (scale); nu from residual kurtosis24elastic_net:25 alpha: 0.00126 l1_ratio: 0.527lightgbm:28 n_estimators: 40029 learning_rate: 0.0330 num_leaves: 3131 subsample: 0.832 colsample_bytree: 0.833mlp:34 inputs: last 60 one-minute bars (15 features each) + 9 global features + future calendar35 hidden: 256 x 2 (GELU, dropout 0.1)36 head: Student-t per future minute, masked NLL37tcn:38 channels: 9639 blocks: 6 dilated causal convolutions (kernel 3, dilation 1..32) over 390 one-minute bars40 head: Student-t per future minute, masked NLL41not_run:42 chronos_timesfm: "pretrained foundation models not evaluated: weights not available offline on the compute node; tokenisers assume a single real-valued series without missingness masks; licenses/terms not reviewed within this project"43 egarch: "multi-step forecasts require simulation; too slow for the number of evaluation origins; GARCH(1,1)-t reported"44 patchtst_itransformer: "the one-minute-only MRPT variant is the equal-parameter patch-transformer control; iTransformer not implemented"45