Solves 500 Errors For Some Users

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+scale-hf-logo.png filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1 +1,13 @@
-__pycache__
+auto_evals/
+venv/
+__pycache__/
+.env
+.ipynb_checkpoints
+*ipynb
+.vscode/
+
+eval-queue/
+eval-results/
+eval-queue-bk/
+eval-results-bk/
+logs/

.pre-commit-config.yaml

@@ -0,0 +1,53 @@
+# Copyright (c) 2022, NVIDIA CORPORATION.  All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+default_language_version:
+  python: python3
+
+ci:
+  autofix_prs: true
+  autoupdate_commit_msg: '[pre-commit.ci] pre-commit suggestions'
+  autoupdate_schedule: quarterly
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: check-yaml
+      - id: check-case-conflict
+      - id: detect-private-key
+      - id: check-added-large-files
+        args: ['--maxkb=1000']
+      - id: requirements-txt-fixer
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+        name: Format imports
+
+  - repo: https://github.com/psf/black
+    rev: 22.12.0
+    hooks:
+      - id: black
+        name: Format code
+        additional_dependencies: ['click==8.0.2']
+
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    # Ruff version.
+    rev: 'v0.0.267'
+    hooks:
+      - id: ruff

.streamlit/config.toml

@@ -1,2 +0,0 @@
-[theme]
-base = "light"

CLAUDE.md

@@ -1,82 +0,0 @@
-# CLAUDE.md
-
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
-## Project Overview
-
-fev-bench Leaderboard is a Streamlit web application displaying time series forecasting model evaluation results from the fev-bench benchmark. It evaluates 30+ forecasting models using multiple metrics (SQL, MASE, WQL, WAPE) across 100 benchmark tasks.
-
-## Common Commands
-
-```bash
-# Run the Streamlit app locally
-uv run streamlit run fev-leaderboard-app.py --server.port=8501 --server.address=0.0.0.0
-
-# Regenerate leaderboard tables from autogluon/fev repo (defaults to main branch)
-uv run python save_tables.py [commit]  # e.g., uv run python save_tables.py abc123
-
-# Docker build and run
-docker build -t fev-leaderboard .
-docker run -p 8501:8501 fev-leaderboard
-```
-
-Note: Use `uv run` prefix for all Python commands in this project.
-
-No test or lint frameworks are configured.
-
-## Architecture
-
-```
-fev-leaderboard-app.py     # Main entry point (Streamlit multi-page router)
-save_tables.py             # Generates pre-computed CSV tables from raw summaries
-pages/
-├── fev_bench.py           # Main leaderboard (100 tasks, loads from tables/)
-├── chronos_bench_ii.py    # Alternative leaderboard (27 tasks, fetches from GitHub)
-└── about.py               # Help page with links
-src/
-├── utils.py               # Visualization, formatting, MODEL_CONFIG, color palette
-├── strings.py             # UI text, metric descriptions, paper citations
-└── task_groups.py         # Task groupings by frequency and domain
-tables/                    # Pre-generated CSVs
-├── pivot_*.csv            # Full pivot tables (filtered in app by task group)
-├── summaries.csv          # Raw evaluation summaries
-└── {group}/               # Subdirectories for each task group (full, mini, frequency_*, domain_*)
-    ├── leaderboard_*.csv  # Leaderboard tables per metric
-    └── pairwise_*.csv     # Pairwise comparison tables per metric
-```
-
-**Data flow**: GitHub (autogluon/fev) → `save_tables.py` → pre-computed tables → `fev_bench.py` visualization
-
-## Key Modules
-
-**`src/utils.py`**: Core module containing:
-- `MODEL_CONFIG`: Dict mapping model names to (huggingface_url, organization, is_zero_shot, model_type)
-- `ALL_METRICS`: Dict with SQL, MASE, WQL, WAPE definitions
-- `format_leaderboard()`, `construct_bar_chart()`, `construct_pairwise_chart()`, `construct_pivot_table()`: Styling functions
-- `COLORS`: Custom palette (purple, gold, silver, bronze)
-
-**`src/strings.py`**: Documentation strings for metric formulas, win rate/skill score calculations, imputation strategies
-
-## Metrics
-
-| Metric | Type | Description |
-|--------|------|-------------|
-| SQL | Probabilistic | Scaled Quantile Loss (scale-invariant) |
-| MASE | Point | Mean Absolute Scaled Error (scale-invariant) |
-| WQL | Probabilistic | Weighted Quantile Loss (scale-dependent) |
-| WAPE | Point | Weighted Absolute Percentage Error (scale-dependent) |
-
-## Model Types
-
-Models are categorized as DL (deep learning) or ST (statistical) in `MODEL_CONFIG`. This affects color-coding in visualizations (blue vs. orange).
-
-## Imputation Strategy
-
-- **Failed tasks**: Replaced with Seasonal Naive scores
-- **Leaky tasks** (training corpus overlap for zero-shot models): Replaced with Chronos-Bolt scores
-
-## External References
-
-- fev-bench paper: https://arxiv.org/abs/2509.26468
-- fev library docs: https://autogluon.github.io/fev/latest/
-- GitHub: https://github.com/autogluon/fev

Dockerfile

@@ -1,21 +0,0 @@
-FROM python:3.13.5-slim
-
-RUN useradd -m -u 1000 user
-WORKDIR /app
-
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
-
-COPY --chown=user ./requirements.txt requirements.txt
-COPY --chown=user . /app
-
-RUN pip3 install -r requirements.txt
-
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "fev-leaderboard-app.py", "--server.port=8501", "--server.address=0.0.0.0"]

Makefile

@@ -0,0 +1,13 @@
+.PHONY: style format
+
+
+style:
+	python -m black --line-length 119 .
+	python -m isort .
+	ruff check --fix .
+
+
+quality:
+	python -m black --check --line-length 119 .
+	python -m isort --check-only .
+	ruff check .

README.md

@@ -1,20 +1,44 @@
 ---
-title: fev-bench
-emoji: 🏆
+title: Fev Leaderboard
+emoji: 🥇
 colorFrom: green
 colorTo: indigo
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
-pinned: false
-short_description: Forecast evaluation benchmark
+sdk: gradio
+app_file: app.py
+pinned: true
 license: apache-2.0
 ---
 
-# Welcome to Streamlit!
+# Start the configuration
 
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+Most of the variables to change for a default leaderboard are in `src/env.py` (replace the path for your leaderboard) and `src/about.py` (for tasks).
 
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+Results files should have the following format and be stored as json files:
+```json
+{
+    "config": {
+        "model_dtype": "torch.float16", # or torch.bfloat16 or 8bit or 4bit
+        "model_name": "path of the model on the hub: org/model",
+        "model_sha": "revision on the hub",
+    },
+    "results": {
+        "task_name": {
+            "metric_name": score,
+        },
+        "task_name2": {
+            "metric_name": score,
+        }
+    }
+}
+```
+
+Request files are created automatically by this tool.
+
+If you encounter problem on the space, don't hesitate to restart it to remove the create eval-queue, eval-queue-bk, eval-results and eval-results-bk created folder.
+
+# Code logic for more complex edits
+
+You'll find 
+- the main table' columns names and properties in `src/display/utils.py`
+- the logic to read all results and request files, then convert them in dataframe lines, in `src/leaderboard/read_evals.py`, and `src/populate.py`
+- the logic to allow or filter submissions in `src/submission/submit.py` and `src/submission/check_validity.py`

app.py

@@ -0,0 +1,97 @@
+import fev
+import gradio as gr
+import pandas as pd
+
+from src import about
+from src.custom_html_js import custom_css
+from src.formatting import make_clickable_model
+
+# Load the CSV data into a pandas DataFrame
+df = pd.read_csv(
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/seasonal_naive.csv"
+)
+
+
+summary_urls = [
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/auto_arima.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/auto_ets.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/auto_theta.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/chronos_base.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/chronos_large.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/chronos_mini.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/chronos_small.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/chronos_tiny.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/chronos_bolt_base.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/chronos_bolt_mini.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/chronos_bolt_small.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/chronos_bolt_tiny.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/moirai_base.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/moirai_large.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/moirai_small.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/seasonal_naive.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/timesfm.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/timesfm-2.0.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/ttm-r2.csv",
+    "https://raw.githubusercontent.com/autogluon/fev/refs/heads/main/benchmarks/chronos_zeroshot/results/tirex.csv",
+]
+
+rename_cols = {
+    "gmean_relative_error": "Average relative error",
+    "avg_rank": "Average rank",
+    "median_inference_time_s": "Median inference time (s)",
+    "training_corpus_overlap": "Training corpus overlap (%)",
+}
+selected_cols = list(rename_cols.keys())
+
+
+def highlight_zeroshot(styler):
+    """Highlight training overlap for zero-shot models with bold green."""
+
+    def style_func(val):
+        if val == 0:
+            return "color: green; font-weight: bold"
+        else:
+            return "color: black"
+
+    return styler.map(style_func, subset=["Training corpus overlap (%)"])
+
+
+leaderboards = {}
+for metric in ["WQL", "MASE"]:
+    lb = fev.leaderboard(summary_urls, metric_column=metric)[selected_cols].rename(columns=rename_cols)
+    lb = lb.astype("float64").round(3).reset_index()
+    lb["Training corpus overlap (%)"] = (lb["Training corpus overlap (%)"] * 100).round(1)
+    lb["model_name"] = lb["model_name"].apply(make_clickable_model)
+    leaderboards[metric] = highlight_zeroshot(lb.style).format(precision=3)
+
+
+with gr.Blocks(css=custom_css) as demo:
+    gr.HTML(about.TITLE)
+    gr.Markdown(about.INTRODUCTION_TEXT, elem_classes="markdown-text")
+
+    with gr.Tabs(elem_classes="tab-buttons"):
+        with gr.Tab("🏅 Chronos Benchmark II", id=0):
+            with gr.Column():
+                gr.Markdown(about.CHRONOS_BENCHMARK, elem_classes="markdown-text")
+            with gr.Tabs():
+                with gr.Tab("📊 Probabilistic forecast (WQL)"):
+                    gr.Markdown("""Forecast accuracy measured by Weighted Quantile Loss.""")
+                    gr.Dataframe(
+                        value=leaderboards["WQL"],
+                        datatype=["markdown", "number", "number", "number"],
+                        interactive=False,
+                    )
+
+                with gr.Tab("📈 Point forecast (MASE)"):
+                    gr.Markdown("""Forecast accuracy measured by Mean Absolute Scaled Error.""")
+                    gr.Dataframe(
+                        value=leaderboards["MASE"],
+                        datatype=["markdown", "number", "number", "number"],
+                        interactive=False,
+                    )
+
+        with gr.Tab("📝 About", id=1):
+            gr.Markdown(about.ABOUT_LEADERBOARD)
+
+if __name__ == "__main__":
+    demo.launch(ssr_mode=False)

fev-leaderboard-app.py

@@ -1,9 +0,0 @@
-import streamlit as st
-
-pages = [
-    st.Page("pages/fev_bench.py", title="fev-bench", icon=":material/trophy:"),
-    st.Page("pages/about.py", title="About", icon=":material/info:"),
-]
-
-page = st.navigation(pages)
-page.run()

pages/about.py

@@ -1,19 +0,0 @@
-import streamlit as st
-
-ABOUT_LEADERBOARD = """
-## About
-
-[**fev**](https://github.com/autogluon/fev) is a lightweight wrapper around the 🤗 [datasets](https://huggingface.co/docs/datasets/en/index) library designed to streamline
- benchmarking of time series forecasting models.
-
-### 📚 Resources
-- **Documentation**: [Official docs](https://autogluon.github.io/fev/latest/)
-- **Publication**: ["fev-bench: A Realistic Benchmark for Time Series Forecasting"](https://arxiv.org/abs/2509.26468)
-- **Source Code**: [GitHub repository](https://github.com/autogluon/fev)
-- **Issues & Questions**: [GitHub Issues](https://github.com/autogluon/fev/issues)
-
-### 🚀 Submit Your Model
-Ready to add your model to the leaderboard? Follow this [tutorial](https://autogluon.github.io/fev/latest/tutorials/05-add-your-model/) to evaluate your model with fev and contribute your results.
-"""
-st.set_page_config(layout="wide", page_title="About FEV", page_icon=":material/info:")
-st.markdown(ABOUT_LEADERBOARD)

pages/fev_bench.py

@@ -1,284 +0,0 @@
-import sys
-from pathlib import Path
-
-sys.path.append(str(Path(__file__).parent))
-
-import pandas as pd
-import streamlit as st
-from src.strings import (
-    CITATION_FEV,
-    CITATION_HEADER,
-    FEV_BENCHMARK_DETAILS,
-    PAIRWISE_BENCHMARK_DETAILS,
-    get_pivot_legend,
-)
-from src.task_groups import (
-    ALL_TASKS,
-    DOMAIN_GROUPS,
-    FREQUENCY_GROUPS,
-    MINI_TASKS,
-    TASK_TYPE_GROUPS,
-)
-from src.utils import (
-    COLORS,
-    HIDDEN_MODELS,
-    construct_pairwise_chart,
-    filter_hidden_models,
-    format_leaderboard,
-    format_metric_name,
-    get_metric_description,
-    validate_model_metadata,
-)
-from streamlit.elements.lib.column_types import ColumnConfig
-
-st.set_page_config(
-    layout="wide", page_title="fev leaderboard", page_icon=":material/trophy:"
-)
-
-TITLE = "<h1 style='text-align: center; font-size: 350%;'>fev-bench</h1>"
-SORT_COL = "win_rate"
-AVAILABLE_METRICS = ["SQL", "MASE", "WQL", "WAPE"]
-
-# Group type options
-GROUP_TYPES = [
-    "Full (100 tasks)",
-    "Mini (20 tasks)",
-    "By frequency",
-    "By domain",
-    "By task type",
-]
-FREQUENCY_OPTIONS = list(FREQUENCY_GROUPS.keys())
-DOMAIN_OPTIONS = list(DOMAIN_GROUPS.keys())
-TASK_TYPE_OPTIONS = list(TASK_TYPE_GROUPS.keys())
-
-
-def get_subset_description(
-    group_type: str, subgroup: str | None, num_tasks: int, metric_name: str
-) -> str:
-    """Generate a description of the current subset."""
-    base = f"Results for various forecasting models, measured using the **{metric_name}** metric, on **{num_tasks} tasks**"
-    if group_type == "Full (100 tasks)":
-        subset_desc = "from the full **fev-bench** benchmark"
-    elif group_type == "Mini (20 tasks)":
-        subset_desc = "from the **fev-bench-mini** subset"
-    elif group_type == "By frequency":
-        subset_desc = f"with **{subgroup.lower()}** frequency"
-    elif group_type == "By task type":
-        subset_desc = f"of type **{subgroup.lower()}**"
-    else:  # By domain
-        subset_desc = f"from the **{subgroup}** domain"
-    paper_link = "[fev-bench: A Realistic Benchmark for Time Series Forecasting](https://arxiv.org/abs/2509.26468)"
-    return f"{base} {subset_desc}, as described in {paper_link}."
-
-
-# Mapping from UI selections to table directory names
-GROUP_DIR_MAPPING = {
-    "Full (100 tasks)": "full",
-    "Mini (20 tasks)": "mini",
-    "Sub-hourly": "frequency_sub_hourly",
-    "Hourly": "frequency_hourly",
-    "Daily": "frequency_daily",
-    "Weekly": "frequency_weekly",
-    "Monthly+": "frequency_monthly_plus",
-    "Energy": "domain_energy",
-    "Nature": "domain_nature",
-    "Cloud": "domain_cloud",
-    "Mobility": "domain_mobility",
-    "Econ": "domain_econ",
-    "Health": "domain_health",
-    "Retail": "domain_retail",
-    "Univariate": "task_type_univariate",
-    "Covariate-informed": "task_type_covariate_informed",
-    "Multivariate": "task_type_multivariate",
-}
-
-
-@st.cache_data()
-def get_leaderboard(metric_name: str, group_dir: str) -> pd.DataFrame:
-    return pd.read_csv(f"tables/{group_dir}/leaderboard_{metric_name}.csv")
-
-
-@st.cache_data()
-def get_pairwise(metric_name: str, group_dir: str) -> pd.DataFrame:
-    return pd.read_csv(f"tables/{group_dir}/pairwise_{metric_name}.csv")
-
-
-@st.cache_data()
-def get_pivot_table(
-    metric_name: str,
-) -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
-    pivot_df = pd.read_csv(f"tables/pivot_{metric_name}.csv")
-    baseline_imputed = pd.read_csv(f"tables/pivot_{metric_name}_baseline_imputed.csv")
-    leakage_imputed = pd.read_csv(f"tables/pivot_{metric_name}_leakage_imputed.csv")
-    return pivot_df, baseline_imputed, leakage_imputed
-
-
-with st.sidebar:
-    # Task group selection
-    selected_group_type = st.selectbox("Subset", options=GROUP_TYPES)
-
-    # Conditional sub-selection for frequency/domain
-    selected_subgroup = None
-    if selected_group_type == "By frequency":
-        selected_subgroup = st.selectbox("Frequency", options=FREQUENCY_OPTIONS)
-    elif selected_group_type == "By domain":
-        selected_subgroup = st.selectbox("Domain", options=DOMAIN_OPTIONS)
-    elif selected_group_type == "By task type":
-        selected_subgroup = st.selectbox("Task type", options=TASK_TYPE_OPTIONS)
-
-    # Determine the directory to load tables from
-    if selected_group_type in ["Full (100 tasks)", "Mini (20 tasks)"]:
-        group_dir = GROUP_DIR_MAPPING[selected_group_type]
-        task_list = (
-            ALL_TASKS if selected_group_type == "Full (100 tasks)" else MINI_TASKS
-        )
-    else:
-        group_dir = GROUP_DIR_MAPPING[selected_subgroup]
-        if selected_group_type == "By frequency":
-            task_list = FREQUENCY_GROUPS[selected_subgroup]
-        elif selected_group_type == "By task type":
-            task_list = TASK_TYPE_GROUPS[selected_subgroup]
-        else:
-            task_list = DOMAIN_GROUPS[selected_subgroup]
-
-    st.caption(f"{len(task_list)} tasks")
-
-    st.divider()
-
-    selected_metric = st.selectbox(
-        "Evaluation Metric", options=AVAILABLE_METRICS, format_func=format_metric_name
-    )
-    st.caption(get_metric_description(selected_metric))
-
-cols = st.columns(spec=[0.025, 0.95, 0.025])
-
-with cols[1] as main_container:
-    st.markdown(TITLE, unsafe_allow_html=True)
-
-    metric_df = get_leaderboard(selected_metric, group_dir).sort_values(
-        by=SORT_COL, ascending=False
-    )
-    metric_df = filter_hidden_models(metric_df, "model_name")
-    validate_model_metadata(metric_df["model_name"])
-
-    pairwise_df = get_pairwise(selected_metric, group_dir)
-    pairwise_df = filter_hidden_models(
-        filter_hidden_models(pairwise_df, "model_1"), "model_2"
-    )
-
-    st.markdown("## :material/trophy: Leaderboard", unsafe_allow_html=True)
-    st.markdown(
-        get_subset_description(
-            selected_group_type, selected_subgroup, len(task_list), selected_metric
-        ),
-        unsafe_allow_html=True,
-    )
-    df_styled = format_leaderboard(metric_df)
-    st.dataframe(
-        df_styled,
-        width="stretch",
-        hide_index=True,
-        column_config={
-            "model_name": ColumnConfig(label="Model Name", alignment="left"),
-            "win_rate": st.column_config.NumberColumn(
-                label="Avg. win rate (%)", format="%.1f"
-            ),
-            "skill_score": st.column_config.NumberColumn(
-                label="Skill score (%)", format="%.1f"
-            ),
-            "median_inference_time_s_per100": st.column_config.NumberColumn(
-                label="Median runtime (s / 100 series)", format="%.1f"
-            ),
-            "training_corpus_overlap": st.column_config.NumberColumn(
-                label="Leakage (%)", format="%d"
-            ),
-            "num_failures": st.column_config.NumberColumn(
-                label="Failed tasks (%)", format="%.0f"
-            ),
-            "zero_shot": ColumnConfig(label="Zero-shot", alignment="center"),
-            "org": ColumnConfig(label="Organization", alignment="left"),
-            "link": st.column_config.LinkColumn(label="Link", display_text="🔗"),
-        },
-    )
-
-    with st.expander("See details"):
-        st.markdown(FEV_BENCHMARK_DETAILS, unsafe_allow_html=True)
-
-    st.markdown("## :material/bar_chart: Pairwise comparison", unsafe_allow_html=True)
-    chart_col_1, _, chart_col_2 = st.columns(spec=[0.45, 0.1, 0.45])
-
-    with chart_col_1:
-        st.altair_chart(
-            construct_pairwise_chart(
-                pairwise_df, col="win_rate", metric_name=selected_metric
-            ),
-            use_container_width=True,
-        )
-
-    with chart_col_2:
-        st.altair_chart(
-            construct_pairwise_chart(
-                pairwise_df, col="skill_score", metric_name=selected_metric
-            ),
-            use_container_width=True,
-        )
-
-    with st.expander("See details"):
-        st.markdown(PAIRWISE_BENCHMARK_DETAILS, unsafe_allow_html=True)
-
-    st.markdown(
-        "## :material/table_chart: Results for individual tasks", unsafe_allow_html=True
-    )
-    with st.expander("Show detailed results"):
-        st.markdown(
-            get_pivot_legend("Seasonal Naive", "Chronos-Bolt"), unsafe_allow_html=True
-        )
-        pivot_df, baseline_imputed, leakage_imputed = get_pivot_table(selected_metric)
-        pivot_df = pivot_df.set_index("Task name")
-        baseline_imputed = baseline_imputed.set_index("Task name")
-        leakage_imputed = leakage_imputed.set_index("Task name")
-
-        # Drop columns for models hidden from the leaderboard
-        hidden_cols = [c for c in pivot_df.columns if c in HIDDEN_MODELS]
-        pivot_df = pivot_df.drop(columns=hidden_cols)
-        baseline_imputed = baseline_imputed.drop(columns=hidden_cols)
-        leakage_imputed = leakage_imputed.drop(columns=hidden_cols)
-
-        # Filter pivot table to only show tasks in the selected group
-        available_tasks = [t for t in task_list if t in pivot_df.index]
-        pivot_df = pivot_df.loc[available_tasks]
-        baseline_imputed = baseline_imputed.loc[available_tasks]
-        leakage_imputed = leakage_imputed.loc[available_tasks]
-
-        def style_pivot_table(errors, is_baseline_imputed, is_leakage_imputed):
-            rank_colors = {1: COLORS["gold"], 2: COLORS["silver"], 3: COLORS["bronze"]}
-
-            def highlight_by_position(styler):
-                for row_idx in errors.index:
-                    row_ranks = errors.loc[row_idx].rank(method="min")
-                    for col_idx in errors.columns:
-                        rank = row_ranks[col_idx]
-                        style_parts = []
-                        if rank <= 3:
-                            style_parts.append(f"background-color: {rank_colors[rank]}")
-                        if is_leakage_imputed.loc[row_idx, col_idx]:
-                            style_parts.append(f"color: {COLORS['leakage_impute']}")
-                        elif is_baseline_imputed.loc[row_idx, col_idx]:
-                            style_parts.append(f"color: {COLORS['failure_impute']}")
-                        elif not style_parts:
-                            style_parts.append(f"color: {COLORS['text_default']}")
-                        if style_parts:
-                            styler = styler.map(
-                                lambda x, s="; ".join(style_parts): s,
-                                subset=pd.IndexSlice[row_idx:row_idx, col_idx:col_idx],
-                            )
-                return styler
-
-            return highlight_by_position(errors.style).format(precision=3)
-
-        st.dataframe(style_pivot_table(pivot_df, baseline_imputed, leakage_imputed))
-
-    st.divider()
-    st.markdown("### :material/format_quote: Citation", unsafe_allow_html=True)
-    st.markdown(CITATION_HEADER)
-    st.markdown(CITATION_FEV)

