diff --git a/experiments/amazon-chronos/README.md b/experiments/amazon-chronos/README.md
index 4e2a2b9d..3e292051 100644
--- a/experiments/amazon-chronos/README.md
+++ b/experiments/amazon-chronos/README.md
@@ -1,6 +1,10 @@
 # Extended comparison of Chronos against the statistical ensemble
 
-We present an extension to the [original comparison by Nixtla](https://github.com/Nixtla/nixtla/tree/main/experiments/amazon-chronos) of Chronos [1] against the SCUM ensemble [2]. In this analysis on over 200K unique time series across 28 datasets from Benchmark II in the Chronos paper [1], we show that **zero-shot** Chronos models perform comparably to this strong ensemble of 4 statistical models while being significantly faster on average. We follow the original study as closely as possible, including loading task definitions from GluonTS and computing metrics using utilsforecast.
+
+## Background
+A few weeks ago, we presented a [fully reproducible experiment](https://github.com/Nixtla/nixtla/tree/main/experiments/amazon-chronos) showing that Amazon Chronos was 10% less accurate and 500% slower than training classical statistical models. The Amazon team kindly answered by extending our benchmarking efforts, confirming our results for the selected datasets, and showing a differentiated performance for new datasets.
+
+Here we present an extension to the [original comparison by Nixtla](https://github.com/Nixtla/nixtla/tree/main/experiments/amazon-chronos) of Chronos [1] against the SCUM ensemble [2]. In this analysis on over 200K unique time series across 28 datasets from Benchmark II in the Chronos paper [1], we show that **zero-shot** Chronos models perform comparably to this strong ensemble of 4 statistical models while being significantly faster on average. We follow the original study as closely as possible, including loading task definitions from GluonTS and computing metrics using utilsforecast.
 
 ## Empirical Evaluation
 
diff --git a/experiments/amazon-chronos/collect_results.ipynb b/experiments/amazon-chronos/collect_results.ipynb
index d7c2f2c1..e2eda55d 100644
--- a/experiments/amazon-chronos/collect_results.ipynb
+++ b/experiments/amazon-chronos/collect_results.ipynb
@@ -2,12 +2,11 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "from metaflow import Flow, Run, Step"
+    "import pandas as pd"
    ]
   },
   {
@@ -19,7 +18,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -48,26 +47,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
-    "save_to_disk = False"
+    "save_to_disk = False\n",
+    "collect_results = False"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Make sure to replace these with your run IDs!\n",
-    "results_all = pd.concat([\n",
-    "    get_results(1712079941097970),  # SeasonalNaive\n",
-    "    get_results(1712079795572065),  # StatisticalEnsemble\n",
-    "    get_results(1712080010851589),  # chronos_mini\n",
-    "    get_results(1712081461874960),  # chronos_large\n",
-    "])\n",
+    "if collect_results:\n",
+    "    from metaflow import Flow, Run, Step\n",
+    "    results_all = pd.concat([\n",
+    "        get_results(1712079941097970),  # SeasonalNaive\n",
+    "        get_results(1712079795572065),  # StatisticalEnsemble\n",
+    "        get_results(1712080010851589),  # chronos_mini\n",
+    "        get_results(1712081461874960),  # chronos_large\n",
+    "    ])\n",
     "if save_to_disk:\n",
     "    results_all.to_csv(\"results/results_all.csv\", index=False)"
    ]
@@ -81,14 +83,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
-    "results_all = []\n",
-    "for run in list(Flow(\"ForecastEvaluation\").runs())[:5]:\n",
-    "    results_all.append(get_results(run.id))\n",
-    "results_all = pd.concat(results_all).dropna(subset=\"value\").drop_duplicates([\"dataset\", \"model\", \"metric\"])\n",
+    "if collect_results:\n",
+    "    results_all = []\n",
+    "    for run in list(Flow(\"ForecastEvaluation\").runs())[:5]:\n",
+    "        results_all.append(get_results(run.id))\n",
+    "    results_all = pd.concat(results_all).dropna(subset=\"value\").drop_duplicates([\"dataset\", \"model\", \"metric\"])\n",
     "if save_to_disk:\n",
     "    results_all.to_csv(\"results/results_all.csv\", index=False)"
    ]
@@ -102,11 +105,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [],
    "source": [
-    "results_all = pd.read_csv(\"results/results_all.csv\")"
+    "results_all = pd.read_csv(\"results/results_all.csv\")\n",
+    "results_all = results_all.query(\"model.str.startswith('amazon')\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Patch Results modifying context length seen by the Statistical Ensemble"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results_all = pd.concat([\n",
+    "    results_all,\n",
+    "    pd.read_csv(\"results/complete-results.csv\"),\n",
+    "])"
    ]
   },
   {
@@ -118,7 +141,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 45,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -127,7 +150,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 46,
    "metadata": {},
    "outputs": [
     {
@@ -203,26 +226,26 @@
        "    <tr>\n",
        "      <th>australian_electricity_demand</th>\n",
        "      <td>1.340</td>\n",
-       "      <td>1.215</td>\n",
+       "      <td>1.115</td>\n",
        "      <td>1.184</td>\n",
        "      <td>0.882</td>\n",
        "      <td>0.098</td>\n",
-       "      <td>0.058</td>\n",
+       "      <td>0.057</td>\n",
        "      <td>0.054</td>\n",
        "      <td>0.042</td>\n",
        "      <td>0.059</td>\n",
-       "      <td>0.055</td>\n",
+       "      <td>0.051</td>\n",
        "      <td>0.051</td>\n",
        "      <td>0.040</td>\n",
-       "      <td>0.333</td>\n",
-       "      <td>12602.872</td>\n",
+       "      <td>0.360</td>\n",
+       "      <td>2716.869</td>\n",
        "      <td>4.703</td>\n",
        "      <td>2.116</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>car_parts_without_missing</th>\n",
        "      <td>1.120</td>\n",
-       "      <td>1.050</td>\n",
+       "      <td>1.051</td>\n",
        "      <td>0.807</td>\n",
        "      <td>0.803</td>\n",
        "      <td>2.225</td>\n",
@@ -233,15 +256,15 @@
        "      <td>0.897</td>\n",
        "      <td>0.947</td>\n",
        "      <td>0.957</td>\n",
-       "      <td>0.944</td>\n",
-       "      <td>110.575</td>\n",
+       "      <td>0.915</td>\n",
+       "      <td>37.927</td>\n",
        "      <td>61.375</td>\n",
        "      <td>5.296</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>cif_2016</th>\n",
        "      <td>1.289</td>\n",
-       "      <td>0.918</td>\n",
+       "      <td>0.902</td>\n",
        "      <td>0.986</td>\n",
        "      <td>1.025</td>\n",
        "      <td>0.056</td>\n",
@@ -249,30 +272,30 @@
        "      <td>0.015</td>\n",
        "      <td>0.019</td>\n",
        "      <td>0.094</td>\n",
-       "      <td>0.058</td>\n",
+       "      <td>0.057</td>\n",
        "      <td>0.074</td>\n",
        "      <td>0.076</td>\n",
-       "      <td>0.672</td>\n",
-       "      <td>83.170</td>\n",
+       "      <td>0.603</td>\n",
+       "      <td>9.755</td>\n",
        "      <td>3.744</td>\n",
        "      <td>1.532</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>covid_deaths</th>\n",
        "      <td>7.762</td>\n",
-       "      <td>5.246</td>\n",
+       "      <td>5.248</td>\n",
        "      <td>6.540</td>\n",
        "      <td>6.555</td>\n",
        "      <td>0.116</td>\n",
-       "      <td>0.025</td>\n",
+       "      <td>0.024</td>\n",
        "      <td>0.050</td>\n",
        "      <td>0.072</td>\n",
        "      <td>0.093</td>\n",
        "      <td>0.054</td>\n",
        "      <td>0.205</td>\n",
        "      <td>0.204</td>\n",
-       "      <td>0.883</td>\n",
-       "      <td>86.333</td>\n",
+       "      <td>0.815</td>\n",
+       "      <td>22.031</td>\n",
        "      <td>32.049</td>\n",
        "      <td>3.871</td>\n",
        "    </tr>\n",
@@ -290,72 +313,72 @@
        "      <td>0.782</td>\n",
        "      <td>0.809</td>\n",
        "      <td>0.817</td>\n",
-       "      <td>11.452</td>\n",
-       "      <td>981.563</td>\n",
+       "      <td>12.371</td>\n",
+       "      <td>874.045</td>\n",
        "      <td>8661.922</td>\n",
        "      <td>653.726</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>ercot</th>\n",
        "      <td>0.761</td>\n",
-       "      <td>1.979</td>\n",
+       "      <td>1.356</td>\n",