pyproject.toml

@@ -1,12 +1,13 @@
-[project]
-name = "hf-leaderboard"
-version = "0.1.0"
-requires-python = ">=3.11"
-dependencies = [
-    "altair>=6.0.0",
-    "fev>=0.7.0",
-    "numpy<2.2",
-    "pyarrow<21",
-    "scipy<1.15",
-    "streamlit>=1.53.1",
-]
+[tool.ruff]
+# Enable pycodestyle (`E`) and Pyflakes (`F`) codes by default.
+select = ["E", "F"]
+ignore = ["E501"] # line too long (black is taking care of this)
+line-length = 119
+fixable = ["A", "B", "C", "D", "E", "F", "G", "I", "N", "Q", "S", "T", "W", "ANN", "ARG", "BLE", "COM", "DJ", "DTZ", "EM", "ERA", "EXE", "FBT", "ICN", "INP", "ISC", "NPY", "PD", "PGH", "PIE", "PL", "PT", "PTH", "PYI", "RET", "RSE", "RUF", "SIM", "SLF", "TCH", "TID", "TRY", "UP", "YTT"]
+
+[tool.isort]
+profile = "black"
+line_length = 119
+
+[tool.black]
+line-length = 119

requirements.txt

@@ -1,7 +1,11 @@
+APScheduler
+black
+datasets
+gradio
+gradio[oauth]
+gradio_client
+huggingface-hub>=0.18.0
 matplotlib
 numpy
 pandas
-requests
-streamlit==1.49.1
-fev>=0.6.0
-altair>=5.5.0
+fev==0.4.0

save_tables.py

@@ -1,241 +0,0 @@
-#!/usr/bin/env python3
-
-import argparse
-import importlib.util
-import io
-import sys
-from pathlib import Path
-
-import requests
-
-sys.path.append(str(Path(__file__).parent))
-
-import fev
-import pandas as pd
-
-from src.task_groups import ALL_TASKS, DOMAIN_GROUPS, FREQUENCY_GROUPS, MINI_TASKS, TASK_TYPE_GROUPS
-
-GITHUB_REPO = "autogluon/fev"
-RESULTS_PATH = "benchmarks/fev_bench/results"
-
-# Default location of the local fev clone (sibling of this repo); override with --fev-repo
-DEFAULT_FEV_REPO = Path(__file__).resolve().parent.parent / "core"
-
-
-def load_fev_bench_module(fev_repo: Path):
-    """Load shared compute logic from the fev repo's figure-generation script.
-
-    This keeps the leaderboard and the fev paper-figure script using a single source of truth for
-    the benchmark config (baseline/leakage models, metrics) and the leaderboard/pairwise compute.
-    """
-    script_path = fev_repo / "scripts" / "generate_fev_bench_figures.py"
-    if not script_path.exists():
-        raise FileNotFoundError(
-            f"Could not find the fev figure script at {script_path}. "
-            "Clone autogluon/fev next to this repo, or pass --fev-repo with your local fev checkout."
-        )
-    spec = importlib.util.spec_from_file_location("fev_bench_figures", script_path)
-    module = importlib.util.module_from_spec(spec)
-    spec.loader.exec_module(module)
-    return module
-
-
-# All task groups to generate tables for
-TASK_GROUPS = {
-    "full": ALL_TASKS,
-    "mini": MINI_TASKS,
-    "frequency_sub_hourly": FREQUENCY_GROUPS["Sub-hourly"],
-    "frequency_hourly": FREQUENCY_GROUPS["Hourly"],
-    "frequency_daily": FREQUENCY_GROUPS["Daily"],
-    "frequency_weekly": FREQUENCY_GROUPS["Weekly"],
-    "frequency_monthly_plus": FREQUENCY_GROUPS["Monthly+"],
-    "domain_energy": DOMAIN_GROUPS["Energy"],
-    "domain_nature": DOMAIN_GROUPS["Nature"],
-    "domain_cloud": DOMAIN_GROUPS["Cloud"],
-    "domain_mobility": DOMAIN_GROUPS["Mobility"],
-    "domain_econ": DOMAIN_GROUPS["Econ"],
-    "domain_health": DOMAIN_GROUPS["Health"],
-    "domain_retail": DOMAIN_GROUPS["Retail"],
-    "task_type_univariate": TASK_TYPE_GROUPS["Univariate"],
-    "task_type_covariate_informed": TASK_TYPE_GROUPS["Covariate-informed"],
-    "task_type_multivariate": TASK_TYPE_GROUPS["Multivariate"],
-}
-
-
-def get_csv_files_from_github(commit: str) -> list[str]:
-    """Get list of CSV file paths from the GitHub repo at a specific commit."""
-    api_url = f"https://api.github.com/repos/{GITHUB_REPO}/contents/{RESULTS_PATH}?ref={commit}"
-    response = requests.get(api_url)
-    response.raise_for_status()
-
-    files = response.json()
-    csv_files = [f["path"] for f in files if f["name"].endswith(".csv")]
-
-    if not csv_files:
-        raise FileNotFoundError(f"No CSV files found in {RESULTS_PATH} at commit {commit}")
-
-    return csv_files
-
-
-def load_summaries_from_github(commit: str) -> pd.DataFrame:
-    """Load and concatenate all CSV summaries from the GitHub repo at a specific commit."""
-    csv_files = get_csv_files_from_github(commit)
-    print(f"Found {len(csv_files)} CSV files")
-
-    dfs = []
-    for file_path in csv_files:
-        raw_url = f"https://raw.githubusercontent.com/{GITHUB_REPO}/{commit}/{file_path}"
-        response = requests.get(raw_url)
-        response.raise_for_status()
-        df = pd.read_csv(io.StringIO(response.text))
-        dfs.append(df)
-        print(f"  Loaded: {Path(file_path).name}")
-
-    return pd.concat(dfs, ignore_index=True)
-
-
-def compute_pivot_table(
-    summaries: pd.DataFrame,
-    metric_name: str,
-    baseline_model: str,
-    leakage_imputation_model: str,
-) -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
-    errors = fev.pivot_table(summaries=summaries, metric_column=metric_name, task_columns=["task_name"])
-    train_overlap = (
-        fev.pivot_table(summaries=summaries, metric_column="trained_on_this_dataset", task_columns=["task_name"])
-        .fillna(False)
-        .astype(bool)
-    )
-
-    is_imputed_baseline = errors.isna()
-    is_leakage_imputed = train_overlap
-
-    # Handle imputations
-    errors = errors.mask(train_overlap, errors[leakage_imputation_model], axis=0)
-    for col in errors.columns:
-        if col != baseline_model:
-            errors[col] = errors[col].fillna(errors[baseline_model])
-
-    errors = errors[errors.rank(axis=1).mean().sort_values().index]
-    is_imputed_baseline = is_imputed_baseline[errors.columns]
-    is_leakage_imputed = is_leakage_imputed[errors.columns]
-
-    errors.index.rename("Task name", inplace=True)
-    is_imputed_baseline.index.rename("Task name", inplace=True)
-    is_leakage_imputed.index.rename("Task name", inplace=True)
-
-    return errors.reset_index(), is_imputed_baseline.reset_index(), is_leakage_imputed.reset_index()
-
-
-def load_summaries_from_local(path: Path) -> pd.DataFrame:
-    """Load and concatenate all CSV summaries from a local directory."""
-    csv_files = sorted(path.glob("*.csv"))
-    if not csv_files:
-        raise FileNotFoundError(f"No CSV files found in {path}")
-
-    print(f"Found {len(csv_files)} CSV files")
-    dfs = []
-    for f in csv_files:
-        df = pd.read_csv(f)
-        dfs.append(df)
-        print(f"  Loaded: {f.name}")
-
-    return pd.concat(dfs, ignore_index=True)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Generate leaderboard tables from CSV summaries in the fev repo")
-    parser.add_argument(
-        "commit",
-        nargs="?",
-        default="main",
-        help=f"Git commit SHA or branch name in the {GITHUB_REPO} repository (default: main)",
-    )
-    parser.add_argument(
-        "--local",
-        type=Path,
-        help="Path to a local directory containing result CSV files (skips GitHub fetching)",
-    )
-    parser.add_argument(
-        "--fev-repo",
-        type=Path,
-        default=DEFAULT_FEV_REPO,
-        help=f"Path to a local clone of the fev repo, used for shared compute logic (default: {DEFAULT_FEV_REPO})",
-    )
-    args = parser.parse_args()
-
-    # Load shared benchmark config + compute layer from the fev repo (single source of truth)
-    fev_bench = load_fev_bench_module(args.fev_repo)
-    baseline_model = fev_bench.BASELINE_MODEL
-    leakage_imputation_model = fev_bench.LEAKAGE_IMPUTATION_MODEL
-    sort_col = fev_bench.SORT_COL
-    top_k_models_to_plot = fev_bench.TOP_K_MODELS_TO_PLOT
-    available_metrics = fev_bench.AVAILABLE_METRICS
-    compute_leaderboard = fev_bench.compute_leaderboard
-    compute_pairwise = fev_bench.compute_pairwise
-
-    # Create tables directory
-    tables_dir = Path("tables")
-    tables_dir.mkdir(exist_ok=True)
-
-    if args.local:
-        print(f"Loading summaries from local path: {args.local}")
-        summaries = load_summaries_from_local(args.local)
-    else:
-        print(f"Loading summaries from {GITHUB_REPO} at commit {args.commit}...")
-        summaries = load_summaries_from_github(args.commit)
-
-    # Save raw summaries for on-the-fly subset computation
-    summaries.to_csv(tables_dir / "summaries.csv", index=False)
-    print("Saved: summaries.csv")
-
-    # Generate pivot tables (full version only, at root level)
-    for metric in available_metrics:
-        print(f"Processing pivot table for {metric}...")
-        pivot_df, baseline_imputed, leakage_imputed = compute_pivot_table(
-            summaries, metric, baseline_model, leakage_imputation_model
-        )
-        pivot_df.to_csv(tables_dir / f"pivot_{metric}.csv", index=False)
-        baseline_imputed.to_csv(tables_dir / f"pivot_{metric}_baseline_imputed.csv", index=False)
-        leakage_imputed.to_csv(tables_dir / f"pivot_{metric}_leakage_imputed.csv", index=False)
-        print(f"  Saved: pivot_{metric}.csv")
-
-    # Generate leaderboard and pairwise tables for each task group
-    for group_name, task_list in TASK_GROUPS.items():
-        print(f"\nProcessing group: {group_name} ({len(task_list)} tasks)...")
-
-        # Create subdirectory for this group
-        group_dir = tables_dir / group_name
-        group_dir.mkdir(exist_ok=True)
-
-        # Filter summaries to only include tasks in this group
-        group_summaries = summaries[summaries["task_name"].isin(task_list)]
-
-        if group_summaries.empty:
-            print(f"  WARNING: No matching tasks found for group {group_name}")
-            continue
-
-        actual_tasks = group_summaries["task_name"].nunique()
-        print(f"  Found {actual_tasks} tasks in summaries")
-
-        for metric in available_metrics:
-            # Compute leaderboard for this group
-            leaderboard_df = compute_leaderboard(group_summaries, metric)
-            leaderboard_df.to_csv(group_dir / f"leaderboard_{metric}.csv", index=False)
-
-            # Get top models for pairwise comparison
-            top_k_models = (
-                leaderboard_df.sort_values(by=sort_col, ascending=False).head(top_k_models_to_plot)["model_name"].tolist()
-            )
-
-            # Compute pairwise comparison
-            pairwise_df = compute_pairwise(group_summaries, metric, top_k_models)
-            pairwise_df.to_csv(group_dir / f"pairwise_{metric}.csv", index=False)
-
-            print(f"  Saved: {group_name}/leaderboard_{metric}.csv, {group_name}/pairwise_{metric}.csv")
-
-    print(f"\nAll tables saved to {tables_dir}/")
-
-
-if __name__ == "__main__":
-    main()

src/about.py

@@ -0,0 +1,50 @@
+TITLE = """<h1 align="center" id="space-title">Forecast evaluation leaderboard</h1>"""
+
+# What does your leaderboard evaluate?
+INTRODUCTION_TEXT = """
+This space hosts evaluation results for time series forecasting models.
+
+The results are obtained using [fev](https://github.com/autogluon/fev) - a lightweight library for evaluating time series forecasting models.
+"""
+
+ABOUT_LEADERBOARD = """
+## What is `fev`?
+
+[`fev`](https://github.com/autogluon/fev) is a lightweight wrapper around the 🤗 [`datasets`](https://huggingface.co/docs/datasets/en/index) library that makes it easy to benchmark time series forecasting models.
+
+For more information about `fev`, please check out [github.com/autogluon/fev](https://github.com/autogluon/fev).
+
+Currently, the results in this space are a minimal proof of concept. We plan to add new benchmark datasets and tasks in the future.
+
+## How is `fev` different from other benchmarking tools?
+Existing forecasting benchmarks usually fall into one of two categories:
+
+- Standalone datasets without any supporting infrastructure. These provide no guarantees that the results obtained by different users are comparable. For example, changing the start date or duration of the forecast horizon totally changes the meaning of the scores.
+- Bespoke end-to-end systems that combine models, datasets and forecasting tasks. Such packages usually come with lots of dependencies and assumptions, which makes extending or integrating these libraries into existing systems difficult.
+
+`fev` aims for the middle ground - it provides the core benchmarking functionality without introducing unnecessary constraints or bloated dependencies. The library supports point & probabilistic forecasting, different types of covariates, as well as all popular forecasting metrics.
+
+
+## Submitting your model
+For instructions on how to evaluate your model using `fev` and contribute your results to the leaderboard, please follow the [instructions in the GitHub repo](https://github.com/autogluon/fev/blob/main/docs/04-models.ipynb).
+"""
+
+CHRONOS_BENCHMARK = """
+## Chronos Benchmark II results
+
+This tab contains results for various forecasting models on the 27 datasets used in Benchmark II in the publication [Chronos: Learning the Language of Time Series](https://arxiv.org/abs/2403.07815).
+
+These datasets were used for zero-shot evaluation of Chronos models (i.e., Chronos models were not trained on these datasets), but some other models did include certain datasets in their training corpus.
+
+Each table contains the following information:
+
+* **Average relative error**: Geometric mean of the relative errors for each task. The relative error for each task is computed as `model_error / baseline_error`.
+* **Average rank**: Arithmetic mean of the ranks achieved by each model on each task.
+* **Median inference time (s)**: Median of the times required to make predictions for the entire dataset (in seconds).
+* **Training corpus overlap (%)**: Percentage of the datasets used in the benchmark that were included in the model's training corpus. Zero-shot models are highlighted in <span style="color:green; font-weight:bold;">green</span>.
+
+Lower values are better for all of the above metrics.
+
+Task definitions and the detailed results are available on [GitHub](https://github.com/autogluon/fev/tree/main/benchmarks/chronos_zeroshot). More information for the datasets is available in [Table 3 of the paper](https://arxiv.org/abs/2403.07815).
+
+"""

src/colors.py

@@ -1,6 +0,0 @@
-# Legacy colors - kept for backward compatibility if needed elsewhere
-VERY_PALE_PURPLE = "#e8d9f3"
-VERY_PALE_GREEN = "#cffdbc"
-VERY_PALE_BLUE = "#d6fffe"
-DEEP_LAVENDER = "#8d5eb7"
-GRASS_GREEN = "#3f9b0b"

src/custom_html_js.py

@@ -0,0 +1,99 @@
+custom_css = """
+
+.markdown-text {
+    font-size: 20px !important;
+}
+
+"""
+
+
+# .tab-buttons button {
+#     font-size: 20px;
+# }
+
+# #citation-button span {
+#     font-size: 16px !important;
+# }
+
+# #citation-button textarea {
+#     font-size: 16px !important;
+# }
+
+# #citation-button > label > button {
+#     margin: 6px;
+#     transform: scale(1.3);
+# }
+
+
+# #leaderboard-table-lite {
+#     margin-top: 15px
+# }
+
+# #search-bar-table-box > div:first-child {
+#     background: none;
+#     border: none;
+# }
+
+# #search-bar {
+#     padding: 0px;
+# }
+
+# /* Hides the final AutoEvalColumn */
+# #llm-benchmark-tab-table table td:last-child,
+# #llm-benchmark-tab-table table th:last-child {
+#     display: none;
+# }
+
+# /* Limit the width of the first AutoEvalColumn so that names don't expand too much */
+# table td:first-child,
+# table th:first-child {
+#     max-width: 400px;
+#     overflow: auto;
+#     white-space: nowrap;
+# }
+
+
+# #scale-logo {
+#     border-style: none !important;
+#     box-shadow: none;
+#     display: block;
+#     margin-left: auto;
+#     margin-right: auto;
+#     max-width: 600px;
+# }
+
+# #scale-logo .download {
+#     display: none;
+# }
+# #filter_type{
+#     border: 0;
+#     padding-left: 0;
+#     padding-top: 0;
+# }
+# #filter_type label {
+#     display: flex;
+# }
+# #filter_type label > span{
+#     margin-top: var(--spacing-lg);
+#     margin-right: 0.5em;
+# }
+# #filter_type label > .wrap{
+#     width: 103px;
+# }
+# #filter_type label > .wrap .wrap-inner{
+#     padding: 2px;
+# }
+# #filter_type label > .wrap .wrap-inner input{
+#     width: 1px
+# }
+# #filter-columns-type{
+#     border:0;
+#     padding:0.5;
+# }
+# #filter-columns-size{
+#     border:0;
+#     padding:0.5;
+# }
+# #box-filter > .form{
+#     border: 0
+# }

src/formatting.py

@@ -0,0 +1,31 @@
+def model_hyperlink(link, model_name):
+    return f'<a target="_blank" href="{link}" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">{model_name}</a>'
+
+
+MODEL_URLS = {
+    "chronos_tiny": "amazon/chronos-t5-tiny",
+    "chronos_mini": "amazon/chronos-t5-mini",
+    "chronos_small": "amazon/chronos-t5-small",
+    "chronos_base": "amazon/chronos-t5-base",
+    "chronos_large": "amazon/chronos-t5-large",
+    "chronos_bolt_tiny": "amazon/chronos-bolt-tiny",
+    "chronos_bolt_mini": "amazon/chronos-bolt-mini",
+    "chronos_bolt_small": "amazon/chronos-bolt-small",
+    "chronos_bolt_base": "amazon/chronos-bolt-base",
+    "moirai_large": "Salesforce/moirai-1.1-R-large",
+    "moirai_base": "Salesforce/moirai-1.1-R-base",
+    "moirai_small": "Salesforce/moirai-1.1-R-small",
+    "timesfm": "google/timesfm-1.0-200m-pytorch",
+    "timesfm-2.0": "google/timesfm-2.0-500m-pytorch",
+    "ttm-r2": "ibm-granite/granite-timeseries-ttm-r2",
+    "tirex": "NX-AI/TiRex",
+}
+
+
+def make_clickable_model(model_name):
+    if model_name in MODEL_URLS:
+        model_path = MODEL_URLS.get(model_name)
+        link = f"https://huggingface.co/{model_path}"
+        return model_hyperlink(link, model_name)
+    else:
+        return model_name

src/streamlit_app.py

@@ -1,9 +0,0 @@
-import streamlit as st
-
-pages = [
-    st.Page("../pages/fev_bench.py", title="fev-bench", icon=":material/trophy:"),
-    st.Page("../pages/about.py", title="About", icon=":material/info:"),
-]
-
-page = st.navigation(pages)
-page.run()

src/strings.py

@@ -1,114 +0,0 @@
-from src.utils import COLORS
-
-INTRODUCTION_TEXT = """
-This space hosts evaluation results for time series forecasting models. The results are obtained using [fev](https://github.com/autogluon/fev) - a lightweight library for evaluating time series forecasting models.
-"""
-
-LEGEND = """
-"""
-
-TABLE_INFO = f"""
-The leaderboard summarizes the performance of all models evaluated on the 100 tasks comprising **fev-bench**. More details available in the [paper](https://arxiv.org/abs/2509.26468).
-
-Model names are colored by type: <span style='color: {COLORS["pretrained_text"]}; font-weight: bold;'>Pretrained</span>, <span style='color: {COLORS["task_specific_text"]}; font-weight: bold;'>Task-specific</span>, and <span style='color: {COLORS["statistical_text"]}; font-weight: bold;'>Statistical</span>.
-
-The full matrix $E_{{rj}}$ with the error of each model $j$ on task $r$ is available at the bottom of the page.
-
-* **Avg. win rate (%)**: Fraction of all possible model pairs and tasks where this model achieves lower error than the competing model. For model $j$, defined as $W_j = \\frac{{1}}{{R(M-1)}} \\sum_{{r=1}}^{{R}} \\sum_{{k \\neq j}} (\\mathbf{{1}}(E_{{rj}} < E_{{rk}}) + 0.5 \\cdot \\mathbf{{1}}(E_{{rj}} = E_{{rk}}))$ where $R$ is number of tasks, $M$ is number of models. Ties count as half-wins.
-
-    Ranges from 0% (worst) to 100% (best). Higher values are better. This value changes as new models are added to the benchmark.
-
-* **Skill score (%)**: Measures how much the model reduces forecasting error compared to the Seasonal Naive baseline. Computed as $S_j = 100 \\times (1 - \\sqrt[R]{{\\prod_{{r=1}}^{{R}} E_{{rj}}/E_{{r\\beta}}}})$, where $E_{{r\\beta}}$ is baseline error on task $r$. Relative errors are clipped between 0.01 and 100 before aggregation to avoid extreme outliers. Positive values indicate better-than-baseline performance, negative values indicate worse-than-baseline performance.
-
-    Higher values are better. This value does not change as new models are added to the benchmark.
-
-* **Median runtime (s)**: Median end-to-end time (training + prediction across all evaluation windows) in seconds. Note that inference times depend on hardware, batch sizes, and implementation details, so these serve as a rough guide rather than definitive performance benchmarks.
-
-* **Leakage (%)**: For zero-shot models, percentage of benchmark datasets included in the model's training corpus. Results for tasks with reported overlap are replaced with Chronos-Bolt (Base) performance to prevent data leakage.
-
-* **Failed tasks (%)**: Percentage of tasks where the model failed to produce a forecast. Results for failed tasks are replaced with Seasonal Naive performance.
-
-* **Zero-shot**: Indicates whether the model can make predictions without task-specific training (✓ = zero-shot, × = task-specific).
-"""
-
-CHRONOS_BENCHMARK_BASIC_INFO = f"""
-**Chronos Benchmark II** contains results for various forecasting models on the 27 datasets used in Benchmark II in the paper [Chronos: Learning the Language of Time Series](https://arxiv.org/abs/2403.07815). {LEGEND}
-"""
-
-CHRONOS_BENCHMARK_DETAILS = f"""
-{TABLE_INFO}
-
-Task definitions and the detailed results are available on [GitHub](https://github.com/autogluon/fev/tree/main/benchmarks/chronos_zeroshot). More information for the datasets is available in [Table 3 of the paper](https://arxiv.org/abs/2403.07815).
-"""
-
-FEV_BENCHMARK_BASIC_INFO = f"""
-Results for various forecasting models on 100 tasks of the **fev-bench** benchmark, as described in [fev-bench: A Realistic Benchmark for Time Series Forecasting](https://arxiv.org/abs/2509.26468). {LEGEND}
-"""
-
-FEV_BENCHMARK_DETAILS = f"""
-{TABLE_INFO}
-
-Task definitions and the detailed results are available on [GitHub](https://github.com/autogluon/fev/tree/main/benchmarks/fev_bench/). For model wrappers, see [`models/`](https://github.com/autogluon/fev/tree/main/models). Datasets used for evaluation are available on [Hugging Face](https://huggingface.co/datasets/autogluon/fev_datasets).
-"""
-
-CITATION_HEADER = """
-If you find this leaderboard useful for your research, please consider citing the associated paper(s):
-
-"""
-CITATION_FEV = """
-```
-@article{shchur2025fev,
-  title={{fev-bench}: A Realistic Benchmark for Time Series Forecasting},
-  author={Shchur, Oleksandr and Ansari, Abdul Fatir and Turkmen, Caner and Stella, Lorenzo and Erickson, Nick and Guerron, Pablo and Bohlke-Schneider, Michael and Wang, Yuyang},
-  year={2025},
-  eprint={2509.26468},
-  archivePrefix={arXiv},
-  primaryClass={cs.LG}
-}
-```
-"""
-
-
-def get_pivot_legend(baseline_model: str, leakage_imputation_model: str) -> str:
-    return f"""
-Task definitions and raw results in CSV format are available on [GitHub](https://github.com/autogluon/fev/tree/main/benchmarks/fev_bench).
-
-Best results for each task are marked with
-<span style='background: {COLORS["gold"]}; color: {COLORS["text_default"]}; padding: 3px; border-radius: 5px;'>🥇 1st</span>
-<span style='background: {COLORS["silver"]}; color: {COLORS["text_default"]}; padding: 3px; border-radius: 5px;'>🥈 2nd</span>
-<span style='background: {COLORS["bronze"]}; color: {COLORS["text_default"]}; padding: 3px; border-radius: 5px;'>🥉 3rd</span>
-<br><br>
-**Imputation:**
-- <span style='color: {COLORS["failure_impute"]}; font-weight: bold;'>Failed tasks</span> imputed by {baseline_model}
-- <span style='color: {COLORS["leakage_impute"]}; font-weight: bold;'>Leaky tasks</span> imputed by {leakage_imputation_model}
-"""
-
-
-PAIRWISE_BENCHMARK_DETAILS = """
-The pairwise charts show head-to-head results between models:
-
-* **Win rate**: Percentage of tasks where Model 1 achieves lower error than Model 2 (ties count as half-wins).
-  A value above 50% means Model 1 is more accurate than Model 2 on average.
-
-* **Skill score**: Average relative error reduction of Model 1 with respect to Model 2.
-  A positive value means Model 1 reduces forecasting error compared to Model 2 on average.
-
-**Confidence Intervals**: 95% intervals are estimated using 1000 bootstrap samples over tasks.
-For each bootstrap sample, tasks are resampled with replacement and the pairwise win rate / skill score are recomputed.
-The intervals correspond to the 2.5th and 97.5th percentiles of these bootstrap distributions,
-capturing how model comparisons vary under alternative benchmark compositions.
-"""
-
-
-CITATION_CHRONOS = """
-```
-@article{ansari2024chronos,
-  title={Chronos: Learning the Language of Time Series},
-  author={Ansari, Abdul Fatir and Stella, Lorenzo and Turkmen, Caner and Zhang, Xiyuan, and Mercado, Pedro and Shen, Huibin and Shchur, Oleksandr and Rangapuram, Syama Syndar and Pineda Arango, Sebastian and Kapoor, Shubham and Zschiegner, Jasper and Maddix, Danielle C. and Wang, Hao and Mahoney, Michael W. and Torkkola, Kari and Gordon Wilson, Andrew and Bohlke-Schneider, Michael and Wang, Yuyang},
-  journal={Transactions on Machine Learning Research},
-  issn={2835-8856},
-  year={2024},
-  url={https://openreview.net/forum?id=gerNCVqqtR}
-}
-```
-"""

src/task_groups.py

@@ -1,266 +0,0 @@
-"""Task groupings for filtering the leaderboard by subsets."""
-
-# All tasks in the benchmark (100 tasks)
-ALL_TASKS = [
-    "ETT_15T", "ETT_1D", "ETT_1H", "ETT_1W",
-    "LOOP_SEATTLE_1D", "LOOP_SEATTLE_1H", "LOOP_SEATTLE_5T",
-    "M_DENSE_1D", "M_DENSE_1H",
-    "SZ_TAXI_15T", "SZ_TAXI_1H",
-    "australian_tourism",
-    "bizitobs_l2c_1H", "bizitobs_l2c_5T",
-    "boomlet_1062", "boomlet_1209", "boomlet_1225", "boomlet_1230", "boomlet_1282",
-    "boomlet_1487", "boomlet_1631", "boomlet_1676", "boomlet_1855", "boomlet_1975",
-    "boomlet_2187", "boomlet_285", "boomlet_619", "boomlet_772", "boomlet_963",
-    "ecdc_ili",
-    "entsoe_15T", "entsoe_1H", "entsoe_30T",
-    "epf_be", "epf_de", "epf_fr", "epf_np", "epf_pjm",
-    "ercot_1D", "ercot_1H", "ercot_1M", "ercot_1W",
-    "favorita_stores_1D", "favorita_stores_1M", "favorita_stores_1W",
-    "favorita_transactions_1D", "favorita_transactions_1M", "favorita_transactions_1W",
-    "fred_md_2025/cee", "fred_md_2025/macro",
-    "fred_qd_2025/cee", "fred_qd_2025/macro",
-    "gvar",
-    "hermes",
-    "hierarchical_sales_1D", "hierarchical_sales_1W",
-    "hospital", "hospital_admissions_1D", "hospital_admissions_1W",
-    "jena_weather_10T", "jena_weather_1D", "jena_weather_1H",
-    "kdd_cup_2022_10T", "kdd_cup_2022_1D", "kdd_cup_2022_30T",
-    "m5_1D", "m5_1M", "m5_1W",
-    "proenfo_gfc12", "proenfo_gfc14", "proenfo_gfc17",
-    "redset_15T", "redset_1H", "redset_5T",
-    "restaurant",
-    "rohlik_orders_1D", "rohlik_orders_1W", "rohlik_sales_1D", "rohlik_sales_1W",
-    "rossmann_1D", "rossmann_1W",
-    "solar_1D", "solar_1W", "solar_with_weather_15T", "solar_with_weather_1H",
-    "uci_air_quality_1D", "uci_air_quality_1H",
-    "uk_covid_nation_1D/cumulative", "uk_covid_nation_1D/new",
-    "uk_covid_nation_1W/cumulative", "uk_covid_nation_1W/new",
-    "uk_covid_utla_1D/new", "uk_covid_utla_1W/cumulative",
-    "us_consumption_1M", "us_consumption_1Q", "us_consumption_1Y",
-    "walmart",
-    "world_co2_emissions", "world_life_expectancy", "world_tourism",
-]
-
-# Mini benchmark - representative subset (20 tasks)
-MINI_TASKS = [
-    "jena_weather_1H",
-    "M_DENSE_1D",
-    "bizitobs_l2c_5T",
-    "rohlik_orders_1D",
-    "boomlet_1282",
-    "rossmann_1D",
-    "rossmann_1W",
-    "boomlet_1676",
-    "solar_with_weather_1H",
-    "boomlet_619",
-    "uci_air_quality_1H",
-    "uk_covid_nation_1D/cumulative",
-    "us_consumption_1Y",
-    "epf_np",
-    "world_co2_emissions",
-    "ETT_15T",
-    "ETT_1H",
-    "proenfo_gfc14",
-    "hospital_admissions_1D",
-    "hospital_admissions_1W",
-]
-
-# Frequency-based groupings
-FREQUENCY_GROUPS = {
-    "Sub-hourly": [
-        # T (1 minute)
-        "boomlet_1225", "boomlet_1282", "boomlet_285", "boomlet_619", "boomlet_772", "boomlet_963",
-        # 5T (5 minutes)
-        "LOOP_SEATTLE_5T", "bizitobs_l2c_5T", "redset_5T",
-        "boomlet_1062", "boomlet_1209", "boomlet_1230", "boomlet_1487",
-        # 10T (10 minutes)
-        "jena_weather_10T", "kdd_cup_2022_10T",
-        # 15T (15 minutes)
-        "ETT_15T", "SZ_TAXI_15T", "entsoe_15T", "redset_15T", "solar_with_weather_15T",
-        # 30T (30 minutes)
-        "entsoe_30T", "kdd_cup_2022_30T", "boomlet_1631", "boomlet_1676",
-    ],
-    "Hourly": [
-        "ETT_1H", "LOOP_SEATTLE_1H", "M_DENSE_1H", "SZ_TAXI_1H",
-        "bizitobs_l2c_1H", "entsoe_1H", "ercot_1H",
-        "epf_be", "epf_de", "epf_fr", "epf_np", "epf_pjm",
-        "jena_weather_1H",
-        "proenfo_gfc12", "proenfo_gfc14", "proenfo_gfc17",
-        "redset_1H", "solar_with_weather_1H", "uci_air_quality_1H",
-        "boomlet_1855", "boomlet_1975", "boomlet_2187",
-    ],
-    "Daily": [
-        "ETT_1D", "LOOP_SEATTLE_1D", "M_DENSE_1D",
-        "ercot_1D", "kdd_cup_2022_1D", "solar_1D",
-        "favorita_stores_1D", "favorita_transactions_1D",
-        "hierarchical_sales_1D", "m5_1D",
-        "restaurant",
-        "rohlik_orders_1D", "rohlik_sales_1D", "rossmann_1D",
-        "jena_weather_1D", "uci_air_quality_1D",
-        "hospital_admissions_1D",
-        "uk_covid_nation_1D/cumulative", "uk_covid_nation_1D/new", "uk_covid_utla_1D/new",
-    ],
-    "Weekly": [
-        "ETT_1W", "ercot_1W", "solar_1W",
-        "favorita_stores_1W", "favorita_transactions_1W",
-        "hierarchical_sales_1W", "m5_1W",
-        "hermes", "walmart",
-        "rohlik_orders_1W", "rohlik_sales_1W", "rossmann_1W",
-        "ecdc_ili",
-        "hospital_admissions_1W",
-        "uk_covid_nation_1W/cumulative", "uk_covid_nation_1W/new", "uk_covid_utla_1W/cumulative",
-    ],
-    "Monthly+": [
-        # Monthly
-        "ercot_1M",
-        "favorita_stores_1M", "favorita_transactions_1M", "m5_1M",
-        "fred_md_2025/cee", "fred_md_2025/macro",
-        "hospital",
-        "us_consumption_1M",
-        # Quarterly
-        "australian_tourism", "gvar",
-        "fred_qd_2025/cee", "fred_qd_2025/macro",
-        "us_consumption_1Q",
-        # Yearly
-        "us_consumption_1Y",
-        "world_co2_emissions", "world_life_expectancy", "world_tourism",
-    ],
-}
-
-# Domain-based groupings
-DOMAIN_GROUPS = {
-    "Energy": [
-        "ETT_15T", "ETT_1D", "ETT_1H", "ETT_1W",
-        "entsoe_15T", "entsoe_1H", "entsoe_30T",
-        "epf_be", "epf_de", "epf_fr", "epf_np", "epf_pjm",
-        "ercot_1D", "ercot_1H", "ercot_1M", "ercot_1W",
-        "kdd_cup_2022_10T", "kdd_cup_2022_1D", "kdd_cup_2022_30T",
-        "proenfo_gfc12", "proenfo_gfc14", "proenfo_gfc17",
-        "solar_1D", "solar_1W", "solar_with_weather_15T", "solar_with_weather_1H",
-    ],
-    "Retail": [
-        "favorita_stores_1D", "favorita_stores_1M", "favorita_stores_1W",
-        "favorita_transactions_1D", "favorita_transactions_1M", "favorita_transactions_1W",
-        "hermes",
-        "hierarchical_sales_1D", "hierarchical_sales_1W",
-        "m5_1D", "m5_1M", "m5_1W",
-        "restaurant",
-        "rohlik_orders_1D", "rohlik_orders_1W", "rohlik_sales_1D", "rohlik_sales_1W",
-        "rossmann_1D", "rossmann_1W",
-        "walmart",
-    ],
-    "Nature": [
-        "jena_weather_10T", "jena_weather_1D", "jena_weather_1H",
-        "uci_air_quality_1D", "uci_air_quality_1H",
-    ],
-    "Cloud": [
-        "bizitobs_l2c_1H", "bizitobs_l2c_5T",
-        "boomlet_1062", "boomlet_1209", "boomlet_1225", "boomlet_1230", "boomlet_1282",
-        "boomlet_1487", "boomlet_1631", "boomlet_1676", "boomlet_1855", "boomlet_1975",
-        "boomlet_2187", "boomlet_285", "boomlet_619", "boomlet_772", "boomlet_963",
-        "redset_15T", "redset_1H", "redset_5T",
-    ],
-    "Health": [
-        "ecdc_ili",
-        "hospital", "hospital_admissions_1D", "hospital_admissions_1W",
-        "uk_covid_nation_1D/cumulative", "uk_covid_nation_1D/new",
-        "uk_covid_nation_1W/cumulative", "uk_covid_nation_1W/new",
-        "uk_covid_utla_1D/new", "uk_covid_utla_1W/cumulative",
-    ],
-    "Econ": [
-        "australian_tourism",
-        "fred_md_2025/cee", "fred_md_2025/macro",
-        "fred_qd_2025/cee", "fred_qd_2025/macro",
-        "gvar",
-        "us_consumption_1M", "us_consumption_1Q", "us_consumption_1Y",
-        "world_co2_emissions", "world_life_expectancy", "world_tourism",
-    ],
-    "Mobility": [
-        "LOOP_SEATTLE_1D", "LOOP_SEATTLE_1H", "LOOP_SEATTLE_5T",
-        "M_DENSE_1D", "M_DENSE_1H",
-        "SZ_TAXI_15T", "SZ_TAXI_1H",
-    ],
-}
-# Task type groupings (overlapping: a multivariate task with covariates
-# belongs to both "Covariate-informed" and "Multivariate").
-# - Multivariate: target is a list of columns
-# - Covariate-informed: known_dynamic_columns or past_dynamic_columns is non-empty
-# - Univariate: neither of the above
-TASK_TYPE_GROUPS = {
-    "Univariate": [
-        "LOOP_SEATTLE_1D", "LOOP_SEATTLE_1H", "LOOP_SEATTLE_5T",
-        "M_DENSE_1D", "M_DENSE_1H",
-        "SZ_TAXI_15T", "SZ_TAXI_1H",
-        "australian_tourism", "ecdc_ili",
-        "ercot_1D", "ercot_1H", "ercot_1M", "ercot_1W",
-        "hierarchical_sales_1D", "hierarchical_sales_1W",
-        "hospital", "hospital_admissions_1D", "hospital_admissions_1W",
-        "redset_15T", "redset_1H", "redset_5T",
-        "restaurant",
-        "solar_1D", "solar_1W",
-        "uk_covid_utla_1D/new", "uk_covid_utla_1W/cumulative",
-        "us_consumption_1M", "us_consumption_1Q", "us_consumption_1Y",
-        "world_co2_emissions", "world_life_expectancy", "world_tourism",
-    ],
-    "Covariate-informed": [
-        "entsoe_15T", "entsoe_1H", "entsoe_30T",
-        "epf_be", "epf_de", "epf_fr", "epf_np", "epf_pjm",
-        "favorita_stores_1D", "favorita_stores_1M", "favorita_stores_1W",
-        "favorita_transactions_1D", "favorita_transactions_1M", "favorita_transactions_1W",
-        "fred_md_2025/cee", "fred_qd_2025/cee",
-        "gvar", "hermes",
-        "kdd_cup_2022_10T", "kdd_cup_2022_1D", "kdd_cup_2022_30T",
-        "m5_1D", "m5_1M", "m5_1W",
-        "proenfo_gfc12", "proenfo_gfc14", "proenfo_gfc17",
-        "rohlik_orders_1D", "rohlik_orders_1W", "rohlik_sales_1D", "rohlik_sales_1W",
-        "rossmann_1D", "rossmann_1W",
-        "solar_with_weather_15T", "solar_with_weather_1H",
-        "uci_air_quality_1D", "uci_air_quality_1H",
-        "uk_covid_nation_1D/cumulative", "uk_covid_nation_1D/new",
-        "uk_covid_nation_1W/cumulative", "uk_covid_nation_1W/new",
-        "walmart",
-    ],
-    "Multivariate": [
-        "ETT_15T", "ETT_1D", "ETT_1H", "ETT_1W",
-        "bizitobs_l2c_1H", "bizitobs_l2c_5T",
-        "boomlet_1062", "boomlet_1209", "boomlet_1225", "boomlet_1230", "boomlet_1282",
-        "boomlet_1487", "boomlet_1631", "boomlet_1676", "boomlet_1855", "boomlet_1975",
-        "boomlet_2187", "boomlet_285", "boomlet_619", "boomlet_772", "boomlet_963",
-        "fred_md_2025/cee", "fred_md_2025/macro", "fred_qd_2025/cee", "fred_qd_2025/macro",
-        "gvar",
-        "jena_weather_10T", "jena_weather_1D", "jena_weather_1H",
-        "uci_air_quality_1D", "uci_air_quality_1H",
-        "uk_covid_nation_1D/cumulative", "uk_covid_nation_1D/new",
-        "uk_covid_nation_1W/cumulative", "uk_covid_nation_1W/new",
-    ],
-}
-
-
-def get_task_group(group_type: str, group_value: str | None = None) -> list[str]:
-    """Get the list of tasks for a given group type and value.
-
-    Args:
-        group_type: One of "full", "mini", "frequency", "domain", "task_type"
-        group_value: Required for "frequency", "domain", and "task_type" types
-
-    Returns:
-        List of task names belonging to the group
-    """
-    if group_type == "full":
-        return ALL_TASKS
-    elif group_type == "mini":
-        return MINI_TASKS
-    elif group_type == "frequency":
-        if group_value is None:
-            raise ValueError("group_value required for frequency grouping")
-        return FREQUENCY_GROUPS[group_value]
-    elif group_type == "domain":
-        if group_value is None:
-            raise ValueError("group_value required for domain grouping")
-        return DOMAIN_GROUPS[group_value]
-    elif group_type == "task_type":
-        if group_value is None:
-            raise ValueError("group_value required for task_type grouping")
-        return TASK_TYPE_GROUPS[group_value]
-    else:
-        raise ValueError(f"Unknown group_type: {group_type}")