        "      <td>0.578</td>\n",
        "      <td>0.585</td>\n",
        "      <td>0.039</td>\n",
-       "      <td>0.050</td>\n",
+       "      <td>0.034</td>\n",
        "      <td>0.017</td>\n",
        "      <td>0.016</td>\n",
        "      <td>0.016</td>\n",
-       "      <td>0.040</td>\n",
+       "      <td>0.027</td>\n",
        "      <td>0.012</td>\n",
        "      <td>0.012</td>\n",
-       "      <td>0.375</td>\n",
-       "      <td>5119.783</td>\n",
+       "      <td>0.397</td>\n",
+       "      <td>390.501</td>\n",
        "      <td>3.666</td>\n",
        "      <td>1.979</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>ett_small_15min</th>\n",
        "      <td>0.768</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>0.638</td>\n",
        "      <td>0.714</td>\n",
        "      <td>0.739</td>\n",
        "      <td>0.143</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>0.083</td>\n",
        "      <td>0.083</td>\n",
        "      <td>0.088</td>\n",
        "      <td>0.095</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>0.100</td>\n",
        "      <td>0.110</td>\n",
        "      <td>0.116</td>\n",
-       "      <td>0.422</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>0.457</td>\n",
+       "      <td>5034.763</td>\n",
        "      <td>4.933</td>\n",
        "      <td>2.050</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>ett_small_1h</th>\n",
        "      <td>0.932</td>\n",
-       "      <td>1.003</td>\n",
+       "      <td>0.852</td>\n",
        "      <td>0.737</td>\n",
        "      <td>0.805</td>\n",
        "      <td>0.153</td>\n",
-       "      <td>0.123</td>\n",
+       "      <td>0.109</td>\n",
        "      <td>0.083</td>\n",
        "      <td>0.085</td>\n",
        "      <td>0.103</td>\n",
-       "      <td>0.131</td>\n",
+       "      <td>0.117</td>\n",
        "      <td>0.091</td>\n",
        "      <td>0.100</td>\n",
-       "      <td>0.183</td>\n",
-       "      <td>4206.250</td>\n",
+       "      <td>0.209</td>\n",
+       "      <td>332.130</td>\n",
        "      <td>4.607</td>\n",
        "      <td>1.688</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>exchange_rate</th>\n",
        "      <td>1.524</td>\n",
-       "      <td>1.429</td>\n",
+       "      <td>1.407</td>\n",
        "      <td>1.882</td>\n",
        "      <td>2.118</td>\n",
        "      <td>0.016</td>\n",
@@ -366,34 +389,34 @@
        "      <td>0.004</td>\n",
        "      <td>0.006</td>\n",
        "      <td>0.007</td>\n",
-       "      <td>0.075</td>\n",
-       "      <td>259.485</td>\n",
+       "      <td>0.094</td>\n",
+       "      <td>9.354</td>\n",
        "      <td>3.613</td>\n",
        "      <td>1.554</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>fred_md</th>\n",
        "      <td>1.101</td>\n",
-       "      <td>0.489</td>\n",
+       "      <td>0.482</td>\n",
        "      <td>0.571</td>\n",
        "      <td>0.564</td>\n",
        "      <td>0.082</td>\n",
-       "      <td>0.035</td>\n",
+       "      <td>0.033</td>\n",
        "      <td>0.029</td>\n",
        "      <td>0.029</td>\n",
        "      <td>0.073</td>\n",
        "      <td>0.052</td>\n",
        "      <td>0.052</td>\n",
        "      <td>0.052</td>\n",
-       "      <td>0.872</td>\n",
-       "      <td>235.237</td>\n",
+       "      <td>0.847</td>\n",
+       "      <td>49.065</td>\n",
        "      <td>15.487</td>\n",
        "      <td>2.359</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>hospital</th>\n",
        "      <td>0.921</td>\n",
-       "      <td>0.748</td>\n",
+       "      <td>0.749</td>\n",
        "      <td>0.810</td>\n",
        "      <td>0.815</td>\n",
        "      <td>0.083</td>\n",
@@ -404,8 +427,8 @@
        "      <td>0.086</td>\n",
        "      <td>0.093</td>\n",
        "      <td>0.093</td>\n",
-       "      <td>0.880</td>\n",
-       "      <td>78.938</td>\n",
+       "      <td>0.840</td>\n",
+       "      <td>30.615</td>\n",
        "      <td>20.415</td>\n",
        "      <td>2.852</td>\n",
        "    </tr>\n",
@@ -423,15 +446,15 @@
        "      <td>0.716</td>\n",
        "      <td>0.818</td>\n",
        "      <td>0.827</td>\n",
-       "      <td>27.139</td>\n",
-       "      <td>15599.160</td>\n",
+       "      <td>29.344</td>\n",
+       "      <td>15082.485</td>\n",
        "      <td>8071.688</td>\n",
        "      <td>662.490</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>nn5_daily_without_missing</th>\n",
        "      <td>1.011</td>\n",
-       "      <td>0.844</td>\n",
+       "      <td>0.842</td>\n",
        "      <td>0.824</td>\n",
        "      <td>0.900</td>\n",
        "      <td>0.535</td>\n",
@@ -442,8 +465,8 @@
        "      <td>0.105</td>\n",
        "      <td>0.103</td>\n",
        "      <td>0.112</td>\n",
-       "      <td>0.882</td>\n",
-       "      <td>235.894</td>\n",
+       "      <td>0.812</td>\n",
+       "      <td>38.450</td>\n",
        "      <td>57.016</td>\n",
        "      <td>5.834</td>\n",
        "    </tr>\n",
@@ -461,46 +484,46 @@
        "      <td>0.060</td>\n",
        "      <td>0.058</td>\n",
        "      <td>0.058</td>\n",
-       "      <td>0.812</td>\n",
-       "      <td>51.829</td>\n",
+       "      <td>0.817</td>\n",
+       "      <td>5.758</td>\n",
        "      <td>3.854</td>\n",
        "      <td>1.515</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>traffic</th>\n",
        "      <td>1.785</td>\n",
-       "      <td>1.163</td>\n",
+       "      <td>1.089</td>\n",
        "      <td>0.644</td>\n",
        "      <td>0.640</td>\n",
        "      <td>0.411</td>\n",
-       "      <td>0.353</td>\n",
+       "      <td>0.341</td>\n",
        "      <td>0.115</td>\n",
        "      <td>0.120</td>\n",
        "      <td>0.244</td>\n",
-       "      <td>0.179</td>\n",
+       "      <td>0.161</td>\n",
        "      <td>0.077</td>\n",
        "      <td>0.082</td>\n",
-       "      <td>2.627</td>\n",
-       "      <td>12285.943</td>\n",
+       "      <td>3.057</td>\n",
+       "      <td>4173.052</td>\n",
        "      <td>202.267</td>\n",
        "      <td>18.898</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>weather</th>\n",
        "      <td>0.755</td>\n",
-       "      <td>0.675</td>\n",
+       "      <td>0.691</td>\n",
        "      <td>0.565</td>\n",
        "      <td>0.598</td>\n",
        "      <td>0.702</td>\n",
-       "      <td>0.207</td>\n",
+       "      <td>0.201</td>\n",
        "      <td>0.122</td>\n",
        "      <td>0.128</td>\n",
        "      <td>0.213</td>\n",
-       "      <td>0.312</td>\n",
+       "      <td>0.314</td>\n",
        "      <td>0.327</td>\n",
        "      <td>0.334</td>\n",
-       "      <td>19.922</td>\n",
-       "      <td>4159.202</td>\n",
+       "      <td>22.065</td>\n",
+       "      <td>1108.493</td>\n",
        "      <td>873.384</td>\n",
        "      <td>92.715</td>\n",
        "    </tr>\n",
@@ -518,8 +541,8 @@
        "      <td>0.073</td>\n",
        "      <td>0.076</td>\n",
        "      <td>0.082</td>\n",
-       "      <td>0.842</td>\n",
-       "      <td>84.964</td>\n",
+       "      <td>0.826</td>\n",
+       "      <td>27.710</td>\n",
        "      <td>36.095</td>\n",
        "      <td>4.165</td>\n",
        "    </tr>\n",
@@ -537,8 +560,8 @@
        "      <td>0.078</td>\n",
        "      <td>0.087</td>\n",
        "      <td>0.092</td>\n",
-       "      <td>0.836</td>\n",
-       "      <td>56.230</td>\n",
+       "      <td>0.798</td>\n",
+       "      <td>7.182</td>\n",
        "      <td>6.025</td>\n",
        "      <td>1.691</td>\n",
        "    </tr>\n",
@@ -556,15 +579,15 @@
        "      <td>0.088</td>\n",
        "      <td>0.107</td>\n",
        "      <td>0.129</td>\n",
-       "      <td>0.854</td>\n",
-       "      <td>49.356</td>\n",
+       "      <td>0.785</td>\n",
+       "      <td>5.733</td>\n",
        "      <td>3.797</td>\n",
        "      <td>1.471</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>m3_monthly</th>\n",
        "      <td>1.146</td>\n",
-       "      <td>0.826</td>\n",
+       "      <td>0.827</td>\n",
        "      <td>0.854</td>\n",
        "      <td>0.899</td>\n",
        "      <td>0.166</td>\n",
@@ -575,8 +598,8 @@
        "      <td>0.067</td>\n",
        "      <td>0.070</td>\n",
        "      <td>0.071</td>\n",
-       "      <td>0.904</td>\n",
-       "      <td>155.557</td>\n",
+       "      <td>0.902</td>\n",