src/utils.py

@@ -1,413 +0,0 @@
-import altair as alt
-import fev
-import pandas as pd
-import pandas.io.formats.style
-
-# Color constants - all colors defined in one place
-
-COLORS = {
-    "pretrained_text": "#5A7FA5",
-    "task_specific_text": "#7B5A9A",
-    "statistical_text": "#A5795A",
-    "bar_fill": "#8d5eb7",
-    "error_bar": "#222222",
-    "point": "#111111",
-    "text_white": "white",
-    "text_black": "black",
-    "text_default": "#111",
-    "gold": "#F7D36B",
-    "silver": "#E5E7EB",
-    "bronze": "#E6B089",
-    "leakage_impute": "#3B82A0",
-    "failure_impute": "#E07B39",
-}
-HEATMAP_COLOR_SCHEME = "purplegreen"
-
-# Model configuration: (url, org, zero_shot, model_type)
-MODEL_CONFIG = {
-    # Chronos Models
-    "chronos_tiny": ("amazon/chronos-t5-tiny", "AWS", True, "pretrained"),
-    "chronos_mini": ("amazon/chronos-t5-mini", "AWS", True, "pretrained"),
-    "chronos_small": ("amazon/chronos-t5-small", "AWS", True, "pretrained"),
-    "chronos_base": ("amazon/chronos-t5-base", "AWS", True, "pretrained"),
-    "chronos_large": ("amazon/chronos-t5-large", "AWS", True, "pretrained"),
-    "chronos_bolt_tiny": ("amazon/chronos-bolt-tiny", "AWS", True, "pretrained"),
-    "chronos_bolt_mini": ("amazon/chronos-bolt-mini", "AWS", True, "pretrained"),
-    "chronos_bolt_small": ("amazon/chronos-bolt-small", "AWS", True, "pretrained"),
-    "chronos_bolt_base": ("amazon/chronos-bolt-base", "AWS", True, "pretrained"),
-    "chronos-bolt": ("amazon/chronos-bolt-base", "AWS", True, "pretrained"),
-    "chronos-2": ("amazon/chronos-2", "AWS", True, "pretrained"),
-    # Moirai Models
-    "moirai_large": ("Salesforce/moirai-1.1-R-large", "Salesforce", True, "pretrained"),
-    "moirai_base": ("Salesforce/moirai-1.1-R-base", "Salesforce", True, "pretrained"),
-    "moirai_small": ("Salesforce/moirai-1.1-R-small", "Salesforce", True, "pretrained"),
-    "moirai-2.0": ("Salesforce/moirai-2.0-R-small", "Salesforce", True, "pretrained"),
-    # TimesFM Models
-    "timesfm": ("google/timesfm-1.0-200m-pytorch", "Google", True, "pretrained"),
-    "timesfm-2.0": ("google/timesfm-2.0-500m-pytorch", "Google", True, "pretrained"),
-    "timesfm-2.5": ("google/timesfm-2.5-200m-pytorch", "Google", True, "pretrained"),
-    # Toto Models
-    "toto-1.0": ("Datadog/Toto-Open-Base-1.0", "Datadog", True, "pretrained"),
-    "toto-2.0-2.5b": ("Datadog/Toto-2.0-2.5B", "Datadog", True, "pretrained"),
-    "toto-2.0-22m": ("Datadog/Toto-2.0-22m", "Datadog", True, "pretrained"),
-    # Other Models
-    "tirex": ("NX-AI/TiRex", "NX-AI", True, "pretrained"),
-    "tirex-2": ("NX-AI/TiRex-2-fevbench", "NX-AI", True, "pretrained"),
-    "tabpfn-ts": ("Prior-Labs/TabPFN-v2-reg", "Prior Labs", True, "pretrained"),
-    "tabpfn-ts-3": ("Prior-Labs/TabPFN-2.5-reg", "Prior Labs", True, "pretrained"),
-    "sundial-base": ("thuml/sundial-base-128m", "Tsinghua University", True, "pretrained"),
-    "ttm-r2": ("ibm-granite/granite-timeseries-ttm-r2", "IBM", True, "pretrained"),
-    "flowstate": ("ibm-granite/granite-timeseries-flowstate-r1", "IBM", True, "pretrained"),
-    # GluonTS Models
-    "deepar": ("https://github.com/awslabs/gluonts", "—", False, "task-specific"),
-    "tft": ("https://github.com/awslabs/gluonts", "—", False, "task-specific"),
-    "patchtst": ("https://github.com/awslabs/gluonts", "—", False, "task-specific"),
-    # MLForecast Models
-    "lightgbm": ("https://nixtlaverse.nixtla.io/mlforecast", "—", False, "task-specific"),
-    "catboost": ("https://nixtlaverse.nixtla.io/mlforecast", "—", False, "task-specific"),
-    # Statistical models
-    "stat. ensemble": (
-        "https://nixtlaverse.nixtla.io/statsforecast/",
-        "—",
-        False,
-        "statistical",
-    ),
-    "autoarima": ("https://nixtlaverse.nixtla.io/statsforecast/", "—", False, "statistical"),
-    "autotheta": ("https://nixtlaverse.nixtla.io/statsforecast/", "—", False, "statistical"),
-    "autoets": ("https://nixtlaverse.nixtla.io/statsforecast/", "—", False, "statistical"),
-    "seasonalnaive": ("https://nixtlaverse.nixtla.io/statsforecast/", "—", False, "statistical"),
-    "seasonal naive": (
-        "https://nixtlaverse.nixtla.io/statsforecast/",
-        "—",
-        False,
-        "statistical",
-    ),
-    "drift": ("https://nixtlaverse.nixtla.io/statsforecast/", "—", False, "statistical"),
-    "naive": ("https://nixtlaverse.nixtla.io/statsforecast/", "—", False, "statistical"),
-}
-
-
-ALL_METRICS = {
-    "SQL": (
-        "SQL: Scaled Quantile Loss",
-        "The [Scaled Quantile Loss (SQL)](https://auto.gluon.ai/dev/tutorials/timeseries/forecasting-metrics.html#autogluon.timeseries.metrics.SQL) is a **scale-invariant** metric for evaluating **probabilistic** forecasts.",
-    ),
-    "MASE": (
-        "MASE: Mean Absolute Scaled Error",
-        "The [Mean Absolute Scaled Error (MASE)](https://auto.gluon.ai/dev/tutorials/timeseries/forecasting-metrics.html#autogluon.timeseries.metrics.MASE) is a **scale-invariant** metric for evaluating **point** forecasts.",
-    ),
-    "WQL": (
-        "WQL: Weighted Quantile Loss",
-        "The [Weighted Quantile Loss (WQL)](https://auto.gluon.ai/dev/tutorials/timeseries/forecasting-metrics.html#autogluon.timeseries.metrics.WQL), is a **scale-dependent** metric for evaluating **probabilistic** forecasts.",
-    ),
-    "WAPE": (
-        "WAPE: Weighted Absolute Percentage Error",
-        "The [Weighted Absolute Percentage Error (WAPE)](https://auto.gluon.ai/dev/tutorials/timeseries/forecasting-metrics.html#autogluon.timeseries.metrics.WAPE) is a **scale-dependent** metric for evaluating **point** forecasts.",
-    ),
-}
-
-
-def format_metric_name(metric_name: str):
-    return ALL_METRICS[metric_name][0]
-
-
-def get_metric_description(metric_name: str):
-    return ALL_METRICS[metric_name][1]
-
-
-# Models excluded from the leaderboard display (redundant Toto-2.0 sizes; keep 2.5B and 22m)
-HIDDEN_MODELS = ["Toto-2.0-1B", "Toto-2.0-313m", "Toto-2.0-4m"]
-
-
-def filter_hidden_models(df: pd.DataFrame, model_column: str = "model_name") -> pd.DataFrame:
-    """Drop rows for models in HIDDEN_MODELS based on the given model-name column."""
-    return df[~df[model_column].isin(HIDDEN_MODELS)]
-
-
-def validate_model_metadata(model_names) -> None:
-    """Raise if any displayed model lacks a MODEL_CONFIG entry (organization, link, type, etc.)."""
-    missing = sorted({m for m in model_names if MODEL_CONFIG.get(m.lower()) is None})
-    if missing:
-        raise ValueError(
-            f"Missing MODEL_CONFIG metadata (organization, link, type) for models: {missing}. "
-            "Add entries to MODEL_CONFIG in src/utils.py."
-        )
-
-
-def get_model_link(model_name):
-    config = MODEL_CONFIG.get(model_name.lower())
-    if not config or not config[0]:
-        return ""
-    url = config[0]
-    return url if url.startswith("https:") else f"https://huggingface.co/{url}"
-
-
-def get_model_organization(model_name):
-    config = MODEL_CONFIG.get(model_name.lower())
-    return config[1] if config else "—"
-
-
-def get_zero_shot_status(model_name):
-    config = MODEL_CONFIG.get(model_name.lower())
-    return "✓" if config and config[2] else "×"
-
-
-def get_model_type(model_name):
-    config = MODEL_CONFIG.get(model_name.lower())
-    return config[3] if config else "—"
-
-
-MODEL_TYPE_COLORS = {
-    "pretrained": "pretrained_text",
-    "task-specific": "task_specific_text",
-    "statistical": "statistical_text",
-}
-
-
-def highlight_model_type_color(cell):
-    config = MODEL_CONFIG.get(cell.lower())
-    if config:
-        color_key = MODEL_TYPE_COLORS.get(config[3], "text_default")
-        return f"font-weight: bold; color: {COLORS[color_key]}"
-    return "font-weight: bold"
-
-
-def format_leaderboard(df: pd.DataFrame):
-    df = df.copy()
-    df["skill_score"] = df["skill_score"].round(1)
-    df["win_rate"] = df["win_rate"].round(1)
-    df["zero_shot"] = df["model_name"].apply(get_zero_shot_status)
-    # Format leakage column: convert to int for all models, 0 for non-zero-shot
-    df["training_corpus_overlap"] = df.apply(
-        lambda row: int(round(row["training_corpus_overlap"] * 100)) if row["zero_shot"] == "✓" else 0,
-        axis=1,
-    )
-    df["link"] = df["model_name"].apply(get_model_link)
-    df["org"] = df["model_name"].apply(get_model_organization)
-    df = df[
-        [
-            "model_name",
-            "win_rate",
-            "skill_score",
-            "median_inference_time_s_per100",
-            "training_corpus_overlap",
-            "num_failures",
-            "zero_shot",
-            "org",
-            "link",
-        ]
-    ]
-    return (
-        df.style.map(highlight_model_type_color, subset=["model_name"])
-        .map(lambda x: "font-weight: bold", subset=["zero_shot"])
-        .apply(
-            lambda x: ["background-color: #f8f9fa" if i % 2 == 1 else "" for i in range(len(x))],
-            axis=0,
-        )
-    )
-
-
-def construct_bar_chart(df: pd.DataFrame, col: str, metric_name: str):
-    label = "Skill Score" if col == "skill_score" else "Win Rate"
-
-    tooltip = [
-        alt.Tooltip("model_name:N"),
-        alt.Tooltip(f"{col}:Q", format=".2f"),
-        alt.Tooltip(f"{col}_lower:Q", title="95% CI Lower", format=".2f"),
-        alt.Tooltip(f"{col}_upper:Q", title="95% CI Upper", format=".2f"),
-    ]
-
-    base_encode = {
-        "y": alt.Y("model_name:N", title="Forecasting Model", sort=None),
-        "tooltip": tooltip,
-    }
-
-    bars = (
-        alt.Chart(df)
-        .mark_bar(color=COLORS["bar_fill"], cornerRadius=4)
-        .encode(
-            x=alt.X(f"{col}:Q", title=f"{label} (%)", scale=alt.Scale(zero=False)),
-            **base_encode,
-        )
-    )
-
-    error_bars = (
-        alt.Chart(df)
-        .mark_errorbar(ticks={"height": 5}, color=COLORS["error_bar"])
-        .encode(
-            y=alt.Y("model_name:N", title=None, sort=None),
-            x=alt.X(f"{col}_lower:Q", title=f"{label} (%)"),
-            x2=alt.X2(f"{col}_upper:Q"),
-            tooltip=tooltip,
-        )
-    )
-
-    points = (
-        alt.Chart(df)
-        .mark_point(filled=True, color=COLORS["point"])
-        .encode(x=alt.X(f"{col}:Q", title=f"{label} (%)"), **base_encode)
-    )
-
-    return (
-        (bars + error_bars + points)
-        .properties(height=500, title=f"{label} ({metric_name}) with 95% CIs")
-        .configure_title(fontSize=16)
-    )
-
-
-def construct_pairwise_chart(df: pd.DataFrame, col: str, metric_name: str):
-    # Color ranges kept in sync with the fev repo's generate_fev_bench_figures.py
-    config = {
-        "win_rate": ("Win Rate", [0, 100], 50, f"abs(datum.{col} - 50) > 30"),
-        "skill_score": ("Skill Score", [-30, 30], 0, f"abs(datum.{col}) > 20"),
-    }
-    cbar_label, domain, domain_mid, text_condition = config[col]
-
-    df = df.copy()
-    for c in [col, f"{col}_lower", f"{col}_upper"]:
-        df[c] *= 100
-
-    model_order = df.groupby("model_1")[col].mean().sort_values(ascending=False).index.tolist()
-
-    tooltip = [
-        alt.Tooltip("model_1:N", title="Model 1"),
-        alt.Tooltip("model_2:N", title="Model 2"),
-        alt.Tooltip(f"{col}:Q", title=cbar_label.split(" ")[0], format=".1f"),
-        alt.Tooltip(f"{col}_lower:Q", title="95% CI Lower", format=".1f"),
-        alt.Tooltip(f"{col}_upper:Q", title="95% CI Upper", format=".1f"),
-    ]
-
-    base = alt.Chart(df).encode(
-        x=alt.X(
-            "model_2:N",
-            sort=model_order,
-            title="Model 2",
-            axis=alt.Axis(orient="top", labelAngle=-90),
-        ),
-        y=alt.Y("model_1:N", sort=model_order, title="Model 1"),
-    )
-
-    heatmap = base.mark_rect().encode(
-        color=alt.Color(
-            f"{col}:Q",
-            legend=None,
-            scale=alt.Scale(
-                scheme=HEATMAP_COLOR_SCHEME,
-                domain=domain,
-                domainMid=domain_mid,
-                clamp=True,
-            ),
-        ),
-        tooltip=tooltip,
-    )
-
-    text_main = base.mark_text(dy=-8, fontSize=8, baseline="top", yOffset=5).encode(
-        text=alt.Text(f"{col}:Q", format=".1f"),
-        color=alt.condition(
-            text_condition,
-            alt.value(COLORS["text_white"]),
-            alt.value(COLORS["text_black"]),
-        ),
-        tooltip=tooltip,
-    )
-
-    return (
-        (heatmap + text_main)
-        .properties(
-            height=550,
-            title={
-                "text": f"Pairwise {cbar_label} ({metric_name}) with 95% CIs",
-                "fontSize": 16,
-            },
-        )
-        .configure_axis(labelFontSize=11, titleFontSize=13, titleFontWeight="bold")
-        .resolve_scale(color="independent")
-    )
-
-
-def construct_pivot_table_from_df(errors: pd.DataFrame, metric_name: str) -> pd.io.formats.style.Styler:
-    """Construct styled pivot table from precomputed DataFrame."""
-
-    def highlight_by_position(styler):
-        rank_colors = {1: COLORS["gold"], 2: COLORS["silver"], 3: COLORS["bronze"]}
-
-        for row_idx in errors.index:
-            row_ranks = errors.loc[row_idx].rank(method="min")
-            for col_idx in errors.columns:
-                rank = row_ranks[col_idx]
-                style_parts = []
-
-                # Rank background colors
-                if rank <= 3:
-                    style_parts.append(f"background-color: {rank_colors[rank]}")
-                else:
-                    style_parts.append(f"color: {COLORS['text_default']}")
-
-                if style_parts:
-                    styler = styler.map(
-                        lambda x, s="; ".join(style_parts): s,
-                        subset=pd.IndexSlice[row_idx:row_idx, col_idx:col_idx],
-                    )
-        return styler
-
-    return highlight_by_position(errors.style).format(precision=3)
-
-
-def construct_pivot_table(
-    summaries: pd.DataFrame,
-    metric_name: str,
-    baseline_model: str,
-    leakage_imputation_model: str,
-) -> pd.io.formats.style.Styler:
-    errors = fev.pivot_table(summaries=summaries, metric_column=metric_name, task_columns=["task_name"])
-    train_overlap = (
-        fev.pivot_table(
-            summaries=summaries,
-            metric_column="trained_on_this_dataset",
-            task_columns=["task_name"],
-        )
-        .fillna(False)
-        .astype(bool)
-    )
-
-    is_imputed_baseline = errors.isna()
-    is_leakage_imputed = train_overlap
-
-    # Handle imputations
-    errors = errors.mask(train_overlap, errors[leakage_imputation_model], axis=0)
-    for col in errors.columns:
-        if col != baseline_model:
-            errors[col] = errors[col].fillna(errors[baseline_model])
-
-    errors = errors[errors.rank(axis=1).mean().sort_values().index]
-    errors.index.rename("Task name", inplace=True)
-
-    def highlight_by_position(styler):
-        rank_colors = {1: COLORS["gold"], 2: COLORS["silver"], 3: COLORS["bronze"]}
-
-        for row_idx in errors.index:
-            row_ranks = errors.loc[row_idx].rank(method="min")
-            for col_idx in errors.columns:
-                rank = row_ranks[col_idx]
-                style_parts = []
-
-                # Rank background colors
-                if rank <= 3:
-                    style_parts.append(f"background-color: {rank_colors[rank]}")
-
-                # Imputation text colors
-                if is_leakage_imputed.loc[row_idx, col_idx]:
-                    style_parts.append(f"color: {COLORS['leakage_impute']}")
-                elif is_imputed_baseline.loc[row_idx, col_idx]:
-                    style_parts.append(f"color: {COLORS['failure_impute']}")
-                elif not style_parts or (len(style_parts) == 1 and "font-weight" in style_parts[0]):
-                    style_parts.append(f"color: {COLORS['text_default']}")
-
-                if style_parts:
-                    styler = styler.map(
-                        lambda x, s="; ".join(style_parts): s,
-                        subset=pd.IndexSlice[row_idx:row_idx, col_idx:col_idx],
-                    )
-        return styler
-
-    return highlight_by_position(errors.style).format(precision=3)

tables/domain_cloud/leaderboard_MASE.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-Toto-2.0-2.5B,96.11111111111113,47.105140103596796,0.0,5.064579399732653,0.0,0.0
-Toto-2.0-1B,95.37037037037037,47.049179559947774,0.0,2.3743196950416188,0.0,0.0
-Toto-2.0-313m,92.4074074074074,46.485472580621256,0.0,0.9745701860666667,0.0,0.0
-Toto-2.0-22m,84.25925925925925,43.92623198246986,0.0,0.13920661274489796,0.0,0.0
-Toto-1.0,78.70370370370371,41.88927928450025,0.0,45.854219394249995,0.0,0.0
-Chronos-2,75.55555555555556,42.51579967639686,0.0,1.1862588189,0.0,0.0
-Toto-2.0-4m,73.51851851851853,40.931171483779714,0.0,0.09261558033545919,0.0,0.0
-TimesFM-2.5,69.44444444444444,40.26605676264323,0.0,6.434508300230608,0.0,0.0
-TiRex-2,67.96296296296298,39.65417127595432,0.0,0.19312244271691675,0.0,0.0
-TiRex,64.81481481481481,38.09940061802194,0.0,0.20884203875396826,0.0,0.0
-Moirai-2.0,52.03703703703704,35.5798994200739,0.0,0.35171731723214283,0.1,0.0
-FlowState,51.66666666666666,30.68598311802213,0.0,12.472611368300264,0.0,0.0
-TabPFN-TS-3,50.74074074074074,34.02528132692776,0.0,431.5150328579276,0.0,0.0
-PatchTST,48.51851851851852,34.304846616783294,1068.4652680383783,0.7892402496428571,0.0,0.0
-TFT,48.425925925925924,34.39379489295074,1003.5120332510221,1.1076982505700976,0.0,0.0
-Sundial-Base,48.14814814814816,34.444932595485724,0.0,7.874095355196429,0.0,0.0
-Chronos-Bolt,46.11111111111111,30.890375949929528,0.0,0.21284866287857143,0.0,0.0
-TabPFN-TS,44.25925925925926,31.182648441489537,0.0,285.2805137923404,0.0,0.0
-CatBoost,40.74074074074074,28.99041616417205,123.37088255733154,0.43462186795918367,0.0,0.0
-DeepAR,36.48148148148148,25.641579380120593,1590.4637105111146,1.558186748969388,0.0,0.0
-LightGBM,30.185185185185183,21.217567102831968,7.053590123430682,0.3469036807346939,0.0,0.0
-Stat. Ensemble,23.98148148148148,12.457381191619765,0.0,140.07917045413043,0.0,5.0
-AutoARIMA,21.38888888888889,13.156560456056853,0.0,18.324502920714288,0.0,5.0
-AutoETS,15.64814814814815,9.008132945543156,0.0,2.9907604154761906,0.0,15.0
-AutoTheta,15.555555555555555,6.832233363582574,0.0,4.0546638315458425,0.0,0.0
-Naive,12.77777777777778,-25.50199781747715,0.0,0.43933051720441596,0.0,0.0
-Seasonal Naive,10.37037037037037,0.0,0.0,0.5176203110585994,0.0,0.0
-Drift,4.814814814814815,-32.85429098273796,0.0,0.4190869192562794,0.0,0.0

tables/domain_cloud/leaderboard_SQL.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-Toto-2.0-2.5B,97.03703703703704,66.67609437659667,0.0,5.064579399732653,0.0,0.0
-Toto-2.0-1B,95.55555555555557,66.67229326421315,0.0,2.3743196950416188,0.0,0.0
-Toto-2.0-313m,92.77777777777779,66.42835118245338,0.0,0.9745701860666667,0.0,0.0
-Toto-2.0-22m,85.74074074074073,64.64905946685398,0.0,0.13920661274489796,0.0,0.0
-Toto-1.0,78.70370370370368,63.05875031595707,0.0,45.854219394249995,0.0,0.0
-Chronos-2,76.4814814814815,63.92789670076326,0.0,1.1862588189,0.0,0.0
-Toto-2.0-4m,75.0,62.51740509789393,0.0,0.09261558033545919,0.0,0.0
-TiRex-2,70.74074074074075,61.657338261486025,0.0,0.19312244271691675,0.0,0.0
-TimesFM-2.5,69.81481481481482,61.98663035039822,0.0,6.434508300230608,0.0,0.0
-TiRex,66.48148148148148,60.871565834690514,0.0,0.20884203875396826,0.0,0.0
-TabPFN-TS-3,57.59259259259261,59.42246884042356,0.0,431.5150328579276,0.0,0.0
-Moirai-2.0,54.44444444444445,58.416109773202194,0.0,0.35171731723214283,0.1,0.0
-FlowState,53.51851851851852,55.917373913965896,0.0,12.472611368300264,0.0,0.0
-PatchTST,49.351851851851855,56.65838528437654,1068.4652680383783,0.7892402496428571,0.0,0.0
-TFT,48.51851851851852,56.101100728840805,1003.5120332510221,1.1076982505700976,0.0,0.0
-Sundial-Base,45.37037037037038,56.64773521043558,0.0,7.874095355196429,0.0,0.0
-Chronos-Bolt,45.370370370370374,54.85929046462743,0.0,0.21284866287857143,0.0,0.0
-TabPFN-TS,43.7037037037037,54.882167458139385,0.0,285.2805137923404,0.0,0.0
-DeepAR,38.7962962962963,50.20430422932948,1590.4637105111146,1.558186748969388,0.0,0.0
-CatBoost,31.85185185185186,46.25315473529981,123.37088255733154,0.43462186795918367,0.0,0.0
-LightGBM,25.740740740740737,40.369919076130486,7.053590123430682,0.3469036807346939,0.0,0.0
-AutoARIMA,25.092592592592595,34.1099179045811,0.0,18.324502920714288,0.0,5.0
-Stat. Ensemble,22.499999999999996,21.741616773476768,0.0,140.07917045413043,0.0,5.0
-AutoETS,16.01851851851852,-26.853793282334813,0.0,2.9907604154761906,0.0,15.0
-AutoTheta,11.851851851851853,-2.114517117703918,0.0,4.0546638315458425,0.0,0.0
-Seasonal Naive,11.759259259259258,0.0,0.0,0.5176203110585994,0.0,0.0
-Naive,7.962962962962965,-102.14853947002402,0.0,0.43933051720441596,0.0,0.0
-Drift,2.2222222222222228,-110.24318719846286,0.0,0.4190869192562794,0.0,0.0

tables/domain_cloud/leaderboard_WAPE.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-Toto-2.0-2.5B,97.03703703703704,53.71035361627254,0.0,5.064579399732653,0.0,0.0
-Toto-2.0-1B,95.37037037037038,53.096830919470946,0.0,2.3743196950416188,0.0,0.0
-Toto-2.0-313m,93.14814814814815,52.69411150627982,0.0,0.9745701860666667,0.0,0.0
-Toto-2.0-22m,85.92592592592592,50.191472774349634,0.0,0.13920661274489796,0.0,0.0
-Chronos-2,78.14814814814817,50.57276323971893,0.0,1.1862588189,0.0,0.0
-Toto-1.0,77.5925925925926,47.09252281338565,0.0,45.854219394249995,0.0,0.0
-Toto-2.0-4m,72.96296296296298,47.10219495180865,0.0,0.09261558033545919,0.0,0.0
-TiRex-2,68.33333333333333,46.55373683052376,0.0,0.19312244271691675,0.0,0.0
-TimesFM-2.5,68.14814814814817,46.24771958720855,0.0,6.434508300230608,0.0,0.0
-TiRex,63.888888888888886,44.520635260445665,0.0,0.20884203875396826,0.0,0.0
-TabPFN-TS-3,56.85185185185186,46.210313482546184,0.0,431.5150328579276,0.0,0.0
-FlowState,56.11111111111112,44.39308253523333,0.0,12.472611368300264,0.0,0.0
-Moirai-2.0,53.51851851851852,42.79254856807111,0.0,0.35171731723214283,0.1,0.0
-TabPFN-TS,50.37037037037037,42.304181829008726,0.0,285.2805137923404,0.0,0.0
-PatchTST,49.07407407407408,42.75818805959519,1068.4652680383783,0.7892402496428571,0.0,0.0
-Sundial-Base,47.5925925925926,41.966358434053696,0.0,7.874095355196429,0.0,0.0
-Chronos-Bolt,47.22222222222222,39.89366883509092,0.0,0.21284866287857143,0.0,0.0
-TFT,45.46296296296297,37.9920627846737,1003.5120332510221,1.1076982505700976,0.0,0.0
-CatBoost,37.03703703703704,34.58752644878078,123.37088255733154,0.43462186795918367,0.0,0.0
-DeepAR,36.11111111111111,31.125782577257844,1590.4637105111146,1.558186748969388,0.0,0.0
-LightGBM,29.074074074074076,27.03716130150796,7.053590123430682,0.3469036807346939,0.0,0.0
-Stat. Ensemble,21.38888888888889,17.59542897915567,0.0,140.07917045413043,0.0,5.0
-AutoARIMA,18.425925925925924,16.5309827995087,0.0,18.324502920714288,0.0,5.0
-AutoETS,14.351851851851851,5.6618608202705705,0.0,2.9907604154761906,0.0,15.0
-AutoTheta,12.77777777777778,12.660865320459136,0.0,4.0546638315458425,0.0,0.0
-Naive,12.222222222222221,4.49837321934039,0.0,0.43933051720441596,0.0,0.0
-Seasonal Naive,7.4074074074074066,0.0,0.0,0.5176203110585994,0.0,0.0
-Drift,4.4444444444444455,-1.7537853153904326,0.0,0.4190869192562794,0.0,0.0

tables/domain_cloud/leaderboard_WQL.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-Toto-2.0-2.5B,97.96296296296296,69.03469555605878,0.0,5.064579399732653,0.0,0.0
-Toto-2.0-1B,95.74074074074075,68.75529346896873,0.0,2.3743196950416188,0.0,0.0
-Toto-2.0-313m,92.5925925925926,68.41066967488192,0.0,0.9745701860666667,0.0,0.0
-Toto-2.0-22m,86.11111111111111,66.78327813931047,0.0,0.13920661274489796,0.0,0.0
-Chronos-2,78.70370370370372,66.94397676250325,0.0,1.1862588189,0.0,0.0
-Toto-1.0,76.2962962962963,64.46135334372015,0.0,45.854219394249995,0.0,0.0
-Toto-2.0-4m,73.88888888888887,64.42603072886158,0.0,0.09261558033545919,0.0,0.0
-TiRex-2,70.37037037037037,63.99709672683953,0.0,0.19312244271691675,0.0,0.0
-TimesFM-2.5,67.77777777777779,63.7537487246866,0.0,6.434508300230608,0.0,0.0
-TiRex,66.29629629629629,62.74382048246822,0.0,0.20884203875396826,0.0,0.0
-TabPFN-TS-3,61.66666666666669,64.3601359782909,0.0,431.5150328579276,0.0,0.0
-FlowState,58.518518518518526,62.649468493586056,0.0,12.472611368300264,0.0,0.0
-Moirai-2.0,55.37037037037037,61.08750954950368,0.0,0.35171731723214283,0.1,0.0
-PatchTST,50.64814814814817,59.71037333425973,1068.4652680383783,0.7892402496428571,0.0,0.0
-TFT,47.77777777777778,55.556509382143545,1003.5120332510221,1.1076982505700976,0.0,0.0
-TabPFN-TS,46.2962962962963,58.432181218600874,0.0,285.2805137923404,0.0,0.0
-Chronos-Bolt,45.18518518518518,58.15816295699815,0.0,0.21284866287857143,0.0,0.0
-Sundial-Base,43.88888888888889,59.21372871831863,0.0,7.874095355196429,0.0,0.0
-DeepAR,38.425925925925924,50.79429174981283,1590.4637105111146,1.558186748969388,0.0,0.0
-CatBoost,31.48148148148148,46.843426009989976,123.37088255733154,0.43462186795918367,0.0,0.0
-LightGBM,26.481481481481485,40.70772252024998,7.053590123430682,0.3469036807346939,0.0,0.0
-AutoARIMA,23.240740740740744,34.821696297938075,0.0,18.324502920714288,0.0,5.0
-Stat. Ensemble,20.09259259259259,22.34504540092107,0.0,140.07917045413043,0.0,5.0
-AutoETS,13.425925925925927,-39.995047645386684,0.0,2.9907604154761906,0.0,15.0
-AutoTheta,11.48148148148148,7.361982676335321,0.0,4.0546638315458425,0.0,0.0
-Seasonal Naive,10.648148148148149,0.0,0.0,0.5176203110585994,0.0,0.0
-Naive,7.222222222222223,-64.9788901369484,0.0,0.43933051720441596,0.0,0.0
-Drift,2.407407407407407,-71.7471743825873,0.0,0.4190869192562794,0.0,0.0

tables/domain_cloud/pairwise_MASE.csv

@@ -1,290 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,Toto-2.0-1B,0.6,0.4,0.8,0.001,-0.011,0.012
-Toto-2.0-2.5B,Toto-2.0-313m,0.8,0.6,0.95,0.012,0.002,0.024
-Toto-2.0-2.5B,Toto-2.0-22m,1.0,1.0,1.0,0.057,0.031,0.088
-Toto-2.0-2.5B,Toto-1.0,0.95,0.85,1.0,0.09,0.05,0.136
-Toto-2.0-2.5B,Chronos-2,0.95,0.85,1.0,0.08,0.048,0.124
-Toto-2.0-2.5B,Toto-2.0-4m,1.0,1.0,1.0,0.105,0.061,0.155
-Toto-2.0-2.5B,TiRex-2,0.95,0.85,1.0,0.123,0.077,0.173
-Toto-2.0-2.5B,TimesFM-2.5,0.95,0.85,1.0,0.114,0.07,0.181
-Toto-2.0-2.5B,TiRex,1.0,1.0,1.0,0.145,0.082,0.223
-Toto-2.0-2.5B,FlowState,0.9,0.75,1.0,0.237,0.125,0.356
-Toto-2.0-2.5B,Moirai-2.0,1.0,1.0,1.0,0.179,0.114,0.268
-Toto-2.0-2.5B,TabPFN-TS-3,0.95,0.85,1.0,0.198,0.107,0.308
-Toto-2.0-2.5B,TFT,1.0,1.0,1.0,0.194,0.136,0.259
-Toto-2.0-2.5B,PatchTST,0.95,0.85,1.0,0.195,0.12,0.276
-Toto-2.0-2.5B,Chronos-Bolt,1.0,1.0,1.0,0.235,0.163,0.308
-Toto-2.0-2.5B,Seasonal Naive,1.0,1.0,1.0,0.471,0.37,0.587
-Toto-2.0-1B,Toto-2.0-2.5B,0.4,0.2,0.6,-0.001,-0.012,0.011
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-313m,0.8,0.6,0.95,0.011,0.001,0.022
-Toto-2.0-1B,Toto-2.0-22m,1.0,1.0,1.0,0.056,0.028,0.092
-Toto-2.0-1B,Toto-1.0,1.0,1.0,1.0,0.089,0.051,0.132
-Toto-2.0-1B,Chronos-2,0.95,0.85,1.0,0.079,0.042,0.127
-Toto-2.0-1B,Toto-2.0-4m,1.0,1.0,1.0,0.104,0.06,0.157
-Toto-2.0-1B,TiRex-2,0.95,0.85,1.0,0.123,0.077,0.175
-Toto-2.0-1B,TimesFM-2.5,0.9,0.75,1.0,0.114,0.068,0.183
-Toto-2.0-1B,TiRex,1.0,1.0,1.0,0.145,0.084,0.223
-Toto-2.0-1B,FlowState,0.9,0.75,1.0,0.236,0.115,0.36
-Toto-2.0-1B,Moirai-2.0,1.0,1.0,1.0,0.178,0.112,0.271
-Toto-2.0-1B,TabPFN-TS-3,0.95,0.85,1.0,0.197,0.101,0.318
-Toto-2.0-1B,TFT,1.0,1.0,1.0,0.193,0.137,0.254
-Toto-2.0-1B,PatchTST,0.95,0.85,1.0,0.194,0.117,0.277
-Toto-2.0-1B,Chronos-Bolt,1.0,1.0,1.0,0.234,0.16,0.311
-Toto-2.0-1B,Seasonal Naive,1.0,1.0,1.0,0.47,0.372,0.586
-Toto-2.0-313m,Toto-2.0-2.5B,0.2,0.05,0.4,-0.012,-0.024,-0.002
-Toto-2.0-313m,Toto-2.0-1B,0.2,0.05,0.4,-0.011,-0.023,-0.001
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,Toto-2.0-22m,1.0,1.0,1.0,0.046,0.025,0.076
-Toto-2.0-313m,Toto-1.0,0.95,0.85,1.0,0.079,0.045,0.121
-Toto-2.0-313m,Chronos-2,0.95,0.85,1.0,0.069,0.033,0.115
-Toto-2.0-313m,Toto-2.0-4m,1.0,1.0,1.0,0.094,0.056,0.144
-Toto-2.0-313m,TiRex-2,0.95,0.85,1.0,0.113,0.073,0.158
-Toto-2.0-313m,TimesFM-2.5,0.95,0.85,1.0,0.104,0.058,0.173
-Toto-2.0-313m,TiRex,1.0,1.0,1.0,0.135,0.076,0.212
-Toto-2.0-313m,FlowState,0.9,0.75,1.0,0.228,0.113,0.349
-Toto-2.0-313m,Moirai-2.0,1.0,1.0,1.0,0.169,0.107,0.26
-Toto-2.0-313m,TabPFN-TS-3,0.95,0.85,1.0,0.189,0.093,0.302
-Toto-2.0-313m,TFT,1.0,1.0,1.0,0.184,0.131,0.249
-Toto-2.0-313m,PatchTST,0.95,0.85,1.0,0.185,0.105,0.268
-Toto-2.0-313m,Chronos-Bolt,1.0,1.0,1.0,0.226,0.157,0.3
-Toto-2.0-313m,Seasonal Naive,1.0,1.0,1.0,0.465,0.364,0.583
-Toto-2.0-22m,Toto-2.0-2.5B,0.0,0.0,0.0,-0.06,-0.096,-0.032
-Toto-2.0-22m,Toto-2.0-1B,0.0,0.0,0.0,-0.059,-0.102,-0.029
-Toto-2.0-22m,Toto-2.0-313m,0.0,0.0,0.0,-0.048,-0.082,-0.026
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,Toto-1.0,0.75,0.55,0.9,0.035,0.012,0.064
-Toto-2.0-22m,Chronos-2,0.85,0.7,1.0,0.025,-0.013,0.052
-Toto-2.0-22m,Toto-2.0-4m,1.0,1.0,1.0,0.051,0.03,0.076
-Toto-2.0-22m,TiRex-2,0.9,0.75,1.0,0.071,0.046,0.096
-Toto-2.0-22m,TimesFM-2.5,0.85,0.699,1.0,0.061,0.016,0.111
-Toto-2.0-22m,TiRex,0.85,0.7,1.0,0.094,0.047,0.149
-Toto-2.0-22m,FlowState,0.9,0.75,1.0,0.191,0.077,0.306
-Toto-2.0-22m,Moirai-2.0,1.0,1.0,1.0,0.13,0.081,0.2
-Toto-2.0-22m,TabPFN-TS-3,0.95,0.85,1.0,0.15,0.058,0.249
-Toto-2.0-22m,TFT,1.0,1.0,1.0,0.145,0.093,0.21
-Toto-2.0-22m,PatchTST,0.9,0.75,1.0,0.146,0.069,0.221
-Toto-2.0-22m,Chronos-Bolt,1.0,1.0,1.0,0.189,0.128,0.252
-Toto-2.0-22m,Seasonal Naive,1.0,1.0,1.0,0.439,0.34,0.551
-Toto-1.0,Toto-2.0-2.5B,0.05,0.0,0.15,-0.099,-0.157,-0.052
-Toto-1.0,Toto-2.0-1B,0.0,0.0,0.0,-0.097,-0.152,-0.053
-Toto-1.0,Toto-2.0-313m,0.05,0.0,0.15,-0.086,-0.138,-0.047
-Toto-1.0,Toto-2.0-22m,0.25,0.1,0.45,-0.036,-0.068,-0.012
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,Chronos-2,0.65,0.45,0.85,-0.011,-0.063,0.027
-Toto-1.0,Toto-2.0-4m,0.7,0.45,0.9,0.016,-0.007,0.04
-Toto-1.0,TiRex-2,0.85,0.7,1.0,0.037,0.014,0.059
-Toto-1.0,TimesFM-2.5,0.7,0.5,0.9,0.027,-0.02,0.072
-Toto-1.0,TiRex,0.8,0.6,0.95,0.061,0.027,0.114
-Toto-1.0,FlowState,0.85,0.7,1.0,0.162,0.041,0.286
-Toto-1.0,Moirai-2.0,0.95,0.85,1.0,0.098,0.052,0.164
-Toto-1.0,TabPFN-TS-3,0.95,0.85,1.0,0.119,0.024,0.226
-Toto-1.0,TFT,0.9,0.75,1.0,0.114,0.071,0.159
-Toto-1.0,PatchTST,0.9,0.75,1.0,0.115,0.034,0.185
-Toto-1.0,Chronos-Bolt,0.9,0.75,1.0,0.159,0.094,0.224
-Toto-1.0,Seasonal Naive,1.0,1.0,1.0,0.419,0.323,0.528
-Chronos-2,Toto-2.0-2.5B,0.05,0.0,0.15,-0.087,-0.141,-0.05
-Chronos-2,Toto-2.0-1B,0.05,0.0,0.15,-0.086,-0.145,-0.044
-Chronos-2,Toto-2.0-313m,0.05,0.0,0.15,-0.074,-0.13,-0.034
-Chronos-2,Toto-2.0-22m,0.15,0.0,0.3,-0.025,-0.055,0.013
-Chronos-2,Toto-1.0,0.35,0.15,0.55,0.011,-0.028,0.059
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,Toto-2.0-4m,0.6,0.35,0.8,0.027,-0.006,0.067
-Chronos-2,TiRex-2,0.7,0.5,0.9,0.047,0.011,0.093
-Chronos-2,TimesFM-2.5,0.7,0.5,0.9,0.038,0.009,0.071
-Chronos-2,TiRex,0.75,0.55,0.95,0.071,0.022,0.128
-Chronos-2,FlowState,0.8,0.6,0.95,0.171,0.067,0.29
-Chronos-2,Moirai-2.0,1.0,1.0,1.0,0.108,0.053,0.168
-Chronos-2,TabPFN-TS-3,0.8,0.6,0.95,0.129,0.052,0.222
-Chronos-2,TFT,0.85,0.699,1.0,0.124,0.065,0.193
-Chronos-2,PatchTST,0.9,0.75,1.0,0.125,0.065,0.189
-Chronos-2,Chronos-Bolt,0.95,0.85,1.0,0.168,0.101,0.231
-Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.425,0.331,0.534