+       "      <td>69.007</td>\n",
        "      <td>79.104</td>\n",
        "      <td>7.552</td>\n",
        "    </tr>\n",
@@ -594,8 +617,8 @@
        "      <td>0.022</td>\n",
        "      <td>0.024</td>\n",
        "      <td>0.025</td>\n",
-       "      <td>0.809</td>\n",
-       "      <td>57.059</td>\n",
+       "      <td>0.800</td>\n",
+       "      <td>7.381</td>\n",
        "      <td>5.051</td>\n",
        "      <td>1.609</td>\n",
        "    </tr>\n",
@@ -613,15 +636,15 @@
        "      <td>0.046</td>\n",
        "      <td>0.048</td>\n",
        "      <td>0.053</td>\n",
-       "      <td>0.877</td>\n",
-       "      <td>60.618</td>\n",
+       "      <td>0.820</td>\n",
+       "      <td>12.747</td>\n",
        "      <td>14.497</td>\n",
        "      <td>2.305</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>m3_yearly</th>\n",
        "      <td>3.172</td>\n",
-       "      <td>2.704</td>\n",
+       "      <td>2.706</td>\n",
        "      <td>3.062</td>\n",
        "      <td>3.486</td>\n",
        "      <td>0.157</td>\n",
@@ -632,8 +655,8 @@
        "      <td>0.080</td>\n",
        "      <td>0.089</td>\n",
        "      <td>0.101</td>\n",
-       "      <td>0.838</td>\n",
-       "      <td>53.385</td>\n",
+       "      <td>0.812</td>\n",
+       "      <td>8.576</td>\n",
        "      <td>9.448</td>\n",
        "      <td>1.886</td>\n",
        "    </tr>\n",
@@ -651,15 +674,15 @@
        "      <td>0.050</td>\n",
        "      <td>0.053</td>\n",
        "      <td>0.055</td>\n",
-       "      <td>1.491</td>\n",
-       "      <td>408.369</td>\n",
+       "      <td>1.633</td>\n",
+       "      <td>331.264</td>\n",
        "      <td>2403.956</td>\n",
        "      <td>170.778</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>m4_yearly</th>\n",
        "      <td>3.966</td>\n",
-       "      <td>3.002</td>\n",
+       "      <td>3.003</td>\n",
        "      <td>3.559</td>\n",
        "      <td>3.750</td>\n",
        "      <td>0.132</td>\n",
@@ -670,8 +693,8 @@
        "      <td>0.067</td>\n",
        "      <td>0.081</td>\n",
        "      <td>0.086</td>\n",
-       "      <td>1.280</td>\n",
-       "      <td>197.224</td>\n",
+       "      <td>1.336</td>\n",
+       "      <td>117.779</td>\n",
        "      <td>1027.831</td>\n",
        "      <td>77.065</td>\n",
        "    </tr>\n",
@@ -689,8 +712,8 @@
        "      <td>0.092</td>\n",
        "      <td>0.121</td>\n",
        "      <td>0.132</td>\n",
-       "      <td>0.866</td>\n",
-       "      <td>343.512</td>\n",
+       "      <td>0.865</td>\n",
+       "      <td>151.140</td>\n",
        "      <td>55.717</td>\n",
        "      <td>5.705</td>\n",
        "    </tr>\n",
@@ -708,8 +731,8 @@
        "      <td>0.072</td>\n",
        "      <td>0.081</td>\n",
        "      <td>0.090</td>\n",
-       "      <td>0.843</td>\n",
-       "      <td>69.271</td>\n",
+       "      <td>0.814</td>\n",
+       "      <td>16.846</td>\n",
        "      <td>12.613</td>\n",
        "      <td>2.191</td>\n",
        "    </tr>\n",
@@ -727,8 +750,8 @@
        "      <td>0.184</td>\n",
        "      <td>0.207</td>\n",
        "      <td>0.245</td>\n",
-       "      <td>0.842</td>\n",
-       "      <td>51.096</td>\n",
+       "      <td>0.807</td>\n",
+       "      <td>7.067</td>\n",
        "      <td>5.982</td>\n",
        "      <td>1.653</td>\n",
        "    </tr>\n",
@@ -740,31 +763,31 @@
        "metric                                 mase                      \\\n",
        "model                         SeasonalNaive StatisticalEnsemble   \n",
        "dataset                                                           \n",
-       "australian_electricity_demand         1.340               1.215   \n",
-       "car_parts_without_missing             1.120               1.050   \n",
-       "cif_2016                              1.289               0.918   \n",
-       "covid_deaths                          7.762               5.246   \n",
+       "australian_electricity_demand         1.340               1.115   \n",
+       "car_parts_without_missing             1.120               1.051   \n",
+       "cif_2016                              1.289               0.902   \n",
+       "covid_deaths                          7.762               5.248   \n",
        "dominick                              0.828               0.848   \n",
-       "ercot                                 0.761               1.979   \n",
-       "ett_small_15min                       0.768                 NaN   \n",
-       "ett_small_1h                          0.932               1.003   \n",
-       "exchange_rate                         1.524               1.429   \n",
-       "fred_md                               1.101               0.489   \n",
-       "hospital                              0.921               0.748   \n",
+       "ercot                                 0.761               1.356   \n",
+       "ett_small_15min                       0.768               0.638   \n",
+       "ett_small_1h                          0.932               0.852   \n",
+       "exchange_rate                         1.524               1.407   \n",
+       "fred_md                               1.101               0.482   \n",
+       "hospital                              0.921               0.749   \n",
        "m5                                    1.867               1.638   \n",
-       "nn5_daily_without_missing             1.011               0.844   \n",
+       "nn5_daily_without_missing             1.011               0.842   \n",
        "nn5_weekly                            1.063               0.974   \n",
-       "traffic                               1.785               1.163   \n",
-       "weather                               0.755               0.675   \n",
+       "traffic                               1.785               1.089   \n",
+       "weather                               0.755               0.691   \n",
        "m1_monthly                            1.314               1.034   \n",
        "m1_quarterly                          2.078               1.594   \n",
        "m1_yearly                             4.894               3.574   \n",
-       "m3_monthly                            1.146               0.826   \n",
+       "m3_monthly                            1.146               0.827   \n",
        "m3_other                              1.474               0.727   \n",
        "m3_quarterly                          1.425               1.164   \n",
-       "m3_yearly                             3.172               2.704   \n",
+       "m3_yearly                             3.172               2.706   \n",
        "m4_quarterly                          1.602               1.142   \n",
-       "m4_yearly                             3.966               3.002   \n",
+       "m4_yearly                             3.966               3.003   \n",
        "tourism_monthly                       1.631               1.441   \n",
        "tourism_quarterly                     1.699               1.506   \n",
        "tourism_yearly                        3.552               3.277   \n",
@@ -804,22 +827,22 @@
        "metric                          scaled_crps                      \\\n",
        "model                         SeasonalNaive StatisticalEnsemble   \n",
        "dataset                                                           \n",
-       "australian_electricity_demand         0.098               0.058   \n",
+       "australian_electricity_demand         0.098               0.057   \n",
        "car_parts_without_missing             2.225               1.132   \n",
        "cif_2016                              0.056               0.021   \n",
-       "covid_deaths                          0.116               0.025   \n",
+       "covid_deaths                          0.116               0.024   \n",
        "dominick                              2.210               0.529   \n",
-       "ercot                                 0.039               0.050   \n",
-       "ett_small_15min                       0.143                 NaN   \n",
-       "ett_small_1h                          0.153               0.123   \n",
+       "ercot                                 0.039               0.034   \n",
+       "ett_small_15min                       0.143               0.083   \n",
+       "ett_small_1h                          0.153               0.109   \n",
        "exchange_rate                         0.016               0.007   \n",