-Toto-2.0-4m,Toto-2.0-2.5B,0.0,0.0,0.0,-0.117,-0.184,-0.065
-Toto-2.0-4m,Toto-2.0-1B,0.0,0.0,0.0,-0.116,-0.187,-0.064
-Toto-2.0-4m,Toto-2.0-313m,0.0,0.0,0.0,-0.104,-0.168,-0.059
-Toto-2.0-4m,Toto-2.0-22m,0.0,0.0,0.0,-0.053,-0.083,-0.031
-Toto-2.0-4m,Toto-1.0,0.3,0.1,0.55,-0.016,-0.042,0.007
-Toto-2.0-4m,Chronos-2,0.4,0.2,0.65,-0.028,-0.072,0.006
-Toto-2.0-4m,Toto-2.0-4m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-4m,TiRex-2,0.85,0.65,1.0,0.021,0.008,0.034
-Toto-2.0-4m,TimesFM-2.5,0.65,0.4,0.85,0.011,-0.032,0.048
-Toto-2.0-4m,TiRex,0.75,0.55,0.9,0.046,0.017,0.083
-Toto-2.0-4m,FlowState,0.85,0.699,1.0,0.148,0.032,0.269
-Toto-2.0-4m,Moirai-2.0,1.0,1.0,1.0,0.083,0.05,0.134
-Toto-2.0-4m,TabPFN-TS-3,0.9,0.75,1.0,0.105,0.014,0.197
-Toto-2.0-4m,TFT,0.9,0.75,1.0,0.1,0.046,0.16
-Toto-2.0-4m,PatchTST,0.85,0.699,1.0,0.101,0.019,0.165
-Toto-2.0-4m,Chronos-Bolt,1.0,1.0,1.0,0.145,0.092,0.201
-Toto-2.0-4m,Seasonal Naive,0.95,0.85,1.0,0.409,0.315,0.516
-TiRex-2,Toto-2.0-2.5B,0.05,0.0,0.15,-0.141,-0.209,-0.084
-TiRex-2,Toto-2.0-1B,0.05,0.0,0.15,-0.14,-0.212,-0.083
-TiRex-2,Toto-2.0-313m,0.05,0.0,0.15,-0.128,-0.188,-0.078
-TiRex-2,Toto-2.0-22m,0.1,0.0,0.25,-0.076,-0.106,-0.049
-TiRex-2,Toto-1.0,0.15,0.0,0.3,-0.038,-0.063,-0.014
-TiRex-2,Chronos-2,0.3,0.1,0.5,-0.05,-0.103,-0.011
-TiRex-2,Toto-2.0-4m,0.15,0.0,0.35,-0.022,-0.035,-0.008
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,TimesFM-2.5,0.6,0.4,0.8,-0.01,-0.061,0.036
-TiRex-2,TiRex,0.65,0.45,0.85,0.025,-0.006,0.072
-TiRex-2,FlowState,0.8,0.6,0.95,0.129,0.009,0.25
-TiRex-2,Moirai-2.0,0.85,0.7,1.0,0.063,0.027,0.121
-TiRex-2,TabPFN-TS-3,0.85,0.7,1.0,0.085,-0.01,0.184
-TiRex-2,TFT,0.8,0.6,0.95,0.08,0.03,0.141
-TiRex-2,PatchTST,0.9,0.75,1.0,0.081,-0.011,0.149
-TiRex-2,Chronos-Bolt,0.95,0.85,1.0,0.127,0.072,0.184
-TiRex-2,Seasonal Naive,0.95,0.85,1.0,0.397,0.293,0.51
-TimesFM-2.5,Toto-2.0-2.5B,0.05,0.0,0.15,-0.129,-0.22,-0.075
-TimesFM-2.5,Toto-2.0-1B,0.1,0.0,0.25,-0.128,-0.224,-0.073
-TimesFM-2.5,Toto-2.0-313m,0.05,0.0,0.15,-0.116,-0.209,-0.061
-TimesFM-2.5,Toto-2.0-22m,0.15,0.0,0.301,-0.065,-0.125,-0.016
-TimesFM-2.5,Toto-1.0,0.3,0.1,0.5,-0.028,-0.078,0.02
-TimesFM-2.5,Chronos-2,0.3,0.1,0.5,-0.039,-0.077,-0.009
-TimesFM-2.5,Toto-2.0-4m,0.35,0.15,0.6,-0.011,-0.05,0.031
-TimesFM-2.5,TiRex-2,0.4,0.2,0.6,0.01,-0.037,0.058
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,TiRex,0.65,0.45,0.85,0.035,-0.0,0.077
-TimesFM-2.5,FlowState,0.7,0.5,0.9,0.138,0.03,0.267
-TimesFM-2.5,Moirai-2.0,0.9,0.75,1.0,0.073,0.035,0.115
-TimesFM-2.5,TabPFN-TS-3,0.75,0.55,0.95,0.095,0.024,0.186
-TimesFM-2.5,TFT,0.8,0.6,0.95,0.09,0.017,0.163
-TimesFM-2.5,PatchTST,0.8,0.649,0.95,0.091,0.037,0.142
-TimesFM-2.5,Chronos-Bolt,0.85,0.65,1.0,0.136,0.068,0.199
-TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.403,0.318,0.501
-TiRex,Toto-2.0-2.5B,0.0,0.0,0.0,-0.17,-0.287,-0.09
-TiRex,Toto-2.0-1B,0.0,0.0,0.0,-0.169,-0.287,-0.092
-TiRex,Toto-2.0-313m,0.0,0.0,0.0,-0.157,-0.27,-0.083
-TiRex,Toto-2.0-22m,0.15,0.0,0.3,-0.104,-0.176,-0.05
-TiRex,Toto-1.0,0.2,0.05,0.4,-0.065,-0.129,-0.028
-TiRex,Chronos-2,0.25,0.05,0.45,-0.077,-0.146,-0.022
-TiRex,Toto-2.0-4m,0.25,0.1,0.45,-0.048,-0.091,-0.017
-TiRex,TiRex-2,0.35,0.15,0.55,-0.026,-0.077,0.006
-TiRex,TimesFM-2.5,0.35,0.15,0.55,-0.036,-0.083,0.0
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,FlowState,0.65,0.45,0.85,0.107,-0.02,0.236
-TiRex,Moirai-2.0,0.8,0.6,0.95,0.039,0.014,0.065
-TiRex,TabPFN-TS-3,0.85,0.7,1.0,0.062,-0.03,0.149
-TiRex,TFT,0.8,0.6,0.95,0.056,-0.02,0.121
-TiRex,PatchTST,0.85,0.7,1.0,0.058,-0.029,0.118
-TiRex,Chronos-Bolt,0.75,0.55,0.9,0.104,0.038,0.166
-TiRex,Seasonal Naive,1.0,1.0,1.0,0.381,0.295,0.476
-FlowState,Toto-2.0-2.5B,0.1,0.0,0.25,-0.31,-0.554,-0.142
-FlowState,Toto-2.0-1B,0.1,0.0,0.25,-0.309,-0.563,-0.131
-FlowState,Toto-2.0-313m,0.1,0.0,0.25,-0.295,-0.536,-0.128
-FlowState,Toto-2.0-22m,0.1,0.0,0.25,-0.236,-0.442,-0.084
-FlowState,Toto-1.0,0.15,0.0,0.3,-0.193,-0.401,-0.043
-FlowState,Chronos-2,0.2,0.05,0.4,-0.206,-0.408,-0.072
-FlowState,Toto-2.0-4m,0.15,0.0,0.301,-0.173,-0.368,-0.033
-FlowState,TiRex-2,0.2,0.05,0.4,-0.149,-0.333,-0.009
-FlowState,TimesFM-2.5,0.3,0.1,0.5,-0.16,-0.363,-0.031
-FlowState,TiRex,0.35,0.15,0.55,-0.12,-0.308,0.02
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,Moirai-2.0,0.4,0.2,0.6,-0.076,-0.251,0.058
-FlowState,TabPFN-TS-3,0.5,0.3,0.7,-0.051,-0.155,0.045
-FlowState,TFT,0.55,0.3,0.75,-0.057,-0.249,0.076
-FlowState,PatchTST,0.5,0.3,0.7,-0.055,-0.227,0.056
-FlowState,Chronos-Bolt,0.5,0.3,0.7,-0.003,-0.136,0.112
-FlowState,Seasonal Naive,0.9,0.75,1.0,0.307,0.147,0.442
-Moirai-2.0,Toto-2.0-2.5B,0.0,0.0,0.0,-0.218,-0.367,-0.129
-Moirai-2.0,Toto-2.0-1B,0.0,0.0,0.0,-0.217,-0.371,-0.126
-Moirai-2.0,Toto-2.0-313m,0.0,0.0,0.0,-0.204,-0.352,-0.12
-Moirai-2.0,Toto-2.0-22m,0.0,0.0,0.0,-0.149,-0.25,-0.088
-Moirai-2.0,Toto-1.0,0.05,0.0,0.15,-0.109,-0.196,-0.055
-Moirai-2.0,Chronos-2,0.0,0.0,0.0,-0.121,-0.202,-0.056
-Moirai-2.0,Toto-2.0-4m,0.0,0.0,0.0,-0.091,-0.155,-0.052
-Moirai-2.0,TiRex-2,0.15,0.0,0.3,-0.068,-0.137,-0.027
-Moirai-2.0,TimesFM-2.5,0.1,0.0,0.25,-0.078,-0.13,-0.036
-Moirai-2.0,TiRex,0.2,0.05,0.4,-0.041,-0.07,-0.015
-Moirai-2.0,FlowState,0.6,0.4,0.8,0.071,-0.062,0.201
-Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
-Moirai-2.0,TabPFN-TS-3,0.65,0.45,0.85,0.024,-0.061,0.104
-Moirai-2.0,TFT,0.5,0.3,0.7,0.018,-0.08,0.104
-Moirai-2.0,PatchTST,0.6,0.4,0.8,0.019,-0.064,0.081
-Moirai-2.0,Chronos-Bolt,0.65,0.425,0.825,0.068,-0.002,0.135
-Moirai-2.0,Seasonal Naive,0.95,0.85,1.0,0.356,0.268,0.451
-TabPFN-TS-3,Toto-2.0-2.5B,0.05,0.0,0.15,-0.247,-0.446,-0.12
-TabPFN-TS-3,Toto-2.0-1B,0.05,0.0,0.15,-0.246,-0.466,-0.113
-TabPFN-TS-3,Toto-2.0-313m,0.05,0.0,0.15,-0.233,-0.432,-0.103
-TabPFN-TS-3,Toto-2.0-22m,0.05,0.0,0.15,-0.177,-0.331,-0.061
-TabPFN-TS-3,Toto-1.0,0.05,0.0,0.15,-0.135,-0.291,-0.025
-TabPFN-TS-3,Chronos-2,0.2,0.05,0.4,-0.148,-0.286,-0.055
-TabPFN-TS-3,Toto-2.0-4m,0.1,0.0,0.25,-0.117,-0.245,-0.014
-TabPFN-TS-3,TiRex-2,0.15,0.0,0.3,-0.093,-0.225,0.01
-TabPFN-TS-3,TimesFM-2.5,0.25,0.05,0.45,-0.104,-0.229,-0.025
-TabPFN-TS-3,TiRex,0.15,0.0,0.3,-0.066,-0.176,0.03
-TabPFN-TS-3,FlowState,0.5,0.3,0.7,0.048,-0.047,0.134
-TabPFN-TS-3,Moirai-2.0,0.35,0.15,0.55,-0.024,-0.116,0.057
-TabPFN-TS-3,TabPFN-TS-3,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS-3,TFT,0.6,0.4,0.8,-0.006,-0.164,0.102
-TabPFN-TS-3,PatchTST,0.45,0.25,0.65,-0.004,-0.118,0.077
-TabPFN-TS-3,Chronos-Bolt,0.45,0.25,0.65,0.045,-0.057,0.144
-TabPFN-TS-3,Seasonal Naive,0.95,0.85,1.0,0.34,0.224,0.444
-TFT,Toto-2.0-2.5B,0.0,0.0,0.0,-0.24,-0.35,-0.157
-TFT,Toto-2.0-1B,0.0,0.0,0.0,-0.239,-0.34,-0.159
-TFT,Toto-2.0-313m,0.0,0.0,0.0,-0.226,-0.331,-0.15
-TFT,Toto-2.0-22m,0.0,0.0,0.0,-0.17,-0.266,-0.102
-TFT,Toto-1.0,0.1,0.0,0.25,-0.129,-0.188,-0.076
-TFT,Chronos-2,0.15,0.0,0.301,-0.141,-0.239,-0.069
-TFT,Toto-2.0-4m,0.1,0.0,0.25,-0.111,-0.191,-0.048
-TFT,TiRex-2,0.2,0.05,0.4,-0.087,-0.164,-0.03
-TFT,TimesFM-2.5,0.2,0.05,0.4,-0.098,-0.194,-0.017
-TFT,TiRex,0.2,0.05,0.4,-0.06,-0.138,0.02
-TFT,FlowState,0.45,0.25,0.7,0.053,-0.082,0.2
-TFT,Moirai-2.0,0.5,0.3,0.7,-0.018,-0.117,0.074
-TFT,TabPFN-TS-3,0.4,0.2,0.6,0.006,-0.113,0.141
-TFT,TFT,0.5,0.5,0.5,0.0,0.0,0.0
-TFT,PatchTST,0.575,0.375,0.8,0.001,-0.11,0.092
-TFT,Chronos-Bolt,0.55,0.35,0.75,0.051,-0.051,0.135
-TFT,Seasonal Naive,0.925,0.824,1.0,0.344,0.234,0.473
-PatchTST,Toto-2.0-2.5B,0.05,0.0,0.15,-0.242,-0.381,-0.137
-PatchTST,Toto-2.0-1B,0.05,0.0,0.15,-0.241,-0.383,-0.132
-PatchTST,Toto-2.0-313m,0.05,0.0,0.15,-0.228,-0.366,-0.118
-PatchTST,Toto-2.0-22m,0.1,0.0,0.25,-0.172,-0.283,-0.074
-PatchTST,Toto-1.0,0.1,0.0,0.25,-0.131,-0.227,-0.035
-PatchTST,Chronos-2,0.1,0.0,0.25,-0.143,-0.234,-0.07
-PatchTST,Toto-2.0-4m,0.15,0.0,0.301,-0.112,-0.197,-0.02
-PatchTST,TiRex-2,0.1,0.0,0.25,-0.089,-0.174,0.01
-PatchTST,TimesFM-2.5,0.2,0.05,0.351,-0.1,-0.166,-0.038
-PatchTST,TiRex,0.15,0.0,0.3,-0.061,-0.134,0.028
-PatchTST,FlowState,0.5,0.3,0.7,0.052,-0.059,0.185
-PatchTST,Moirai-2.0,0.4,0.2,0.6,-0.02,-0.089,0.06
-PatchTST,TabPFN-TS-3,0.55,0.35,0.75,0.004,-0.084,0.105
-PatchTST,TFT,0.425,0.2,0.625,-0.001,-0.101,0.099
-PatchTST,PatchTST,0.5,0.5,0.5,0.0,0.0,0.0
-PatchTST,Chronos-Bolt,0.45,0.2,0.65,0.049,-0.039,0.137
-PatchTST,Seasonal Naive,0.9,0.775,1.0,0.343,0.237,0.456
-Chronos-Bolt,Toto-2.0-2.5B,0.0,0.0,0.0,-0.307,-0.445,-0.194
-Chronos-Bolt,Toto-2.0-1B,0.0,0.0,0.0,-0.305,-0.452,-0.191
-Chronos-Bolt,Toto-2.0-313m,0.0,0.0,0.0,-0.291,-0.429,-0.186
-Chronos-Bolt,Toto-2.0-22m,0.0,0.0,0.0,-0.232,-0.336,-0.147
-Chronos-Bolt,Toto-1.0,0.1,0.0,0.25,-0.189,-0.288,-0.104
-Chronos-Bolt,Chronos-2,0.05,0.0,0.15,-0.202,-0.3,-0.112
-Chronos-Bolt,Toto-2.0-4m,0.0,0.0,0.0,-0.17,-0.252,-0.101
-Chronos-Bolt,TiRex-2,0.05,0.0,0.15,-0.145,-0.225,-0.077
-Chronos-Bolt,TimesFM-2.5,0.15,0.0,0.35,-0.157,-0.248,-0.073
-Chronos-Bolt,TiRex,0.25,0.1,0.45,-0.116,-0.198,-0.039
-Chronos-Bolt,FlowState,0.5,0.3,0.7,0.003,-0.127,0.12
-Chronos-Bolt,Moirai-2.0,0.35,0.175,0.575,-0.073,-0.156,0.002
-Chronos-Bolt,TabPFN-TS-3,0.55,0.35,0.75,-0.048,-0.169,0.054
-Chronos-Bolt,TFT,0.45,0.25,0.65,-0.053,-0.156,0.049
-Chronos-Bolt,PatchTST,0.55,0.35,0.8,-0.052,-0.159,0.037
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,Seasonal Naive,0.85,0.7,1.0,0.309,0.185,0.434
-Seasonal Naive,Toto-2.0-2.5B,0.0,0.0,0.0,-0.891,-1.422,-0.588
-Seasonal Naive,Toto-2.0-1B,0.0,0.0,0.0,-0.889,-1.413,-0.593
-Seasonal Naive,Toto-2.0-313m,0.0,0.0,0.0,-0.869,-1.396,-0.571
-Seasonal Naive,Toto-2.0-22m,0.0,0.0,0.0,-0.783,-1.229,-0.515
-Seasonal Naive,Toto-1.0,0.0,0.0,0.0,-0.721,-1.121,-0.477
-Seasonal Naive,Chronos-2,0.0,0.0,0.0,-0.74,-1.148,-0.496
-Seasonal Naive,Toto-2.0-4m,0.05,0.0,0.15,-0.693,-1.065,-0.459
-Seasonal Naive,TiRex-2,0.05,0.0,0.15,-0.657,-1.043,-0.414
-Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-0.674,-1.003,-0.466
-Seasonal Naive,TiRex,0.0,0.0,0.0,-0.615,-0.909,-0.418
-Seasonal Naive,FlowState,0.1,0.0,0.25,-0.443,-0.793,-0.172
-Seasonal Naive,Moirai-2.0,0.05,0.0,0.15,-0.552,-0.822,-0.365
-Seasonal Naive,TabPFN-TS-3,0.05,0.0,0.15,-0.516,-0.797,-0.289
-Seasonal Naive,TFT,0.075,0.0,0.176,-0.524,-0.897,-0.305
-Seasonal Naive,PatchTST,0.1,0.0,0.225,-0.522,-0.838,-0.31
-Seasonal Naive,Chronos-Bolt,0.15,0.0,0.3,-0.447,-0.766,-0.228
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_cloud/pairwise_SQL.csv