-       "fred_md                               0.082               0.035   \n",
+       "fred_md                               0.082               0.033   \n",
        "hospital                              0.083               0.047   \n",
        "m5                                    1.457               0.516   \n",
        "nn5_daily_without_missing             0.535               0.146   \n",
        "nn5_weekly                            0.256               0.077   \n",
-       "traffic                               0.411               0.353   \n",
-       "weather                               0.702               0.207   \n",
+       "traffic                               0.411               0.341   \n",
+       "weather                               0.702               0.201   \n",
        "m1_monthly                            0.193               0.121   \n",
        "m1_quarterly                          0.143               0.070   \n",
        "m1_yearly                             0.150               0.092   \n",
@@ -868,22 +891,22 @@
        "metric                                smape                      \\\n",
        "model                         SeasonalNaive StatisticalEnsemble   \n",
        "dataset                                                           \n",
-       "australian_electricity_demand         0.059               0.055   \n",
+       "australian_electricity_demand         0.059               0.051   \n",
        "car_parts_without_missing             0.310               0.897   \n",
-       "cif_2016                              0.094               0.058   \n",
+       "cif_2016                              0.094               0.057   \n",
        "covid_deaths                          0.093               0.054   \n",
        "dominick                              0.160               0.782   \n",
-       "ercot                                 0.016               0.040   \n",
-       "ett_small_15min                       0.095                 NaN   \n",
-       "ett_small_1h                          0.103               0.131   \n",
+       "ercot                                 0.016               0.027   \n",
+       "ett_small_15min                       0.095               0.100   \n",
+       "ett_small_1h                          0.103               0.117   \n",
        "exchange_rate                         0.005               0.004   \n",
        "fred_md                               0.073               0.052   \n",
        "hospital                              0.105               0.086   \n",
        "m5                                    0.404               0.716   \n",
        "nn5_daily_without_missing             0.132               0.105   \n",
        "nn5_weekly                            0.066               0.060   \n",
-       "traffic                               0.244               0.179   \n",
-       "weather                               0.213               0.312   \n",
+       "traffic                               0.244               0.161   \n",
+       "weather                               0.213               0.314   \n",
        "m1_monthly                            0.087               0.073   \n",
        "m1_quarterly                          0.095               0.078   \n",
        "m1_yearly                             0.112               0.088   \n",
@@ -932,34 +955,34 @@
        "metric                                 time                      \\\n",
        "model                         SeasonalNaive StatisticalEnsemble   \n",
        "dataset                                                           \n",
-       "australian_electricity_demand         0.333           12602.872   \n",
-       "car_parts_without_missing             0.944             110.575   \n",
-       "cif_2016                              0.672              83.170   \n",
-       "covid_deaths                          0.883              86.333   \n",
-       "dominick                             11.452             981.563   \n",
-       "ercot                                 0.375            5119.783   \n",
-       "ett_small_15min                       0.422                 NaN   \n",
-       "ett_small_1h                          0.183            4206.250   \n",
-       "exchange_rate                         0.075             259.485   \n",
-       "fred_md                               0.872             235.237   \n",
-       "hospital                              0.880              78.938   \n",
-       "m5                                   27.139           15599.160   \n",
-       "nn5_daily_without_missing             0.882             235.894   \n",
-       "nn5_weekly                            0.812              51.829   \n",
-       "traffic                               2.627           12285.943   \n",
-       "weather                              19.922            4159.202   \n",
-       "m1_monthly                            0.842              84.964   \n",
-       "m1_quarterly                          0.836              56.230   \n",
-       "m1_yearly                             0.854              49.356   \n",
-       "m3_monthly                            0.904             155.557   \n",
-       "m3_other                              0.809              57.059   \n",
-       "m3_quarterly                          0.877              60.618   \n",
-       "m3_yearly                             0.838              53.385   \n",
-       "m4_quarterly                          1.491             408.369   \n",
-       "m4_yearly                             1.280             197.224   \n",
-       "tourism_monthly                       0.866             343.512   \n",
-       "tourism_quarterly                     0.843              69.271   \n",
-       "tourism_yearly                        0.842              51.096   \n",
+       "australian_electricity_demand         0.360            2716.869   \n",
+       "car_parts_without_missing             0.915              37.927   \n",
+       "cif_2016                              0.603               9.755   \n",
+       "covid_deaths                          0.815              22.031   \n",
+       "dominick                             12.371             874.045   \n",
+       "ercot                                 0.397             390.501   \n",
+       "ett_small_15min                       0.457            5034.763   \n",
+       "ett_small_1h                          0.209             332.130   \n",
+       "exchange_rate                         0.094               9.354   \n",
+       "fred_md                               0.847              49.065   \n",
+       "hospital                              0.840              30.615   \n",
+       "m5                                   29.344           15082.485   \n",
+       "nn5_daily_without_missing             0.812              38.450   \n",
+       "nn5_weekly                            0.817               5.758   \n",
+       "traffic                               3.057            4173.052   \n",
+       "weather                              22.065            1108.493   \n",
+       "m1_monthly                            0.826              27.710   \n",
+       "m1_quarterly                          0.798               7.182   \n",
+       "m1_yearly                             0.785               5.733   \n",
+       "m3_monthly                            0.902              69.007   \n",
+       "m3_other                              0.800               7.381   \n",
+       "m3_quarterly                          0.820              12.747   \n",
+       "m3_yearly                             0.812               8.576   \n",
+       "m4_quarterly                          1.633             331.264   \n",
+       "m4_yearly                             1.336             117.779   \n",
+       "tourism_monthly                       0.865             151.140   \n",
+       "tourism_quarterly                     0.814              16.846   \n",
+       "tourism_yearly                        0.807               7.067   \n",
        "\n",
        "metric                                                                        \n",
        "model                         amazon/chronos-t5-large amazon/chronos-t5-mini  \n",
@@ -994,13 +1017,27 @@
        "tourism_yearly                                  5.982                  1.653  "
       ]
      },
-     "execution_count": 8,
+     "execution_count": 46,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# StatisticalEnsemble takes >24 hours to forecast on `ett_small_15min`, so the result is missing for this dataset.\n",
+    "original_datasets = [\n",
+    "    \"m1_monthly\",\n",
+    "    \"m1_quarterly\", \n",
+    "    \"m1_yearly\", \n",
+    "    \"m3_monthly\", \n",
+    "    \"m3_other\", \n",
+    "    \"m3_quarterly\",\n",
+    "    \"m3_yearly\", \n",
+    "    \"m4_quarterly\", \n",
+    "    \"m4_yearly\", \n",
+    "    \"tourism_monthly\",\n",
+    "    \"tourism_quarterly\", \n",
+    "    \"tourism_yearly\", \n",
+    "]\n",
     "dataset_order = [\n",
     "    \"australian_electricity_demand\", \n",
     "    \"car_parts_without_missing\",\n",
@@ -1018,18 +1055,7 @@
     "    \"nn5_weekly\", \n",
     "    \"traffic\", \n",
     "    \"weather\",\n",
-    "    \"m1_monthly\",\n",
-    "    \"m1_quarterly\", \n",
-    "    \"m1_yearly\", \n",
-    "    \"m3_monthly\", \n",
-    "    \"m3_other\", \n",
-    "    \"m3_quarterly\",\n",
-    "    \"m3_yearly\", \n",
-    "    \"m4_quarterly\", \n",
-    "    \"m4_yearly\", \n",
-    "    \"tourism_monthly\",\n",
-    "    \"tourism_quarterly\", \n",
-    "    \"tourism_yearly\", \n",
+    "    *original_datasets\n",
     "]\n",
     "table = table.reindex(dataset_order)\n",
     "table"
@@ -1046,7 +1072,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy.stats import gmean\n",
+    "\n",
+    "def calculate_gmean(table: pd.DataFrame):\n",
+    "    results = []\n",
+    "    for metric in [\"mase\", \"scaled_crps\", \"smape\"]:\n",
+    "        scaled = table[metric].divide(table[metric][\"SeasonalNaive\"], axis=0).fillna(1.0)\n",
+    "        agg = pd.concat({metric: scaled.apply(gmean)})\n",
+    "        results.append(agg)\n",
+    "    return pd.concat(results).round(3).to_frame().T"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
    "metadata": {},
    "outputs": [
     {
@@ -1094,15 +1137,15 @@
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>1.0</td>\n",
-       "      <td>0.836</td>\n",
+       "      <td>0.809</td>\n",
        "      <td>0.81</td>\n",
        "      <td>0.845</td>\n",
        "      <td>1.0</td>\n",
-       "      <td>0.505</td>\n",
+       "      <td>0.483</td>\n",
        "      <td>0.472</td>\n",
        "      <td>0.485</td>\n",
        "      <td>1.0</td>\n",
-       "      <td>0.987</td>\n",
+       "      <td>0.964</td>\n",
        "      <td>1.034</td>\n",
        "      <td>1.085</td>\n",
        "    </tr>\n",
@@ -1113,11 +1156,11 @@
       "text/plain": [
        "               mase                                              \\\n",
        "model SeasonalNaive StatisticalEnsemble amazon/chronos-t5-large   \n",
-       "0               1.0               0.836                    0.81   \n",
+       "0               1.0               0.809                    0.81   \n",
        "\n",
        "                               scaled_crps                      \\\n",
        "model amazon/chronos-t5-mini SeasonalNaive StatisticalEnsemble   \n",
-       "0                      0.845           1.0               0.505   \n",
+       "0                      0.845           1.0               0.483   \n",
        "\n",
        "                                                             smape  \\\n",
        "model amazon/chronos-t5-large amazon/chronos-t5-mini SeasonalNaive   \n",
@@ -1125,23 +1168,16 @@
        "\n",
        "                                                                          \n",
        "model StatisticalEnsemble amazon/chronos-t5-large amazon/chronos-t5-mini  \n",
-       "0                   0.987                   1.034                  1.085  "
+       "0                   0.964                   1.034                  1.085  "
       ]
      },
-     "execution_count": 9,
+     "execution_count": 48,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from scipy.stats import gmean\n",
-    "\n",
-    "results = []\n",
-    "for metric in [\"mase\", \"scaled_crps\", \"smape\"]:\n",
-    "    scaled = table[metric].divide(table[metric][\"SeasonalNaive\"], axis=0).fillna(1.0)\n",
-    "    agg = pd.concat({metric: scaled.apply(gmean)})\n",
-    "    results.append(agg)\n",
-    "pd.concat(results).round(3).to_frame().T"
+    "calculate_gmean(table)"
    ]
   },
   {
@@ -1153,7 +1189,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 51,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1180,7 +1216,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 52,
    "metadata": {},
    "outputs": [
     {
@@ -1190,34 +1226,34 @@
       "\\begin{tabular}{lllllllllllllllll}\n",
       " & \\multicolumn{4}{r}{mase} & \\multicolumn{4}{r}{scaled_crps} & \\multicolumn{4}{r}{smape} & \\multicolumn{4}{r}{time} \\\\\n",
       "model & StatisticalEnsemble & Chronos (large) & Chronos (mini) & SeasonalNaive & StatisticalEnsemble & Chronos (large) & Chronos (mini) & SeasonalNaive & StatisticalEnsemble & Chronos (large) & Chronos (mini) & SeasonalNaive & StatisticalEnsemble & Chronos (large) & Chronos (mini) & SeasonalNaive \\\\\n",
-      "australian-electricity-demand & 1.215 & \\underline{1.184} & \\textbf{0.882} & 1.340 & 0.058 & \\underline{0.054} & \\textbf{0.042} & 0.098 & 0.055 & \\underline{0.051} & \\textbf{0.040} & 0.059 & 12602.9 & 4.7 & \\underline{2.1} & \\textbf{0.3} \\\\\n",
-      "car-parts-without-missing & 1.050 & \\underline{0.807} & \\textbf{0.803} & 1.120 & 1.132 & \\underline{1.059} & \\textbf{1.022} & 2.225 & \\underline{0.897} & 0.947 & 0.957 & \\textbf{0.310} & 110.6 & 61.4 & \\underline{5.3} & \\textbf{0.9} \\\\\n",
-      "cif-2016 & \\textbf{0.918} & \\underline{0.986} & 1.025 & 1.289 & 0.021 & \\textbf{0.015} & \\underline{0.019} & 0.056 & \\textbf{0.058} & \\underline{0.074} & 0.076 & 0.094 & 83.2 & 3.7 & \\underline{1.5} & \\textbf{0.7} \\\\\n",
-      "covid-deaths & \\textbf{5.246} & \\underline{6.540} & 6.555 & 7.762 & \\textbf{0.025} & \\underline{0.050} & 0.072 & 0.116 & \\textbf{0.054} & 0.205 & 0.204 & \\underline{0.093} & 86.3 & 32.0 & \\underline{3.9} & \\textbf{0.9} \\\\\n",
-      "dominick & 0.848 & \\underline{0.786} & \\textbf{0.782} & 0.828 & 0.529 & \\underline{0.414} & \\textbf{0.399} & 2.210 & \\underline{0.782} & 0.809 & 0.817 & \\textbf{0.160} & 981.6 & 8661.9 & \\underline{653.7} & \\textbf{11.5} \\\\\n",
-      "ercot & 1.979 & \\textbf{0.578} & \\underline{0.585} & 0.761 & 0.050 & \\underline{0.017} & \\textbf{0.016} & 0.039 & 0.040 & \\textbf{0.012} & \\underline{0.012} & 0.016 & 5119.8 & 3.7 & \\underline{2.0} & \\textbf{0.4} \\\\\n",
-      "ett-small-15min & N/A & \\textbf{0.714} & \\underline{0.739} & 0.768 & N/A & \\textbf{0.083} & \\underline{0.088} & 0.143 & N/A & \\underline{0.110} & 0.116 & \\textbf{0.095} & N/A & 4.9 & \\underline{2.0} & \\textbf{0.4} \\\\\n",
-      "ett-small-1h & 1.003 & \\textbf{0.737} & \\underline{0.805} & 0.932 & 0.123 & \\textbf{0.083} & \\underline{0.085} & 0.153 & 0.131 & \\textbf{0.091} & \\underline{0.100} & 0.103 & 4206.2 & 4.6 & \\underline{1.7} & \\textbf{0.2} \\\\\n",
-      "exchange-rate & \\textbf{1.429} & 1.882 & 2.118 & \\underline{1.524} & \\textbf{0.007} & 0.011 & \\underline{0.010} & 0.016 & \\textbf{0.004} & 0.006 & 0.007 & \\underline{0.005} & 259.5 & 3.6 & \\underline{1.6} & \\textbf{0.1} \\\\\n",
-      "fred-md & \\textbf{0.489} & 0.571 & \\underline{0.564} & 1.101 & 0.035 & \\textbf{0.029} & \\underline{0.029} & 0.082 & \\textbf{0.052} & \\underline{0.052} & 0.052 & 0.073 & 235.2 & 15.5 & \\underline{2.4} & \\textbf{0.9} \\\\\n",
-      "hospital & \\textbf{0.748} & \\underline{0.810} & 0.815 & 0.921 & \\textbf{0.047} & \\underline{0.059} & 0.061 & 0.083 & \\textbf{0.086} & \\underline{0.093} & 0.093 & 0.105 & 78.9 & 20.4 & \\underline{2.9} & \\textbf{0.9} \\\\\n",
-      "m5 & 1.638 & \\underline{1.433} & \\textbf{1.432} & 1.867 & \\textbf{0.516} & 0.535 & \\underline{0.532} & 1.457 & \\underline{0.716} & 0.818 & 0.827 & \\textbf{0.404} & 15599.2 & 8071.7 & \\underline{662.5} & \\textbf{27.1} \\\\\n",
-      "nn5-daily-without-missing & \\underline{0.844} & \\textbf{0.824} & 0.900 & 1.011 & 0.146 & \\textbf{0.119} & \\underline{0.136} & 0.535 & \\underline{0.105} & \\textbf{0.103} & 0.112 & 0.132 & 235.9 & 57.0 & \\underline{5.8} & \\textbf{0.9} \\\\\n",
-      "nn5-weekly & 0.974 & \\textbf{0.929} & \\underline{0.933} & 1.063 & \\textbf{0.077} & \\underline{0.078} & 0.079 & 0.256 & 0.060 & \\textbf{0.058} & \\underline{0.058} & 0.066 & 51.8 & 3.9 & \\underline{1.5} & \\textbf{0.8} \\\\\n",