@@ -1,290 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,Toto-2.0-1B,0.7,0.5,0.851,0.0,-0.014,0.012
-Toto-2.0-2.5B,Toto-2.0-313m,0.8,0.6,0.95,0.007,-0.005,0.02
-Toto-2.0-2.5B,Toto-2.0-22m,1.0,1.0,1.0,0.057,0.035,0.084
-Toto-2.0-2.5B,Toto-1.0,1.0,1.0,1.0,0.098,0.06,0.139
-Toto-2.0-2.5B,Chronos-2,0.95,0.85,1.0,0.076,0.052,0.104
-Toto-2.0-2.5B,Toto-2.0-4m,1.0,1.0,1.0,0.111,0.069,0.154
-Toto-2.0-2.5B,TiRex-2,1.0,1.0,1.0,0.131,0.084,0.178
-Toto-2.0-2.5B,TimesFM-2.5,1.0,1.0,1.0,0.123,0.081,0.177
-Toto-2.0-2.5B,TiRex,1.0,1.0,1.0,0.148,0.088,0.214
-Toto-2.0-2.5B,TabPFN-TS-3,0.95,0.85,1.0,0.179,0.107,0.265
-Toto-2.0-2.5B,FlowState,0.9,0.75,1.0,0.244,0.135,0.358
-Toto-2.0-2.5B,Moirai-2.0,1.0,1.0,1.0,0.199,0.13,0.271
-Toto-2.0-2.5B,TFT,1.0,1.0,1.0,0.241,0.165,0.317
-Toto-2.0-2.5B,PatchTST,0.95,0.85,1.0,0.231,0.156,0.306
-Toto-2.0-2.5B,Chronos-Bolt,1.0,1.0,1.0,0.262,0.194,0.323
-Toto-2.0-2.5B,Seasonal Naive,1.0,1.0,1.0,0.667,0.566,0.758
-Toto-2.0-1B,Toto-2.0-2.5B,0.3,0.149,0.5,-0.0,-0.012,0.014
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-313m,0.8,0.6,0.95,0.007,-0.001,0.018
-Toto-2.0-1B,Toto-2.0-22m,1.0,1.0,1.0,0.057,0.031,0.089
-Toto-2.0-1B,Toto-1.0,1.0,1.0,1.0,0.098,0.058,0.137
-Toto-2.0-1B,Chronos-2,0.95,0.85,1.0,0.076,0.045,0.113
-Toto-2.0-1B,Toto-2.0-4m,1.0,1.0,1.0,0.111,0.067,0.159
-Toto-2.0-1B,TiRex-2,0.95,0.85,1.0,0.131,0.083,0.181
-Toto-2.0-1B,TimesFM-2.5,1.0,1.0,1.0,0.123,0.079,0.184
-Toto-2.0-1B,TiRex,1.0,1.0,1.0,0.148,0.088,0.217
-Toto-2.0-1B,TabPFN-TS-3,0.95,0.85,1.0,0.179,0.102,0.272
-Toto-2.0-1B,FlowState,0.95,0.85,1.0,0.244,0.129,0.364
-Toto-2.0-1B,Moirai-2.0,1.0,1.0,1.0,0.199,0.129,0.277
-Toto-2.0-1B,TFT,1.0,1.0,1.0,0.241,0.163,0.314
-Toto-2.0-1B,PatchTST,0.95,0.85,1.0,0.231,0.149,0.311
-Toto-2.0-1B,Chronos-Bolt,1.0,1.0,1.0,0.262,0.192,0.328
-Toto-2.0-1B,Seasonal Naive,1.0,1.0,1.0,0.667,0.566,0.759
-Toto-2.0-313m,Toto-2.0-2.5B,0.2,0.05,0.4,-0.007,-0.021,0.005
-Toto-2.0-313m,Toto-2.0-1B,0.2,0.05,0.4,-0.007,-0.018,0.001
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,Toto-2.0-22m,1.0,1.0,1.0,0.05,0.03,0.076
-Toto-2.0-313m,Toto-1.0,1.0,1.0,1.0,0.091,0.055,0.129
-Toto-2.0-313m,Chronos-2,0.95,0.85,1.0,0.069,0.038,0.106
-Toto-2.0-313m,Toto-2.0-4m,1.0,1.0,1.0,0.104,0.064,0.149
-Toto-2.0-313m,TiRex-2,0.95,0.85,1.0,0.124,0.08,0.171
-Toto-2.0-313m,TimesFM-2.5,0.95,0.85,1.0,0.117,0.072,0.179
-Toto-2.0-313m,TiRex,1.0,1.0,1.0,0.142,0.084,0.212
-Toto-2.0-313m,TabPFN-TS-3,0.95,0.85,1.0,0.173,0.093,0.266
-Toto-2.0-313m,FlowState,0.95,0.85,1.0,0.238,0.125,0.356
-Toto-2.0-313m,Moirai-2.0,1.0,1.0,1.0,0.193,0.124,0.271
-Toto-2.0-313m,TFT,1.0,1.0,1.0,0.235,0.16,0.307
-Toto-2.0-313m,PatchTST,0.95,0.85,1.0,0.225,0.146,0.305
-Toto-2.0-313m,Chronos-Bolt,1.0,1.0,1.0,0.256,0.19,0.318
-Toto-2.0-313m,Seasonal Naive,1.0,1.0,1.0,0.664,0.561,0.758
-Toto-2.0-22m,Toto-2.0-2.5B,0.0,0.0,0.0,-0.061,-0.091,-0.036
-Toto-2.0-22m,Toto-2.0-1B,0.0,0.0,0.0,-0.061,-0.098,-0.032
-Toto-2.0-22m,Toto-2.0-313m,0.0,0.0,0.0,-0.053,-0.082,-0.031
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,Toto-1.0,0.85,0.7,1.0,0.043,0.02,0.071
-Toto-2.0-22m,Chronos-2,0.85,0.7,1.0,0.02,-0.019,0.047
-Toto-2.0-22m,Toto-2.0-4m,1.0,1.0,1.0,0.057,0.034,0.082
-Toto-2.0-22m,TiRex-2,0.95,0.85,1.0,0.078,0.049,0.106
-Toto-2.0-22m,TimesFM-2.5,0.85,0.699,1.0,0.07,0.023,0.119
-Toto-2.0-22m,TiRex,0.95,0.85,1.0,0.097,0.053,0.149
-Toto-2.0-22m,TabPFN-TS-3,0.95,0.85,1.0,0.129,0.048,0.211
-Toto-2.0-22m,FlowState,0.9,0.75,1.0,0.198,0.085,0.312
-Toto-2.0-22m,Moirai-2.0,1.0,1.0,1.0,0.15,0.094,0.211
-Toto-2.0-22m,TFT,1.0,1.0,1.0,0.195,0.126,0.267
-Toto-2.0-22m,PatchTST,0.95,0.85,1.0,0.184,0.101,0.256
-Toto-2.0-22m,Chronos-Bolt,1.0,1.0,1.0,0.217,0.158,0.27
-Toto-2.0-22m,Seasonal Naive,1.0,1.0,1.0,0.646,0.539,0.743
-Toto-1.0,Toto-2.0-2.5B,0.0,0.0,0.0,-0.109,-0.162,-0.064
-Toto-1.0,Toto-2.0-1B,0.0,0.0,0.0,-0.108,-0.159,-0.062
-Toto-1.0,Toto-2.0-313m,0.0,0.0,0.0,-0.1,-0.148,-0.058
-Toto-1.0,Toto-2.0-22m,0.15,0.0,0.3,-0.045,-0.076,-0.02
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,Chronos-2,0.6,0.4,0.8,-0.024,-0.08,0.018
-Toto-1.0,Toto-2.0-4m,0.7,0.5,0.9,0.014,-0.008,0.036
-Toto-1.0,TiRex-2,0.85,0.7,1.0,0.037,0.012,0.06
-Toto-1.0,TimesFM-2.5,0.75,0.55,0.95,0.028,-0.025,0.076
-Toto-1.0,TiRex,0.8,0.6,0.95,0.056,0.022,0.104
-Toto-1.0,TabPFN-TS-3,0.95,0.85,1.0,0.09,0.005,0.175
-Toto-1.0,FlowState,0.85,0.7,1.0,0.162,0.04,0.284
-Toto-1.0,Moirai-2.0,0.95,0.85,1.0,0.112,0.064,0.169
-Toto-1.0,TFT,0.95,0.85,1.0,0.158,0.096,0.217
-Toto-1.0,PatchTST,0.9,0.75,1.0,0.148,0.055,0.221
-Toto-1.0,Chronos-Bolt,0.95,0.85,1.0,0.182,0.124,0.236
-Toto-1.0,Seasonal Naive,1.0,1.0,1.0,0.631,0.52,0.73
-Chronos-2,Toto-2.0-2.5B,0.05,0.0,0.15,-0.082,-0.116,-0.055
-Chronos-2,Toto-2.0-1B,0.05,0.0,0.15,-0.082,-0.127,-0.047
-Chronos-2,Toto-2.0-313m,0.05,0.0,0.15,-0.074,-0.119,-0.039
-Chronos-2,Toto-2.0-22m,0.15,0.0,0.3,-0.02,-0.049,0.019
-Chronos-2,Toto-1.0,0.4,0.2,0.6,0.024,-0.018,0.074
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,Toto-2.0-4m,0.6,0.35,0.8,0.038,0.001,0.085
-Chronos-2,TiRex-2,0.65,0.4,0.85,0.059,0.017,0.111
-Chronos-2,TimesFM-2.5,0.75,0.55,0.9,0.051,0.017,0.09
-Chronos-2,TiRex,0.75,0.55,0.9,0.078,0.024,0.139
-Chronos-2,TabPFN-TS-3,0.85,0.7,1.0,0.111,0.053,0.183
-Chronos-2,FlowState,0.85,0.65,1.0,0.182,0.078,0.296
-Chronos-2,Moirai-2.0,1.0,1.0,1.0,0.133,0.069,0.2
-Chronos-2,TFT,0.9,0.75,1.0,0.178,0.097,0.258
-Chronos-2,PatchTST,0.85,0.7,1.0,0.168,0.103,0.231
-Chronos-2,Chronos-Bolt,1.0,1.0,1.0,0.201,0.134,0.261
-Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.639,0.533,0.735
-Toto-2.0-4m,Toto-2.0-2.5B,0.0,0.0,0.0,-0.125,-0.182,-0.074
-Toto-2.0-4m,Toto-2.0-1B,0.0,0.0,0.0,-0.125,-0.189,-0.072
-Toto-2.0-4m,Toto-2.0-313m,0.0,0.0,0.0,-0.116,-0.175,-0.069
-Toto-2.0-4m,Toto-2.0-22m,0.0,0.0,0.0,-0.06,-0.089,-0.035
-Toto-2.0-4m,Toto-1.0,0.3,0.1,0.5,-0.015,-0.037,0.008
-Toto-2.0-4m,Chronos-2,0.4,0.2,0.65,-0.039,-0.093,-0.001
-Toto-2.0-4m,Toto-2.0-4m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-4m,TiRex-2,0.8,0.6,0.95,0.022,0.009,0.035
-Toto-2.0-4m,TimesFM-2.5,0.65,0.4,0.85,0.014,-0.039,0.056
-Toto-2.0-4m,TiRex,0.75,0.55,0.9,0.042,0.015,0.077
-Toto-2.0-4m,TabPFN-TS-3,0.85,0.7,1.0,0.076,-0.009,0.147
-Toto-2.0-4m,FlowState,0.9,0.75,1.0,0.15,0.028,0.27
-Toto-2.0-4m,Moirai-2.0,1.0,1.0,1.0,0.099,0.061,0.145
-Toto-2.0-4m,TFT,0.9,0.75,1.0,0.146,0.077,0.211
-Toto-2.0-4m,PatchTST,0.9,0.75,1.0,0.135,0.047,0.204
-Toto-2.0-4m,Chronos-Bolt,1.0,1.0,1.0,0.17,0.12,0.218
-Toto-2.0-4m,Seasonal Naive,1.0,1.0,1.0,0.625,0.515,0.726
-TiRex-2,Toto-2.0-2.5B,0.0,0.0,0.0,-0.151,-0.216,-0.092
-TiRex-2,Toto-2.0-1B,0.05,0.0,0.15,-0.15,-0.22,-0.09
-TiRex-2,Toto-2.0-313m,0.05,0.0,0.15,-0.142,-0.206,-0.087
-TiRex-2,Toto-2.0-22m,0.05,0.0,0.15,-0.085,-0.119,-0.051
-TiRex-2,Toto-1.0,0.15,0.0,0.3,-0.038,-0.064,-0.012
-TiRex-2,Chronos-2,0.35,0.15,0.6,-0.063,-0.125,-0.017
-TiRex-2,Toto-2.0-4m,0.2,0.05,0.4,-0.023,-0.037,-0.009
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,TimesFM-2.5,0.55,0.349,0.75,-0.009,-0.07,0.04
-TiRex-2,TiRex,0.65,0.45,0.85,0.02,-0.01,0.064
-TiRex-2,TabPFN-TS-3,0.85,0.7,1.0,0.055,-0.036,0.135
-TiRex-2,FlowState,0.85,0.699,1.0,0.13,0.007,0.247
-TiRex-2,Moirai-2.0,0.9,0.75,1.0,0.078,0.043,0.128
-TiRex-2,TFT,0.85,0.7,0.95,0.127,0.064,0.19
-TiRex-2,PatchTST,0.95,0.85,1.0,0.115,0.021,0.184
-TiRex-2,Chronos-Bolt,0.95,0.85,1.0,0.151,0.106,0.197
-TiRex-2,Seasonal Naive,1.0,1.0,1.0,0.617,0.505,0.72
-TimesFM-2.5,Toto-2.0-2.5B,0.0,0.0,0.0,-0.141,-0.216,-0.088
-TimesFM-2.5,Toto-2.0-1B,0.0,0.0,0.0,-0.141,-0.226,-0.086
-TimesFM-2.5,Toto-2.0-313m,0.05,0.0,0.15,-0.132,-0.218,-0.078
-TimesFM-2.5,Toto-2.0-22m,0.15,0.0,0.301,-0.075,-0.136,-0.024
-TimesFM-2.5,Toto-1.0,0.25,0.05,0.45,-0.029,-0.082,0.024
-TimesFM-2.5,Chronos-2,0.25,0.1,0.45,-0.054,-0.099,-0.017
-TimesFM-2.5,Toto-2.0-4m,0.35,0.15,0.6,-0.014,-0.059,0.038
-TimesFM-2.5,TiRex-2,0.45,0.25,0.651,0.009,-0.041,0.065
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,TiRex,0.6,0.4,0.8,0.028,-0.014,0.08
-TimesFM-2.5,TabPFN-TS-3,0.75,0.55,0.95,0.063,0.005,0.129
-TimesFM-2.5,FlowState,0.85,0.7,1.0,0.138,0.034,0.263
-TimesFM-2.5,Moirai-2.0,0.9,0.75,1.0,0.086,0.038,0.143
-TimesFM-2.5,TFT,0.8,0.6,0.95,0.134,0.04,0.217
-TimesFM-2.5,PatchTST,0.8,0.649,0.95,0.123,0.058,0.187
-TimesFM-2.5,Chronos-Bolt,0.9,0.75,1.0,0.158,0.095,0.217
-TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.62,0.519,0.713
-TiRex,Toto-2.0-2.5B,0.0,0.0,0.0,-0.174,-0.273,-0.097
-TiRex,Toto-2.0-1B,0.0,0.0,0.0,-0.174,-0.277,-0.096
-TiRex,Toto-2.0-313m,0.0,0.0,0.0,-0.166,-0.27,-0.091
-TiRex,Toto-2.0-22m,0.05,0.0,0.15,-0.107,-0.176,-0.056
-TiRex,Toto-1.0,0.2,0.05,0.4,-0.059,-0.116,-0.023
-TiRex,Chronos-2,0.25,0.1,0.45,-0.085,-0.162,-0.025
-TiRex,Toto-2.0-4m,0.25,0.1,0.45,-0.044,-0.083,-0.015
-TiRex,TiRex-2,0.35,0.15,0.55,-0.02,-0.068,0.01
-TiRex,TimesFM-2.5,0.4,0.2,0.6,-0.029,-0.086,0.013
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,TabPFN-TS-3,0.8,0.6,0.95,0.036,-0.056,0.102
-TiRex,FlowState,0.7,0.5,0.9,0.112,-0.021,0.241
-TiRex,Moirai-2.0,0.85,0.7,1.0,0.059,0.03,0.09
-TiRex,TFT,0.8,0.6,0.95,0.109,0.017,0.181
-TiRex,PatchTST,0.8,0.6,0.95,0.097,-0.003,0.171
-TiRex,Chronos-Bolt,0.9,0.75,1.0,0.133,0.073,0.186
-TiRex,Seasonal Naive,1.0,1.0,1.0,0.609,0.499,0.709
-TabPFN-TS-3,Toto-2.0-2.5B,0.05,0.0,0.15,-0.218,-0.361,-0.12
-TabPFN-TS-3,Toto-2.0-1B,0.05,0.0,0.15,-0.218,-0.374,-0.114
-TabPFN-TS-3,Toto-2.0-313m,0.05,0.0,0.15,-0.209,-0.363,-0.103
-TabPFN-TS-3,Toto-2.0-22m,0.05,0.0,0.15,-0.148,-0.267,-0.05
-TabPFN-TS-3,Toto-1.0,0.05,0.0,0.15,-0.098,-0.212,-0.005
-TabPFN-TS-3,Chronos-2,0.15,0.0,0.3,-0.125,-0.223,-0.057
-TabPFN-TS-3,Toto-2.0-4m,0.15,0.0,0.3,-0.083,-0.172,0.009
-TabPFN-TS-3,TiRex-2,0.15,0.0,0.3,-0.058,-0.156,0.035
-TabPFN-TS-3,TimesFM-2.5,0.25,0.05,0.45,-0.067,-0.148,-0.006
-TabPFN-TS-3,TiRex,0.2,0.05,0.4,-0.037,-0.113,0.053
-TabPFN-TS-3,TabPFN-TS-3,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS-3,FlowState,0.5,0.3,0.7,0.08,-0.032,0.187
-TabPFN-TS-3,Moirai-2.0,0.45,0.25,0.65,0.024,-0.037,0.104
-TabPFN-TS-3,TFT,0.7,0.5,0.9,0.076,-0.051,0.174
-TabPFN-TS-3,PatchTST,0.7,0.5,0.9,0.064,-0.012,0.126
-TabPFN-TS-3,Chronos-Bolt,0.65,0.4,0.85,0.101,0.008,0.193
-TabPFN-TS-3,Seasonal Naive,1.0,1.0,1.0,0.594,0.486,0.694
-FlowState,Toto-2.0-2.5B,0.1,0.0,0.25,-0.323,-0.558,-0.156
-FlowState,Toto-2.0-1B,0.05,0.0,0.15,-0.323,-0.571,-0.148
-FlowState,Toto-2.0-313m,0.05,0.0,0.15,-0.313,-0.553,-0.142
-FlowState,Toto-2.0-22m,0.1,0.0,0.25,-0.247,-0.453,-0.093
-FlowState,Toto-1.0,0.15,0.0,0.3,-0.193,-0.397,-0.041
-FlowState,Chronos-2,0.15,0.0,0.35,-0.222,-0.421,-0.084
-FlowState,Toto-2.0-4m,0.1,0.0,0.25,-0.176,-0.37,-0.029
-FlowState,TiRex-2,0.15,0.0,0.301,-0.15,-0.328,-0.007
-FlowState,TimesFM-2.5,0.15,0.0,0.3,-0.16,-0.356,-0.035
-FlowState,TiRex,0.3,0.1,0.5,-0.127,-0.318,0.02
-FlowState,TabPFN-TS-3,0.5,0.3,0.7,-0.086,-0.23,0.031
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,Moirai-2.0,0.4,0.2,0.6,-0.06,-0.225,0.076
-FlowState,TFT,0.55,0.3,0.75,-0.004,-0.165,0.115
-FlowState,PatchTST,0.5,0.3,0.7,-0.017,-0.152,0.083
-FlowState,Chronos-Bolt,0.55,0.35,0.75,0.023,-0.108,0.139
-FlowState,Seasonal Naive,0.95,0.85,1.0,0.559,0.424,0.672
-Moirai-2.0,Toto-2.0-2.5B,0.0,0.0,0.0,-0.248,-0.371,-0.15
-Moirai-2.0,Toto-2.0-1B,0.0,0.0,0.0,-0.248,-0.383,-0.148
-Moirai-2.0,Toto-2.0-313m,0.0,0.0,0.0,-0.239,-0.371,-0.142
-Moirai-2.0,Toto-2.0-22m,0.0,0.0,0.0,-0.176,-0.267,-0.104
-Moirai-2.0,Toto-1.0,0.05,0.0,0.15,-0.126,-0.203,-0.068
-Moirai-2.0,Chronos-2,0.0,0.0,0.0,-0.153,-0.249,-0.074
-Moirai-2.0,Toto-2.0-4m,0.0,0.0,0.0,-0.109,-0.169,-0.065
-Moirai-2.0,TiRex-2,0.1,0.0,0.25,-0.085,-0.146,-0.045
-Moirai-2.0,TimesFM-2.5,0.1,0.0,0.25,-0.094,-0.167,-0.039
-Moirai-2.0,TiRex,0.15,0.0,0.3,-0.063,-0.099,-0.03
-Moirai-2.0,TabPFN-TS-3,0.55,0.35,0.75,-0.025,-0.116,0.035
-Moirai-2.0,FlowState,0.6,0.4,0.8,0.057,-0.083,0.184
-Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
-Moirai-2.0,TFT,0.65,0.4,0.85,0.053,-0.052,0.142
-Moirai-2.0,PatchTST,0.65,0.45,0.85,0.041,-0.065,0.115
-Moirai-2.0,Chronos-Bolt,0.8,0.6,0.95,0.079,0.017,0.14
-Moirai-2.0,Seasonal Naive,1.0,1.0,1.0,0.584,0.469,0.689
-TFT,Toto-2.0-2.5B,0.0,0.0,0.0,-0.317,-0.464,-0.198
-TFT,Toto-2.0-1B,0.0,0.0,0.0,-0.317,-0.457,-0.195
-TFT,Toto-2.0-313m,0.0,0.0,0.0,-0.308,-0.444,-0.191
-TFT,Toto-2.0-22m,0.0,0.0,0.0,-0.242,-0.363,-0.144
-TFT,Toto-1.0,0.05,0.0,0.15,-0.188,-0.277,-0.106
-TFT,Chronos-2,0.1,0.0,0.25,-0.217,-0.348,-0.107
-TFT,Toto-2.0-4m,0.1,0.0,0.25,-0.171,-0.267,-0.084
-TFT,TiRex-2,0.15,0.05,0.3,-0.145,-0.235,-0.068
-TFT,TimesFM-2.5,0.2,0.05,0.4,-0.155,-0.277,-0.042
-TFT,TiRex,0.2,0.05,0.4,-0.122,-0.221,-0.018
-TFT,TabPFN-TS-3,0.3,0.1,0.5,-0.082,-0.21,0.049
-TFT,FlowState,0.45,0.25,0.7,0.004,-0.13,0.142
-TFT,Moirai-2.0,0.35,0.15,0.6,-0.056,-0.166,0.049
-TFT,TFT,0.5,0.5,0.5,0.0,0.0,0.0
-TFT,PatchTST,0.575,0.375,0.8,-0.013,-0.135,0.076
-TFT,Chronos-Bolt,0.6,0.4,0.8,0.028,-0.073,0.104
-TFT,Seasonal Naive,0.9,0.75,1.0,0.561,0.416,0.683
-PatchTST,Toto-2.0-2.5B,0.05,0.0,0.15,-0.301,-0.442,-0.186
-PatchTST,Toto-2.0-1B,0.05,0.0,0.15,-0.3,-0.452,-0.175
-PatchTST,Toto-2.0-313m,0.05,0.0,0.15,-0.291,-0.438,-0.17
-PatchTST,Toto-2.0-22m,0.05,0.0,0.15,-0.226,-0.344,-0.113
-PatchTST,Toto-1.0,0.1,0.0,0.25,-0.173,-0.284,-0.058
-PatchTST,Chronos-2,0.15,0.0,0.3,-0.202,-0.3,-0.115
-PatchTST,Toto-2.0-4m,0.1,0.0,0.25,-0.156,-0.256,-0.049
-PatchTST,TiRex-2,0.05,0.0,0.15,-0.13,-0.226,-0.022
-PatchTST,TimesFM-2.5,0.2,0.05,0.351,-0.14,-0.23,-0.061
-PatchTST,TiRex,0.2,0.05,0.4,-0.108,-0.207,0.003
-PatchTST,TabPFN-TS-3,0.3,0.1,0.5,-0.068,-0.144,0.012
-PatchTST,FlowState,0.5,0.3,0.7,0.017,-0.09,0.132
-PatchTST,Moirai-2.0,0.35,0.15,0.55,-0.042,-0.129,0.061
-PatchTST,TFT,0.425,0.2,0.625,0.013,-0.082,0.119
-PatchTST,PatchTST,0.5,0.5,0.5,0.0,0.0,0.0
-PatchTST,Chronos-Bolt,0.4,0.2,0.6,0.04,-0.034,0.126
-PatchTST,Seasonal Naive,0.9,0.75,1.0,0.567,0.435,0.68
-Chronos-Bolt,Toto-2.0-2.5B,0.0,0.0,0.0,-0.355,-0.477,-0.24
-Chronos-Bolt,Toto-2.0-1B,0.0,0.0,0.0,-0.354,-0.487,-0.237
-Chronos-Bolt,Toto-2.0-313m,0.0,0.0,0.0,-0.345,-0.466,-0.235
-Chronos-Bolt,Toto-2.0-22m,0.0,0.0,0.0,-0.277,-0.37,-0.188
-Chronos-Bolt,Toto-1.0,0.05,0.0,0.15,-0.222,-0.31,-0.141
-Chronos-Bolt,Chronos-2,0.0,0.0,0.0,-0.251,-0.352,-0.155
-Chronos-Bolt,Toto-2.0-4m,0.0,0.0,0.0,-0.204,-0.279,-0.137
-Chronos-Bolt,TiRex-2,0.05,0.0,0.15,-0.177,-0.246,-0.119
-Chronos-Bolt,TimesFM-2.5,0.1,0.0,0.25,-0.187,-0.277,-0.105
-Chronos-Bolt,TiRex,0.1,0.0,0.25,-0.154,-0.229,-0.079
-Chronos-Bolt,TabPFN-TS-3,0.35,0.15,0.6,-0.112,-0.239,-0.008
-Chronos-Bolt,FlowState,0.45,0.25,0.65,-0.024,-0.161,0.097
-Chronos-Bolt,Moirai-2.0,0.2,0.05,0.4,-0.086,-0.162,-0.017
-Chronos-Bolt,TFT,0.4,0.2,0.6,-0.028,-0.116,0.068
-Chronos-Bolt,PatchTST,0.6,0.4,0.8,-0.042,-0.144,0.033
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,Seasonal Naive,0.9,0.75,1.0,0.549,0.413,0.67
-Seasonal Naive,Toto-2.0-2.5B,0.0,0.0,0.0,-2.001,-3.137,-1.304
-Seasonal Naive,Toto-2.0-1B,0.0,0.0,0.0,-2.001,-3.152,-1.302
-Seasonal Naive,Toto-2.0-313m,0.0,0.0,0.0,-1.979,-3.139,-1.28
-Seasonal Naive,Toto-2.0-22m,0.0,0.0,0.0,-1.829,-2.894,-1.168
-Seasonal Naive,Toto-1.0,0.0,0.0,0.0,-1.707,-2.709,-1.085
-Seasonal Naive,Chronos-2,0.0,0.0,0.0,-1.772,-2.77,-1.139
-Seasonal Naive,Toto-2.0-4m,0.0,0.0,0.0,-1.668,-2.646,-1.063
-Seasonal Naive,TiRex-2,0.0,0.0,0.0,-1.608,-2.568,-1.019
-Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-1.631,-2.486,-1.077
-Seasonal Naive,TiRex,0.0,0.0,0.0,-1.556,-2.437,-0.997
-Seasonal Naive,TabPFN-TS-3,0.0,0.0,0.0,-1.464,-2.271,-0.947
-Seasonal Naive,FlowState,0.05,0.0,0.15,-1.268,-2.052,-0.736
-Seasonal Naive,Moirai-2.0,0.0,0.0,0.0,-1.405,-2.214,-0.883
-Seasonal Naive,TFT,0.1,0.0,0.25,-1.278,-2.153,-0.713
-Seasonal Naive,PatchTST,0.1,0.0,0.25,-1.307,-2.121,-0.769
-Seasonal Naive,Chronos-Bolt,0.1,0.0,0.25,-1.215,-2.027,-0.704
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_cloud/pairwise_WAPE.csv