-      "traffic & 1.163 & \\underline{0.644} & \\textbf{0.640} & 1.785 & 0.353 & \\textbf{0.115} & \\underline{0.120} & 0.411 & 0.179 & \\textbf{0.077} & \\underline{0.082} & 0.244 & 12285.9 & 202.3 & \\underline{18.9} & \\textbf{2.6} \\\\\n",
-      "weather & 0.675 & \\textbf{0.565} & \\underline{0.598} & 0.755 & 0.207 & \\textbf{0.122} & \\underline{0.128} & 0.702 & \\underline{0.312} & 0.327 & 0.334 & \\textbf{0.213} & 4159.2 & 873.4 & \\underline{92.7} & \\textbf{19.9} \\\\\n",
-      "m1-monthly & \\textbf{1.034} & \\underline{1.089} & 1.193 & 1.314 & 0.121 & \\textbf{0.106} & \\underline{0.111} & 0.193 & \\textbf{0.073} & \\underline{0.076} & 0.082 & 0.087 & 85.0 & 36.1 & \\underline{4.2} & \\textbf{0.8} \\\\\n",
-      "m1-quarterly & \\textbf{1.594} & \\underline{1.730} & 1.799 & 2.078 & \\textbf{0.070} & 0.089 & \\underline{0.084} & 0.143 & \\textbf{0.078} & \\underline{0.087} & 0.092 & 0.095 & 56.2 & 6.0 & \\underline{1.7} & \\textbf{0.8} \\\\\n",
-      "m1-yearly & \\textbf{3.574} & \\underline{4.329} & 5.160 & 4.894 & \\textbf{0.092} & \\underline{0.117} & 0.119 & 0.150 & \\textbf{0.088} & \\underline{0.107} & 0.129 & 0.112 & 49.4 & 3.8 & \\underline{1.5} & \\textbf{0.9} \\\\\n",
-      "m3-monthly & \\textbf{0.826} & \\underline{0.854} & 0.899 & 1.146 & \\textbf{0.078} & \\underline{0.083} & 0.084 & 0.166 & \\textbf{0.067} & \\underline{0.070} & 0.071 & 0.086 & 155.6 & 79.1 & \\underline{7.6} & \\textbf{0.9} \\\\\n",
-      "m3-other & \\textbf{0.727} & \\underline{0.845} & 0.869 & 1.474 & \\textbf{0.027} & 0.033 & \\underline{0.032} & 0.070 & \\textbf{0.022} & \\underline{0.024} & 0.025 & 0.041 & 57.1 & 5.1 & \\underline{1.6} & \\textbf{0.8} \\\\\n",
-      "m3-quarterly & \\textbf{1.164} & \\underline{1.170} & 1.292 & 1.425 & \\textbf{0.053} & \\underline{0.066} & 0.068 & 0.096 & \\textbf{0.046} & \\underline{0.048} & 0.053 & 0.055 & 60.6 & 14.5 & \\underline{2.3} & \\textbf{0.9} \\\\\n",
-      "m3-yearly & \\textbf{2.704} & \\underline{3.062} & 3.486 & 3.172 & \\textbf{0.103} & \\underline{0.111} & 0.118 & 0.157 & \\textbf{0.080} & \\underline{0.089} & 0.101 & 0.089 & 53.4 & 9.4 & \\underline{1.9} & \\textbf{0.8} \\\\\n",
-      "m4-quarterly & \\textbf{1.142} & \\underline{1.218} & 1.269 & 1.602 & \\textbf{0.062} & \\underline{0.068} & 0.068 & 0.113 & \\textbf{0.050} & \\underline{0.053} & 0.055 & 0.063 & 408.4 & 2404.0 & \\underline{170.8} & \\textbf{1.5} \\\\\n",
-      "m4-yearly & \\textbf{3.002} & \\underline{3.559} & 3.750 & 3.966 & \\textbf{0.081} & \\underline{0.097} & 0.100 & 0.132 & \\textbf{0.067} & \\underline{0.081} & 0.086 & 0.082 & 197.2 & 1027.8 & \\underline{77.1} & \\textbf{1.3} \\\\\n",
-      "tourism-monthly & \\textbf{1.441} & 1.783 & 1.974 & \\underline{1.631} & \\textbf{0.072} & \\underline{0.082} & 0.084 & 0.114 & \\textbf{0.092} & 0.121 & 0.132 & \\underline{0.108} & 343.5 & 55.7 & \\underline{5.7} & \\textbf{0.9} \\\\\n",
-      "tourism-quarterly & \\textbf{1.506} & \\underline{1.636} & 1.800 & 1.699 & \\textbf{0.058} & \\underline{0.060} & 0.063 & 0.101 & \\textbf{0.072} & \\underline{0.081} & 0.090 & 0.083 & 69.3 & 12.6 & \\underline{2.2} & \\textbf{0.8} \\\\\n",
-      "tourism-yearly & \\textbf{3.277} & 3.641 & 4.175 & \\underline{3.552} & \\textbf{0.111} & \\underline{0.126} & 0.142 & 0.160 & \\textbf{0.184} & \\underline{0.207} & 0.245 & 0.211 & 51.1 & 6.0 & \\underline{1.7} & \\textbf{0.8} \\\\\n",
+      "australian-electricity-demand & \\underline{1.115} & 1.184 & \\textbf{0.882} & 1.340 & 0.057 & \\underline{0.054} & \\textbf{0.042} & 0.098 & \\underline{0.051} & 0.051 & \\textbf{0.040} & 0.059 & 2716.9 & 4.7 & \\underline{2.1} & \\textbf{0.4} \\\\\n",
+      "car-parts-without-missing & 1.051 & \\underline{0.807} & \\textbf{0.803} & 1.120 & 1.132 & \\underline{1.059} & \\textbf{1.022} & 2.225 & \\underline{0.897} & 0.947 & 0.957 & \\textbf{0.310} & 37.9 & 61.4 & \\underline{5.3} & \\textbf{0.9} \\\\\n",
+      "cif-2016 & \\textbf{0.902} & \\underline{0.986} & 1.025 & 1.289 & 0.021 & \\textbf{0.015} & \\underline{0.019} & 0.056 & \\textbf{0.057} & \\underline{0.074} & 0.076 & 0.094 & 9.8 & 3.7 & \\underline{1.5} & \\textbf{0.6} \\\\\n",
+      "covid-deaths & \\textbf{5.248} & \\underline{6.540} & 6.555 & 7.762 & \\textbf{0.024} & \\underline{0.050} & 0.072 & 0.116 & \\textbf{0.054} & 0.205 & 0.204 & \\underline{0.093} & 22.0 & 32.0 & \\underline{3.9} & \\textbf{0.8} \\\\\n",
+      "dominick & 0.848 & \\underline{0.786} & \\textbf{0.782} & 0.828 & 0.529 & \\underline{0.414} & \\textbf{0.399} & 2.210 & \\underline{0.782} & 0.809 & 0.817 & \\textbf{0.160} & 874.0 & 8661.9 & \\underline{653.7} & \\textbf{12.4} \\\\\n",
+      "ercot & 1.356 & \\textbf{0.578} & \\underline{0.585} & 0.761 & 0.034 & \\underline{0.017} & \\textbf{0.016} & 0.039 & 0.027 & \\textbf{0.012} & \\underline{0.012} & 0.016 & 390.5 & 3.7 & \\underline{2.0} & \\textbf{0.4} \\\\\n",
+      "ett-small-15min & \\textbf{0.638} & \\underline{0.714} & 0.739 & 0.768 & \\textbf{0.083} & \\underline{0.083} & 0.088 & 0.143 & \\underline{0.100} & 0.110 & 0.116 & \\textbf{0.095} & 5034.8 & 4.9 & \\underline{2.0} & \\textbf{0.5} \\\\\n",
+      "ett-small-1h & 0.852 & \\textbf{0.737} & \\underline{0.805} & 0.932 & 0.109 & \\textbf{0.083} & \\underline{0.085} & 0.153 & 0.117 & \\textbf{0.091} & \\underline{0.100} & 0.103 & 332.1 & 4.6 & \\underline{1.7} & \\textbf{0.2} \\\\\n",
+      "exchange-rate & \\textbf{1.407} & 1.882 & 2.118 & \\underline{1.524} & \\textbf{0.007} & 0.011 & \\underline{0.010} & 0.016 & \\textbf{0.004} & 0.006 & 0.007 & \\underline{0.005} & 9.4 & 3.6 & \\underline{1.6} & \\textbf{0.1} \\\\\n",
+      "fred-md & \\textbf{0.482} & 0.571 & \\underline{0.564} & 1.101 & 0.033 & \\textbf{0.029} & \\underline{0.029} & 0.082 & \\textbf{0.052} & \\underline{0.052} & 0.052 & 0.073 & 49.1 & 15.5 & \\underline{2.4} & \\textbf{0.8} \\\\\n",
+      "hospital & \\textbf{0.749} & \\underline{0.810} & 0.815 & 0.921 & \\textbf{0.047} & \\underline{0.059} & 0.061 & 0.083 & \\textbf{0.086} & \\underline{0.093} & 0.093 & 0.105 & 30.6 & 20.4 & \\underline{2.9} & \\textbf{0.8} \\\\\n",
+      "m5 & 1.638 & \\underline{1.433} & \\textbf{1.432} & 1.867 & \\textbf{0.516} & 0.535 & \\underline{0.532} & 1.457 & \\underline{0.716} & 0.818 & 0.827 & \\textbf{0.404} & 15082.5 & 8071.7 & \\underline{662.5} & \\textbf{29.3} \\\\\n",
+      "nn5-daily-without-missing & \\underline{0.842} & \\textbf{0.824} & 0.900 & 1.011 & 0.146 & \\textbf{0.119} & \\underline{0.136} & 0.535 & \\underline{0.105} & \\textbf{0.103} & 0.112 & 0.132 & 38.4 & 57.0 & \\underline{5.8} & \\textbf{0.8} \\\\\n",
+      "nn5-weekly & 0.974 & \\textbf{0.929} & \\underline{0.933} & 1.063 & \\textbf{0.077} & \\underline{0.078} & 0.079 & 0.256 & 0.060 & \\textbf{0.058} & \\underline{0.058} & 0.066 & 5.8 & 3.9 & \\underline{1.5} & \\textbf{0.8} \\\\\n",
+      "traffic & 1.089 & \\underline{0.644} & \\textbf{0.640} & 1.785 & 0.341 & \\textbf{0.115} & \\underline{0.120} & 0.411 & 0.161 & \\textbf{0.077} & \\underline{0.082} & 0.244 & 4173.1 & 202.3 & \\underline{18.9} & \\textbf{3.1} \\\\\n",
+      "weather & 0.691 & \\textbf{0.565} & \\underline{0.598} & 0.755 & 0.201 & \\textbf{0.122} & \\underline{0.128} & 0.702 & \\underline{0.314} & 0.327 & 0.334 & \\textbf{0.213} & 1108.5 & 873.4 & \\underline{92.7} & \\textbf{22.1} \\\\\n",
+      "m1-monthly & \\textbf{1.034} & \\underline{1.089} & 1.193 & 1.314 & 0.121 & \\textbf{0.106} & \\underline{0.111} & 0.193 & \\textbf{0.073} & \\underline{0.076} & 0.082 & 0.087 & 27.7 & 36.1 & \\underline{4.2} & \\textbf{0.8} \\\\\n",
+      "m1-quarterly & \\textbf{1.594} & \\underline{1.730} & 1.799 & 2.078 & \\textbf{0.070} & 0.089 & \\underline{0.084} & 0.143 & \\textbf{0.078} & \\underline{0.087} & 0.092 & 0.095 & 7.2 & 6.0 & \\underline{1.7} & \\textbf{0.8} \\\\\n",
+      "m1-yearly & \\textbf{3.574} & \\underline{4.329} & 5.160 & 4.894 & \\textbf{0.092} & \\underline{0.117} & 0.119 & 0.150 & \\textbf{0.088} & \\underline{0.107} & 0.129 & 0.112 & 5.7 & 3.8 & \\underline{1.5} & \\textbf{0.8} \\\\\n",
+      "m3-monthly & \\textbf{0.827} & \\underline{0.854} & 0.899 & 1.146 & \\textbf{0.078} & \\underline{0.083} & 0.084 & 0.166 & \\textbf{0.067} & \\underline{0.070} & 0.071 & 0.086 & 69.0 & 79.1 & \\underline{7.6} & \\textbf{0.9} \\\\\n",
+      "m3-other & \\textbf{0.727} & \\underline{0.845} & 0.869 & 1.474 & \\textbf{0.027} & 0.033 & \\underline{0.032} & 0.070 & \\textbf{0.022} & \\underline{0.024} & 0.025 & 0.041 & 7.4 & 5.1 & \\underline{1.6} & \\textbf{0.8} \\\\\n",
+      "m3-quarterly & \\textbf{1.164} & \\underline{1.170} & 1.292 & 1.425 & \\textbf{0.053} & \\underline{0.066} & 0.068 & 0.096 & \\textbf{0.046} & \\underline{0.048} & 0.053 & 0.055 & 12.7 & 14.5 & \\underline{2.3} & \\textbf{0.8} \\\\\n",
+      "m3-yearly & \\textbf{2.706} & \\underline{3.062} & 3.486 & 3.172 & \\textbf{0.103} & \\underline{0.111} & 0.118 & 0.157 & \\textbf{0.080} & \\underline{0.089} & 0.101 & 0.089 & 8.6 & 9.4 & \\underline{1.9} & \\textbf{0.8} \\\\\n",
+      "m4-quarterly & \\textbf{1.142} & \\underline{1.218} & 1.269 & 1.602 & \\textbf{0.062} & \\underline{0.068} & 0.068 & 0.113 & \\textbf{0.050} & \\underline{0.053} & 0.055 & 0.063 & 331.3 & 2404.0 & \\underline{170.8} & \\textbf{1.6} \\\\\n",
+      "m4-yearly & \\textbf{3.003} & \\underline{3.559} & 3.750 & 3.966 & \\textbf{0.081} & \\underline{0.097} & 0.100 & 0.132 & \\textbf{0.067} & \\underline{0.081} & 0.086 & 0.082 & 117.8 & 1027.8 & \\underline{77.1} & \\textbf{1.3} \\\\\n",
+      "tourism-monthly & \\textbf{1.441} & 1.783 & 1.974 & \\underline{1.631} & \\textbf{0.072} & \\underline{0.082} & 0.084 & 0.114 & \\textbf{0.092} & 0.121 & 0.132 & \\underline{0.108} & 151.1 & 55.7 & \\underline{5.7} & \\textbf{0.9} \\\\\n",
+      "tourism-quarterly & \\textbf{1.506} & \\underline{1.636} & 1.800 & 1.699 & \\textbf{0.058} & \\underline{0.060} & 0.063 & 0.101 & \\textbf{0.072} & \\underline{0.081} & 0.090 & 0.083 & 16.8 & 12.6 & \\underline{2.2} & \\textbf{0.8} \\\\\n",
+      "tourism-yearly & \\textbf{3.277} & 3.641 & 4.175 & \\underline{3.552} & \\textbf{0.111} & \\underline{0.126} & 0.142 & 0.160 & \\textbf{0.184} & \\underline{0.207} & 0.245 & 0.211 & 7.1 & 6.0 & \\underline{1.7} & \\textbf{0.8} \\\\\n",
       "\\end{tabular}\n",
       "\n"
      ]
@@ -1226,11 +1262,18 @@
    "source": [
     "print(full_df.style.to_latex().replace(\"nan\", \"N/A\"))"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "nx",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -1244,9 +1287,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.14"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }
diff --git a/experiments/amazon-chronos/results/complete-results.csv b/experiments/amazon-chronos/results/complete-results.csv
new file mode 100644
index 00000000..75576d5c
--- /dev/null
+++ b/experiments/amazon-chronos/results/complete-results.csv
@@ -0,0 +1,225 @@
+dataset,metric,model,value
+m5,mase,SeasonalNaive,1.8674323634298993
+m5,mase,StatisticalEnsemble,1.638152191603833
+m5,scaled_crps,SeasonalNaive,1.4574002623684272
+m5,scaled_crps,StatisticalEnsemble,0.5163249612630462
+m5,smape,SeasonalNaive,0.40357140598445107
+m5,smape,StatisticalEnsemble,0.7164228919710989
+m5,time,SeasonalNaive,29.344236135482788
+m5,time,StatisticalEnsemble,15082.48518037796
+dominick,mase,SeasonalNaive,0.8275396708993014
+dominick,mase,StatisticalEnsemble,0.8480031538431272
+dominick,scaled_crps,SeasonalNaive,2.210459061912306
+dominick,scaled_crps,StatisticalEnsemble,0.5288209674678412
+dominick,smape,SeasonalNaive,0.16016363526707927
+dominick,smape,StatisticalEnsemble,0.7823167704484896
+dominick,time,SeasonalNaive,12.37143611907959
+dominick,time,StatisticalEnsemble,874.0449843406677
+nn5_daily_without_missing,mase,SeasonalNaive,1.0112834698529345
+nn5_daily_without_missing,mase,StatisticalEnsemble,0.8423753193786091
+nn5_daily_without_missing,scaled_crps,SeasonalNaive,0.5351702879273849
+nn5_daily_without_missing,scaled_crps,StatisticalEnsemble,0.14553736570775094
+nn5_daily_without_missing,smape,SeasonalNaive,0.13235231518183066
+nn5_daily_without_missing,smape,StatisticalEnsemble,0.10488079515342492
+nn5_daily_without_missing,time,SeasonalNaive,0.8123540878295898
+nn5_daily_without_missing,time,StatisticalEnsemble,38.4502534866333
+nn5_weekly,mase,SeasonalNaive,1.062848269026432
+nn5_weekly,mase,StatisticalEnsemble,0.9735932153741834
+nn5_weekly,scaled_crps,SeasonalNaive,0.25582228822873815
+nn5_weekly,scaled_crps,StatisticalEnsemble,0.07720804470616706
+nn5_weekly,smape,SeasonalNaive,0.06633929067482891
+nn5_weekly,smape,StatisticalEnsemble,0.06025986107271241
+nn5_weekly,time,SeasonalNaive,0.8171298503875732
+nn5_weekly,time,StatisticalEnsemble,5.758360147476196
+traffic,mase,SeasonalNaive,1.7853234976926748
+traffic,mase,StatisticalEnsemble,1.0892706069210114
+traffic,scaled_crps,SeasonalNaive,0.41143591353383
+traffic,scaled_crps,StatisticalEnsemble,0.3414031320024622
+traffic,smape,SeasonalNaive,0.2438530051030199
+traffic,smape,StatisticalEnsemble,0.16081715430023405
+traffic,time,SeasonalNaive,3.057039260864258
+traffic,time,StatisticalEnsemble,4173.05211687088
+weather,mase,SeasonalNaive,0.754604010525011
+weather,mase,StatisticalEnsemble,0.6914725865126918
+weather,scaled_crps,SeasonalNaive,0.7023248754552787
+weather,scaled_crps,StatisticalEnsemble,0.20146415997944236
+weather,smape,SeasonalNaive,0.21257362636712376
+weather,smape,StatisticalEnsemble,0.31372190193744925
+weather,time,SeasonalNaive,22.064918279647827
+weather,time,StatisticalEnsemble,1108.4931182861328
+australian_electricity_demand,mase,SeasonalNaive,1.3403993825206266
+australian_electricity_demand,mase,StatisticalEnsemble,1.1151674787713628
+australian_electricity_demand,scaled_crps,SeasonalNaive,0.09814662393134205
+australian_electricity_demand,scaled_crps,StatisticalEnsemble,0.05735046591017824
+australian_electricity_demand,smape,SeasonalNaive,0.058815216824657776
+australian_electricity_demand,smape,StatisticalEnsemble,0.05083634433366544
+australian_electricity_demand,time,SeasonalNaive,0.3602612018585205
+australian_electricity_demand,time,StatisticalEnsemble,2716.8693885803223
+car_parts_without_missing,mase,SeasonalNaive,1.1201381265856145
+car_parts_without_missing,mase,StatisticalEnsemble,1.050660105202646
+car_parts_without_missing,scaled_crps,SeasonalNaive,2.2252592727461242
+car_parts_without_missing,scaled_crps,StatisticalEnsemble,1.1320439488874523
+car_parts_without_missing,smape,SeasonalNaive,0.31018504435473626
+car_parts_without_missing,smape,StatisticalEnsemble,0.8966779513784662
+car_parts_without_missing,time,SeasonalNaive,0.9146387577056884
+car_parts_without_missing,time,StatisticalEnsemble,37.927063941955566
+cif_2016,mase,SeasonalNaive,1.2892906338147911
+cif_2016,mase,StatisticalEnsemble,0.9022365251221355
+cif_2016,scaled_crps,SeasonalNaive,0.0562778589590996
+cif_2016,scaled_crps,StatisticalEnsemble,0.020951705353389735
+cif_2016,smape,SeasonalNaive,0.094358553312353
+cif_2016,smape,StatisticalEnsemble,0.05749614987192558
+cif_2016,time,SeasonalNaive,0.6034519672393799
+cif_2016,time,StatisticalEnsemble,9.755268335342407
+covid_deaths,mase,SeasonalNaive,7.7623797482537915
+covid_deaths,mase,StatisticalEnsemble,5.247590431278719
+covid_deaths,scaled_crps,SeasonalNaive,0.11604983030613081
+covid_deaths,scaled_crps,StatisticalEnsemble,0.024490948114393132
+covid_deaths,smape,SeasonalNaive,0.09313273813541141
+covid_deaths,smape,StatisticalEnsemble,0.053916857464500395
+covid_deaths,time,SeasonalNaive,0.8153104782104492
+covid_deaths,time,StatisticalEnsemble,22.0314781665802
+ercot,mase,SeasonalNaive,0.7613353868080769
+ercot,mase,StatisticalEnsemble,1.3562494003539405
+ercot,scaled_crps,SeasonalNaive,0.03946121626919911
+ercot,scaled_crps,StatisticalEnsemble,0.034150258315336315
+ercot,smape,SeasonalNaive,0.015630707775037007
+ercot,smape,StatisticalEnsemble,0.026523641327514176
+ercot,time,SeasonalNaive,0.3966584205627441
+ercot,time,StatisticalEnsemble,390.5005609989166
+ett_small_15min,mase,SeasonalNaive,0.7677330344383062
+ett_small_15min,mase,StatisticalEnsemble,0.6382274420888457
+ett_small_15min,scaled_crps,SeasonalNaive,0.1430347714870558
+ett_small_15min,scaled_crps,StatisticalEnsemble,0.08269271740545785
+ett_small_15min,smape,SeasonalNaive,0.09459814128105122
+ett_small_15min,smape,StatisticalEnsemble,0.10039187891984028
+ett_small_15min,time,SeasonalNaive,0.4571559429168701
+ett_small_15min,time,StatisticalEnsemble,5034.763110637665
+ett_small_1h,mase,SeasonalNaive,0.9316203232327729
+ett_small_1h,mase,StatisticalEnsemble,0.8519611234196047
+ett_small_1h,scaled_crps,SeasonalNaive,0.15305326839468023
+ett_small_1h,scaled_crps,StatisticalEnsemble,0.10893023778108452
+ett_small_1h,smape,SeasonalNaive,0.10259586641393585
+ett_small_1h,smape,StatisticalEnsemble,0.1171297505877785
+ett_small_1h,time,SeasonalNaive,0.2092659473419189
+ett_small_1h,time,StatisticalEnsemble,332.1302688121796
+exchange_rate,mase,SeasonalNaive,1.5238482740215735
+exchange_rate,mase,StatisticalEnsemble,1.4067630220218135
+exchange_rate,scaled_crps,SeasonalNaive,0.01577147847394285
+exchange_rate,scaled_crps,StatisticalEnsemble,0.007234723993796653
+exchange_rate,smape,SeasonalNaive,0.004661980297476255
+exchange_rate,smape,StatisticalEnsemble,0.0044398183280252015
+exchange_rate,time,SeasonalNaive,0.0944149494171142
+exchange_rate,time,StatisticalEnsemble,9.35352873802185
+fred_md,mase,SeasonalNaive,1.1008000208784752
+fred_md,mase,StatisticalEnsemble,0.4818602144932258
+fred_md,scaled_crps,SeasonalNaive,0.08215697114580049
+fred_md,scaled_crps,StatisticalEnsemble,0.03272829800542708
+fred_md,smape,SeasonalNaive,0.0729485559677336
+fred_md,smape,StatisticalEnsemble,0.05220994480946772
+fred_md,time,SeasonalNaive,0.8469631671905518
+fred_md,time,StatisticalEnsemble,49.06454372406006
+hospital,mase,SeasonalNaive,0.9205278258071787
+hospital,mase,StatisticalEnsemble,0.7485655129982478
+hospital,scaled_crps,SeasonalNaive,0.08269508339071587
+hospital,scaled_crps,StatisticalEnsemble,0.046899209602966556
+hospital,smape,SeasonalNaive,0.10512677152235944
+hospital,smape,StatisticalEnsemble,0.0859826808296096
+hospital,time,SeasonalNaive,0.8399276733398438
+hospital,time,StatisticalEnsemble,30.61531782150269
+m1_yearly,mase,SeasonalNaive,4.894322198189649
+m1_yearly,mase,StatisticalEnsemble,3.574145484272531
+m1_yearly,scaled_crps,SeasonalNaive,0.14966361102972647
+m1_yearly,scaled_crps,StatisticalEnsemble,0.0922698712661802
+m1_yearly,smape,SeasonalNaive,0.11216119472992997
+m1_yearly,smape,StatisticalEnsemble,0.08812465232291931
+m1_yearly,time,SeasonalNaive,0.7850766181945801
+m1_yearly,time,StatisticalEnsemble,5.73260760307312
+m1_quarterly,mase,SeasonalNaive,2.0775365099320915
+m1_quarterly,mase,StatisticalEnsemble,1.5939583404585844
+m1_quarterly,scaled_crps,SeasonalNaive,0.14308704311173895
+m1_quarterly,scaled_crps,StatisticalEnsemble,0.06983964327851233
+m1_quarterly,smape,SeasonalNaive,0.0947186951123695
+m1_quarterly,smape,StatisticalEnsemble,0.07840308519164578
+m1_quarterly,time,SeasonalNaive,0.7976851463317871
+m1_quarterly,time,StatisticalEnsemble,7.182486057281494
+m1_monthly,mase,SeasonalNaive,1.3144614942308708
+m1_monthly,mase,StatisticalEnsemble,1.0339353928765094
+m1_monthly,scaled_crps,SeasonalNaive,0.1929014674058537
+m1_monthly,scaled_crps,StatisticalEnsemble,0.12133830358487802
+m1_monthly,smape,SeasonalNaive,0.08654688593844032
+m1_monthly,smape,StatisticalEnsemble,0.0730905532066498
+m1_monthly,time,SeasonalNaive,0.8262171745300293
+m1_monthly,time,StatisticalEnsemble,27.710077047348022
+m3_yearly,mase,SeasonalNaive,3.1717102343239496
+m3_yearly,mase,StatisticalEnsemble,2.7060074099502085
+m3_yearly,scaled_crps,SeasonalNaive,0.15694102939190013
+m3_yearly,scaled_crps,StatisticalEnsemble,0.10307027528088823
+m3_yearly,smape,SeasonalNaive,0.08939945244930989
+m3_yearly,smape,StatisticalEnsemble,0.07999691218033288
+m3_yearly,time,SeasonalNaive,0.8121771812438965
+m3_yearly,time,StatisticalEnsemble,8.576204299926758
+m3_quarterly,mase,SeasonalNaive,1.425343782675886
+m3_quarterly,mase,StatisticalEnsemble,1.16376103880926
+m3_quarterly,scaled_crps,SeasonalNaive,0.09558308169170797
+m3_quarterly,scaled_crps,StatisticalEnsemble,0.05341428588839114
+m3_quarterly,smape,SeasonalNaive,0.05532565657960303
+m3_quarterly,smape,StatisticalEnsemble,0.04614976537182415
+m3_quarterly,time,SeasonalNaive,0.8202786445617676
+m3_quarterly,time,StatisticalEnsemble,12.746824741363524
+m3_monthly,mase,SeasonalNaive,1.1462045740727513
+m3_monthly,mase,StatisticalEnsemble,0.8267793470895428
+m3_monthly,scaled_crps,SeasonalNaive,0.1657581291619502
+m3_monthly,scaled_crps,StatisticalEnsemble,0.07762084692788024
+m3_monthly,smape,SeasonalNaive,0.0861955076505472
+m3_monthly,smape,StatisticalEnsemble,0.06722927141202216
+m3_monthly,time,SeasonalNaive,0.9021949768066406
+m3_monthly,time,StatisticalEnsemble,69.00676345825195
+m3_other,mase,SeasonalNaive,1.4741669727228415
+m3_other,mase,StatisticalEnsemble,0.7270561697641876
+m3_other,scaled_crps,SeasonalNaive,0.06994385450714162
+m3_other,scaled_crps,StatisticalEnsemble,0.026865030394171055
+m3_other,smape,SeasonalNaive,0.041276500014025615
+m3_other,smape,StatisticalEnsemble,0.021632279162270698
+m3_other,time,SeasonalNaive,0.7998371124267578
+m3_other,time,StatisticalEnsemble,7.380923748016357
+tourism_yearly,mase,SeasonalNaive,3.552009714599977
+tourism_yearly,mase,StatisticalEnsemble,3.277077062185471
+tourism_yearly,scaled_crps,SeasonalNaive,0.15974723271821942
+tourism_yearly,scaled_crps,StatisticalEnsemble,0.11125194688603007
+tourism_yearly,smape,SeasonalNaive,0.21083326227292737
+tourism_yearly,smape,StatisticalEnsemble,0.18384696850918383
+tourism_yearly,time,SeasonalNaive,0.8069603443145752
+tourism_yearly,time,StatisticalEnsemble,7.067137002944946
+tourism_quarterly,mase,SeasonalNaive,1.6989892602245846
+tourism_quarterly,mase,StatisticalEnsemble,1.5058255429273564
+tourism_quarterly,scaled_crps,SeasonalNaive,0.10142968168460322
+tourism_quarterly,scaled_crps,StatisticalEnsemble,0.0576224860295668
+tourism_quarterly,smape,SeasonalNaive,0.08304859164472883
+tourism_quarterly,smape,StatisticalEnsemble,0.07237160342871483
+tourism_quarterly,time,SeasonalNaive,0.8143134117126465
+tourism_quarterly,time,StatisticalEnsemble,16.84568691253662
+tourism_monthly,mase,SeasonalNaive,1.6309399914977092
+tourism_monthly,mase,StatisticalEnsemble,1.4409102971283867
+tourism_monthly,scaled_crps,SeasonalNaive,0.11447973197962824
+tourism_monthly,scaled_crps,StatisticalEnsemble,0.07190242570828337
+tourism_monthly,smape,SeasonalNaive,0.10834946268820275
+tourism_monthly,smape,StatisticalEnsemble,0.0915893066611628
+tourism_monthly,time,SeasonalNaive,0.864677906036377
+tourism_monthly,time,StatisticalEnsemble,151.14043617248535
+m4_yearly,mase,SeasonalNaive,3.965954942439523
+m4_yearly,mase,StatisticalEnsemble,3.002568369690919
+m4_yearly,scaled_crps,SeasonalNaive,0.13235538778860942
+m4_yearly,scaled_crps,StatisticalEnsemble,0.08139201567816129
+m4_yearly,smape,SeasonalNaive,0.0817671723808375
+m4_yearly,smape,StatisticalEnsemble,0.06748203578862982
+m4_yearly,time,SeasonalNaive,1.3356640338897705
+m4_yearly,time,StatisticalEnsemble,117.77939891815186
+m4_quarterly,mase,SeasonalNaive,1.6022471757947163
+m4_quarterly,mase,StatisticalEnsemble,1.1424438068562632
+m4_quarterly,scaled_crps,SeasonalNaive,0.11284029920261848
+m4_quarterly,scaled_crps,StatisticalEnsemble,0.061619570590469346
+m4_quarterly,smape,SeasonalNaive,0.06260683416118425
+m4_quarterly,smape,StatisticalEnsemble,0.049689605512879355
+m4_quarterly,time,SeasonalNaive,1.6325972080230713
+m4_quarterly,time,StatisticalEnsemble,331.26417803764343
diff --git a/experiments/amazon-chronos/src/eval_utils/statsforecast_pipeline.py b/experiments/amazon-chronos/src/eval_utils/statsforecast_pipeline.py
index a7a2f7e3..0bedbbcf 100644
--- a/experiments/amazon-chronos/src/eval_utils/statsforecast_pipeline.py
+++ b/experiments/amazon-chronos/src/eval_utils/statsforecast_pipeline.py
@@ -72,7 +72,7 @@ def run_statistical_ensemble(
     freq: str,
     seasonality: int,
     quantiles: List[float],
-    max_context_length: int = 5_000,
+    max_context_length: int = 2_000,
 ) -> Tuple[pd.DataFrame, float, str]:
     os.environ["NIXTLA_ID_AS_COL"] = "true"
     models = [
@@ -82,14 +82,11 @@ def run_statistical_ensemble(
         DynamicOptimizedTheta(season_length=seasonality),
     ]
     init_time = time()
-    series_per_core = 15
-    n_series = train_df["unique_id"].nunique()
-    n_jobs = max(1, min(n_series // series_per_core, os.cpu_count()))
     sf = StatsForecast(
         models=models,
         fallback_model=SeasonalNaive(season_length=seasonality),
         freq=freq,
-        n_jobs=n_jobs,
+        n_jobs=-1,
     )
     # Shorten all time series to at most max_context_length to avoid extremely long runtime
     train_df = train_df.groupby("unique_id", sort=False, as_index=False).tail(
diff --git a/experiments/amazon-chronos/src/eval_utils/utils.py b/experiments/amazon-chronos/src/eval_utils/utils.py
index 8c9c4127..712d395a 100644
--- a/experiments/amazon-chronos/src/eval_utils/utils.py
+++ b/experiments/amazon-chronos/src/eval_utils/utils.py
@@ -195,8 +195,10 @@ def evaluate_models(self, models: List[str]) -> pd.DataFrame:
         fcsts_df = pd.concat(fcsts_df, axis=1).reset_index()
         fcsts_df["ds"] = pd.to_datetime(fcsts_df["ds"])
         times_df = pd.concat(times_df)
-        return evaluate_from_predictions(
-            models=model, fcsts_df=fcsts_df, times_df=times_df
+        return self.evaluate_from_predictions(
+            models=model,
+            fcsts_df=fcsts_df,
+            times_df=times_df,
         )
 
     def evaluate_from_predictions(