@@ -1,290 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,Toto-2.0-1B,0.65,0.4,0.85,0.013,-0.0,0.033
-Toto-2.0-2.5B,Toto-2.0-313m,0.85,0.65,1.0,0.021,0.003,0.051
-Toto-2.0-2.5B,Toto-2.0-22m,1.0,1.0,1.0,0.071,0.029,0.124
-Toto-2.0-2.5B,Chronos-2,0.9,0.75,1.0,0.063,0.023,0.11
-Toto-2.0-2.5B,Toto-1.0,1.0,1.0,1.0,0.125,0.053,0.213
-Toto-2.0-2.5B,Toto-2.0-4m,1.0,1.0,1.0,0.125,0.066,0.193
-Toto-2.0-2.5B,TiRex-2,1.0,1.0,1.0,0.134,0.073,0.209
-Toto-2.0-2.5B,TimesFM-2.5,0.95,0.85,1.0,0.139,0.086,0.203
-Toto-2.0-2.5B,TiRex,1.0,1.0,1.0,0.166,0.087,0.257
-Toto-2.0-2.5B,FlowState,0.95,0.85,1.0,0.168,0.079,0.256
-Toto-2.0-2.5B,TabPFN-TS-3,0.95,0.85,1.0,0.139,0.049,0.245
-Toto-2.0-2.5B,TabPFN-TS,1.0,1.0,1.0,0.198,0.141,0.267
-Toto-2.0-2.5B,Moirai-2.0,1.0,1.0,1.0,0.191,0.114,0.276
-Toto-2.0-2.5B,PatchTST,0.95,0.85,1.0,0.191,0.095,0.279
-Toto-2.0-2.5B,Chronos-Bolt,1.0,1.0,1.0,0.23,0.156,0.302
-Toto-2.0-2.5B,Seasonal Naive,1.0,1.0,1.0,0.537,0.421,0.654
-Toto-2.0-1B,Toto-2.0-2.5B,0.35,0.15,0.6,-0.013,-0.034,0.0
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-313m,0.7,0.5,0.9,0.009,-0.002,0.023
-Toto-2.0-1B,Toto-2.0-22m,1.0,1.0,1.0,0.058,0.025,0.099
-Toto-2.0-1B,Chronos-2,0.9,0.75,1.0,0.051,-0.006,0.103
-Toto-2.0-1B,Toto-1.0,1.0,1.0,1.0,0.113,0.051,0.188
-Toto-2.0-1B,Toto-2.0-4m,1.0,1.0,1.0,0.113,0.062,0.171
-Toto-2.0-1B,TiRex-2,1.0,1.0,1.0,0.122,0.069,0.184
-Toto-2.0-1B,TimesFM-2.5,1.0,1.0,1.0,0.127,0.081,0.191
-Toto-2.0-1B,TiRex,1.0,1.0,1.0,0.155,0.082,0.239
-Toto-2.0-1B,FlowState,0.95,0.85,1.0,0.157,0.056,0.251
-Toto-2.0-1B,TabPFN-TS-3,0.95,0.85,1.0,0.128,0.019,0.239
-Toto-2.0-1B,TabPFN-TS,1.0,1.0,1.0,0.187,0.136,0.254
-Toto-2.0-1B,Moirai-2.0,1.0,1.0,1.0,0.18,0.109,0.265
-Toto-2.0-1B,PatchTST,0.95,0.85,1.0,0.181,0.07,0.275
-Toto-2.0-1B,Chronos-Bolt,1.0,1.0,1.0,0.22,0.152,0.285
-Toto-2.0-1B,Seasonal Naive,1.0,1.0,1.0,0.531,0.419,0.647
-Toto-2.0-313m,Toto-2.0-2.5B,0.15,0.0,0.35,-0.022,-0.054,-0.003
-Toto-2.0-313m,Toto-2.0-1B,0.3,0.1,0.5,-0.009,-0.023,0.002
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,Toto-2.0-22m,1.0,1.0,1.0,0.05,0.024,0.082
-Toto-2.0-313m,Chronos-2,0.9,0.75,1.0,0.043,-0.025,0.097
-Toto-2.0-313m,Toto-1.0,1.0,1.0,1.0,0.106,0.048,0.177
-Toto-2.0-313m,Toto-2.0-4m,1.0,1.0,1.0,0.106,0.06,0.159
-Toto-2.0-313m,TiRex-2,1.0,1.0,1.0,0.115,0.068,0.169
-Toto-2.0-313m,TimesFM-2.5,1.0,1.0,1.0,0.12,0.076,0.18
-Toto-2.0-313m,TiRex,1.0,1.0,1.0,0.147,0.08,0.229
-Toto-2.0-313m,FlowState,0.95,0.85,1.0,0.149,0.038,0.248
-Toto-2.0-313m,TabPFN-TS-3,0.95,0.85,1.0,0.121,-0.004,0.231
-Toto-2.0-313m,TabPFN-TS,1.0,1.0,1.0,0.18,0.131,0.245
-Toto-2.0-313m,Moirai-2.0,1.0,1.0,1.0,0.173,0.108,0.251
-Toto-2.0-313m,PatchTST,0.95,0.85,1.0,0.174,0.052,0.27
-Toto-2.0-313m,Chronos-Bolt,1.0,1.0,1.0,0.213,0.151,0.275
-Toto-2.0-313m,Seasonal Naive,1.0,1.0,1.0,0.527,0.414,0.642
-Toto-2.0-22m,Toto-2.0-2.5B,0.0,0.0,0.0,-0.076,-0.142,-0.03
-Toto-2.0-22m,Toto-2.0-1B,0.0,0.0,0.0,-0.062,-0.11,-0.026
-Toto-2.0-22m,Toto-2.0-313m,0.0,0.0,0.0,-0.053,-0.089,-0.025
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,Chronos-2,0.8,0.6,0.95,-0.008,-0.096,0.044
-Toto-2.0-22m,Toto-1.0,0.9,0.75,1.0,0.059,0.02,0.114
-Toto-2.0-22m,Toto-2.0-4m,1.0,1.0,1.0,0.058,0.034,0.085
-Toto-2.0-22m,TiRex-2,0.95,0.85,1.0,0.068,0.042,0.099
-Toto-2.0-22m,TimesFM-2.5,0.9,0.75,1.0,0.073,0.036,0.118
-Toto-2.0-22m,TiRex,0.95,0.85,1.0,0.102,0.053,0.16
-Toto-2.0-22m,FlowState,0.95,0.85,1.0,0.104,-0.035,0.209
-Toto-2.0-22m,TabPFN-TS-3,0.95,0.85,1.0,0.074,-0.075,0.178
-Toto-2.0-22m,TabPFN-TS,0.9,0.75,1.0,0.137,0.098,0.186
-Toto-2.0-22m,Moirai-2.0,1.0,1.0,1.0,0.129,0.081,0.192
-Toto-2.0-22m,PatchTST,0.95,0.85,1.0,0.13,-0.014,0.227
-Toto-2.0-22m,Chronos-Bolt,1.0,1.0,1.0,0.171,0.122,0.223
-Toto-2.0-22m,Seasonal Naive,1.0,1.0,1.0,0.502,0.392,0.613
-Chronos-2,Toto-2.0-2.5B,0.1,0.0,0.25,-0.068,-0.124,-0.023
-Chronos-2,Toto-2.0-1B,0.1,0.0,0.25,-0.054,-0.115,0.006
-Chronos-2,Toto-2.0-313m,0.1,0.0,0.25,-0.045,-0.107,0.024
-Chronos-2,Toto-2.0-22m,0.2,0.05,0.4,0.008,-0.046,0.087
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,Toto-1.0,0.35,0.15,0.55,0.066,-0.014,0.174
-Chronos-2,Toto-2.0-4m,0.6,0.35,0.8,0.066,0.005,0.155
-Chronos-2,TiRex-2,0.85,0.65,1.0,0.075,0.013,0.169
-Chronos-2,TimesFM-2.5,0.75,0.55,0.9,0.08,0.03,0.14
-Chronos-2,TiRex,0.8,0.6,0.95,0.109,0.032,0.209
-Chronos-2,FlowState,0.8,0.6,0.95,0.111,0.049,0.183
-Chronos-2,TabPFN-TS-3,0.85,0.65,1.0,0.081,0.019,0.155
-Chronos-2,TabPFN-TS,0.95,0.85,1.0,0.143,0.087,0.216
-Chronos-2,Moirai-2.0,1.0,1.0,1.0,0.136,0.059,0.226
-Chronos-2,PatchTST,0.85,0.7,1.0,0.137,0.061,0.205
-Chronos-2,Chronos-Bolt,1.0,1.0,1.0,0.178,0.103,0.259
-Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.506,0.388,0.617
-Toto-1.0,Toto-2.0-2.5B,0.0,0.0,0.0,-0.143,-0.27,-0.056
-Toto-1.0,Toto-2.0-1B,0.0,0.0,0.0,-0.128,-0.232,-0.054
-Toto-1.0,Toto-2.0-313m,0.0,0.0,0.0,-0.118,-0.215,-0.05
-Toto-1.0,Toto-2.0-22m,0.1,0.0,0.25,-0.062,-0.128,-0.021
-Toto-1.0,Chronos-2,0.65,0.45,0.85,-0.07,-0.211,0.014
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,Toto-2.0-4m,0.75,0.55,0.95,-0.0,-0.046,0.03
-Toto-1.0,TiRex-2,0.8,0.65,0.95,0.01,-0.05,0.046
-Toto-1.0,TimesFM-2.5,0.8,0.6,0.95,0.016,-0.049,0.069
-Toto-1.0,TiRex,0.75,0.55,0.9,0.046,-0.002,0.1
-Toto-1.0,FlowState,0.8,0.6,0.95,0.049,-0.12,0.172
-Toto-1.0,TabPFN-TS-3,0.85,0.699,1.0,0.016,-0.189,0.136
-Toto-1.0,TabPFN-TS,0.85,0.699,1.0,0.083,0.012,0.143
-Toto-1.0,Moirai-2.0,0.9,0.75,1.0,0.075,0.014,0.139
-Toto-1.0,PatchTST,0.9,0.75,1.0,0.076,-0.112,0.188
-Toto-1.0,Chronos-Bolt,0.95,0.85,1.0,0.12,0.051,0.182
-Toto-1.0,Seasonal Naive,1.0,1.0,1.0,0.471,0.37,0.58
-Toto-2.0-4m,Toto-2.0-2.5B,0.0,0.0,0.0,-0.143,-0.239,-0.07
-Toto-2.0-4m,Toto-2.0-1B,0.0,0.0,0.0,-0.128,-0.206,-0.066
-Toto-2.0-4m,Toto-2.0-313m,0.0,0.0,0.0,-0.118,-0.189,-0.063
-Toto-2.0-4m,Toto-2.0-22m,0.0,0.0,0.0,-0.062,-0.093,-0.036
-Toto-2.0-4m,Chronos-2,0.4,0.2,0.65,-0.07,-0.184,-0.005
-Toto-2.0-4m,Toto-1.0,0.25,0.05,0.45,0.0,-0.031,0.044
-Toto-2.0-4m,Toto-2.0-4m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-4m,TiRex-2,0.75,0.55,0.9,0.01,-0.012,0.033
-Toto-2.0-4m,TimesFM-2.5,0.7,0.5,0.9,0.016,-0.025,0.049
-Toto-2.0-4m,TiRex,0.75,0.55,0.9,0.047,0.016,0.086
-Toto-2.0-4m,FlowState,0.8,0.6,0.95,0.049,-0.109,0.156
-Toto-2.0-4m,TabPFN-TS-3,0.75,0.55,0.95,0.017,-0.155,0.119
-Toto-2.0-4m,TabPFN-TS,0.7,0.5,0.9,0.083,0.042,0.126
-Toto-2.0-4m,Moirai-2.0,0.9,0.75,1.0,0.075,0.041,0.122
-Toto-2.0-4m,PatchTST,0.9,0.75,1.0,0.076,-0.082,0.173
-Toto-2.0-4m,Chronos-Bolt,1.0,1.0,1.0,0.12,0.077,0.168
-Toto-2.0-4m,Seasonal Naive,1.0,1.0,1.0,0.471,0.364,0.579
-TiRex-2,Toto-2.0-2.5B,0.0,0.0,0.0,-0.155,-0.264,-0.079
-TiRex-2,Toto-2.0-1B,0.0,0.0,0.0,-0.14,-0.226,-0.074
-TiRex-2,Toto-2.0-313m,0.0,0.0,0.0,-0.13,-0.204,-0.073
-TiRex-2,Toto-2.0-22m,0.05,0.0,0.15,-0.073,-0.11,-0.044
-TiRex-2,Chronos-2,0.15,0.0,0.35,-0.081,-0.204,-0.013
-TiRex-2,Toto-1.0,0.2,0.05,0.35,-0.01,-0.049,0.047
-TiRex-2,Toto-2.0-4m,0.25,0.1,0.45,-0.01,-0.034,0.012
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,TimesFM-2.5,0.65,0.45,0.85,0.006,-0.055,0.053
-TiRex-2,TiRex,0.65,0.45,0.85,0.037,0.003,0.082
-TiRex-2,FlowState,0.75,0.55,0.95,0.039,-0.135,0.155
-TiRex-2,TabPFN-TS-3,0.8,0.65,0.95,0.006,-0.176,0.12
-TiRex-2,TabPFN-TS,0.8,0.6,0.95,0.074,0.027,0.122
-TiRex-2,Moirai-2.0,0.8,0.6,0.95,0.066,0.026,0.12
-TiRex-2,PatchTST,0.95,0.85,1.0,0.066,-0.107,0.169
-TiRex-2,Chronos-Bolt,0.95,0.85,1.0,0.111,0.066,0.165
-TiRex-2,Seasonal Naive,1.0,1.0,1.0,0.466,0.355,0.579
-TimesFM-2.5,Toto-2.0-2.5B,0.05,0.0,0.15,-0.161,-0.255,-0.094
-TimesFM-2.5,Toto-2.0-1B,0.0,0.0,0.0,-0.146,-0.236,-0.088
-TimesFM-2.5,Toto-2.0-313m,0.0,0.0,0.0,-0.136,-0.22,-0.082
-TimesFM-2.5,Toto-2.0-22m,0.1,0.0,0.25,-0.079,-0.134,-0.037
-TimesFM-2.5,Chronos-2,0.25,0.1,0.45,-0.088,-0.162,-0.031
-TimesFM-2.5,Toto-1.0,0.2,0.05,0.4,-0.016,-0.074,0.047
-TimesFM-2.5,Toto-2.0-4m,0.3,0.1,0.5,-0.016,-0.052,0.025
-TimesFM-2.5,TiRex-2,0.35,0.15,0.55,-0.006,-0.056,0.052
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,TiRex,0.6,0.4,0.8,0.031,-0.009,0.083
-TimesFM-2.5,FlowState,0.8,0.6,0.95,0.033,-0.09,0.123
-TimesFM-2.5,TabPFN-TS-3,0.7,0.5,0.9,0.001,-0.121,0.081
-TimesFM-2.5,TabPFN-TS,0.75,0.55,0.95,0.068,0.034,0.105
-TimesFM-2.5,Moirai-2.0,0.85,0.65,1.0,0.06,0.024,0.101
-TimesFM-2.5,PatchTST,0.8,0.649,0.95,0.061,-0.066,0.141
-TimesFM-2.5,Chronos-Bolt,0.9,0.75,1.0,0.106,0.065,0.148
-TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.462,0.364,0.568
-TiRex,Toto-2.0-2.5B,0.0,0.0,0.0,-0.199,-0.346,-0.095
-TiRex,Toto-2.0-1B,0.0,0.0,0.0,-0.183,-0.313,-0.089
-TiRex,Toto-2.0-313m,0.0,0.0,0.0,-0.173,-0.296,-0.087
-TiRex,Toto-2.0-22m,0.05,0.0,0.15,-0.114,-0.191,-0.056
-TiRex,Chronos-2,0.2,0.05,0.4,-0.122,-0.264,-0.033
-TiRex,Toto-1.0,0.25,0.1,0.45,-0.049,-0.111,0.002
-TiRex,Toto-2.0-4m,0.25,0.1,0.45,-0.049,-0.094,-0.016
-TiRex,TiRex-2,0.35,0.15,0.55,-0.038,-0.09,-0.003
-TiRex,TimesFM-2.5,0.4,0.2,0.6,-0.032,-0.091,0.009
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,FlowState,0.6,0.4,0.8,0.002,-0.176,0.116
-TiRex,TabPFN-TS-3,0.75,0.55,0.901,-0.031,-0.219,0.065
-TiRex,TabPFN-TS,0.7,0.5,0.9,0.038,-0.012,0.083
-TiRex,Moirai-2.0,0.75,0.55,0.9,0.03,0.004,0.056
-TiRex,PatchTST,0.75,0.55,0.9,0.031,-0.152,0.138
-TiRex,Chronos-Bolt,0.85,0.65,1.0,0.077,0.03,0.124
-TiRex,Seasonal Naive,1.0,1.0,1.0,0.445,0.35,0.545
-FlowState,Toto-2.0-2.5B,0.05,0.0,0.15,-0.201,-0.344,-0.085
-FlowState,Toto-2.0-1B,0.05,0.0,0.15,-0.186,-0.335,-0.059
-FlowState,Toto-2.0-313m,0.05,0.0,0.15,-0.175,-0.33,-0.04
-FlowState,Toto-2.0-22m,0.05,0.0,0.15,-0.116,-0.264,0.034
-FlowState,Chronos-2,0.2,0.05,0.4,-0.125,-0.224,-0.051
-FlowState,Toto-1.0,0.2,0.05,0.4,-0.051,-0.208,0.107
-FlowState,Toto-2.0-4m,0.2,0.05,0.4,-0.051,-0.185,0.099
-FlowState,TiRex-2,0.25,0.05,0.45,-0.04,-0.183,0.119
-FlowState,TimesFM-2.5,0.2,0.05,0.4,-0.035,-0.141,0.083
-FlowState,TiRex,0.4,0.2,0.6,-0.002,-0.131,0.149
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,TabPFN-TS-3,0.5,0.3,0.7,-0.034,-0.124,0.05
-FlowState,TabPFN-TS,0.55,0.35,0.75,0.036,-0.086,0.162
-FlowState,Moirai-2.0,0.55,0.35,0.75,0.028,-0.093,0.164
-FlowState,PatchTST,0.6,0.4,0.8,0.029,-0.068,0.106
-FlowState,Chronos-Bolt,0.7,0.5,0.851,0.075,-0.004,0.187
-FlowState,Seasonal Naive,1.0,1.0,1.0,0.444,0.326,0.558
-TabPFN-TS-3,Toto-2.0-2.5B,0.05,0.0,0.15,-0.162,-0.325,-0.051
-TabPFN-TS-3,Toto-2.0-1B,0.05,0.0,0.15,-0.147,-0.313,-0.019
-TabPFN-TS-3,Toto-2.0-313m,0.05,0.0,0.15,-0.137,-0.3,0.004
-TabPFN-TS-3,Toto-2.0-22m,0.05,0.0,0.15,-0.08,-0.217,0.07
-TabPFN-TS-3,Chronos-2,0.15,0.0,0.35,-0.088,-0.184,-0.019
-TabPFN-TS-3,Toto-1.0,0.15,0.0,0.301,-0.017,-0.157,0.159
-TabPFN-TS-3,Toto-2.0-4m,0.25,0.05,0.45,-0.017,-0.135,0.134
-TabPFN-TS-3,TiRex-2,0.2,0.05,0.35,-0.006,-0.137,0.15
-TabPFN-TS-3,TimesFM-2.5,0.3,0.1,0.5,-0.001,-0.088,0.108
-TabPFN-TS-3,TiRex,0.25,0.099,0.45,0.03,-0.07,0.179
-TabPFN-TS-3,FlowState,0.5,0.3,0.7,0.033,-0.052,0.11
-TabPFN-TS-3,TabPFN-TS-3,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS-3,TabPFN-TS,0.65,0.45,0.85,0.068,-0.013,0.181
-TabPFN-TS-3,Moirai-2.0,0.5,0.3,0.7,0.06,-0.026,0.187
-TabPFN-TS-3,PatchTST,0.5,0.3,0.7,0.06,-0.007,0.116
-TabPFN-TS-3,Chronos-Bolt,0.6,0.4,0.8,0.105,-0.001,0.226
-TabPFN-TS-3,Seasonal Naive,1.0,1.0,1.0,0.462,0.342,0.578
-TabPFN-TS,Toto-2.0-2.5B,0.0,0.0,0.0,-0.246,-0.363,-0.164
-TabPFN-TS,Toto-2.0-1B,0.0,0.0,0.0,-0.23,-0.341,-0.157
-TabPFN-TS,Toto-2.0-313m,0.0,0.0,0.0,-0.22,-0.324,-0.151
-TabPFN-TS,Toto-2.0-22m,0.1,0.0,0.25,-0.158,-0.228,-0.109
-TabPFN-TS,Chronos-2,0.05,0.0,0.15,-0.167,-0.275,-0.095
-TabPFN-TS,Toto-1.0,0.15,0.0,0.301,-0.091,-0.166,-0.012
-TabPFN-TS,Toto-2.0-4m,0.3,0.1,0.5,-0.091,-0.145,-0.043
-TabPFN-TS,TiRex-2,0.2,0.05,0.4,-0.08,-0.139,-0.028
-TabPFN-TS,TimesFM-2.5,0.25,0.05,0.45,-0.073,-0.118,-0.035
-TabPFN-TS,TiRex,0.3,0.1,0.5,-0.04,-0.091,0.012
-TabPFN-TS,FlowState,0.45,0.25,0.65,-0.038,-0.193,0.079
-TabPFN-TS,TabPFN-TS-3,0.35,0.15,0.55,-0.073,-0.221,0.013
-TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS,Moirai-2.0,0.45,0.2,0.65,-0.009,-0.056,0.034
-TabPFN-TS,PatchTST,0.45,0.25,0.65,-0.008,-0.175,0.096
-TabPFN-TS,Chronos-Bolt,0.55,0.35,0.75,0.04,-0.028,0.105
-TabPFN-TS,Seasonal Naive,1.0,1.0,1.0,0.423,0.304,0.541
-Moirai-2.0,Toto-2.0-2.5B,0.0,0.0,0.0,-0.236,-0.382,-0.129
-Moirai-2.0,Toto-2.0-1B,0.0,0.0,0.0,-0.22,-0.36,-0.122
-Moirai-2.0,Toto-2.0-313m,0.0,0.0,0.0,-0.209,-0.335,-0.121
-Moirai-2.0,Toto-2.0-22m,0.0,0.0,0.0,-0.149,-0.238,-0.089
-Moirai-2.0,Chronos-2,0.0,0.0,0.0,-0.157,-0.292,-0.062
-Moirai-2.0,Toto-1.0,0.1,0.0,0.25,-0.081,-0.162,-0.014
-Moirai-2.0,Toto-2.0-4m,0.1,0.0,0.25,-0.081,-0.139,-0.043
-Moirai-2.0,TiRex-2,0.2,0.05,0.4,-0.07,-0.136,-0.027
-Moirai-2.0,TimesFM-2.5,0.15,0.0,0.35,-0.064,-0.112,-0.025
-Moirai-2.0,TiRex,0.25,0.1,0.45,-0.031,-0.06,-0.004
-Moirai-2.0,FlowState,0.45,0.25,0.65,-0.029,-0.197,0.085
-Moirai-2.0,TabPFN-TS-3,0.5,0.3,0.7,-0.064,-0.23,0.026
-Moirai-2.0,TabPFN-TS,0.55,0.35,0.8,0.008,-0.035,0.053
-Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
-Moirai-2.0,PatchTST,0.55,0.3,0.75,0.001,-0.174,0.1
-Moirai-2.0,Chronos-Bolt,0.75,0.55,0.9,0.048,0.003,0.096
-Moirai-2.0,Seasonal Naive,1.0,1.0,1.0,0.428,0.333,0.532
-PatchTST,Toto-2.0-2.5B,0.05,0.0,0.15,-0.237,-0.387,-0.105
-PatchTST,Toto-2.0-1B,0.05,0.0,0.15,-0.22,-0.379,-0.075
-PatchTST,Toto-2.0-313m,0.05,0.0,0.15,-0.21,-0.37,-0.055
-PatchTST,Toto-2.0-22m,0.05,0.0,0.15,-0.149,-0.294,0.013
-PatchTST,Chronos-2,0.15,0.0,0.3,-0.158,-0.258,-0.065
-PatchTST,Toto-1.0,0.1,0.0,0.25,-0.082,-0.232,0.1
-PatchTST,Toto-2.0-4m,0.1,0.0,0.25,-0.082,-0.209,0.075
-PatchTST,TiRex-2,0.05,0.0,0.15,-0.071,-0.204,0.097
-PatchTST,TimesFM-2.5,0.2,0.05,0.351,-0.065,-0.165,0.062
-PatchTST,TiRex,0.25,0.1,0.45,-0.032,-0.16,0.132
-PatchTST,FlowState,0.4,0.2,0.6,-0.029,-0.118,0.064
-PatchTST,TabPFN-TS-3,0.5,0.3,0.7,-0.064,-0.131,0.007
-PatchTST,TabPFN-TS,0.55,0.35,0.75,0.008,-0.107,0.149
-PatchTST,Moirai-2.0,0.45,0.25,0.7,-0.001,-0.111,0.148
-PatchTST,PatchTST,0.5,0.5,0.5,0.0,0.0,0.0
-PatchTST,Chronos-Bolt,0.5,0.3,0.7,0.048,-0.064,0.191
-PatchTST,Seasonal Naive,0.9,0.775,1.0,0.428,0.289,0.553
-Chronos-Bolt,Toto-2.0-2.5B,0.0,0.0,0.0,-0.298,-0.433,-0.184
-Chronos-Bolt,Toto-2.0-1B,0.0,0.0,0.0,-0.281,-0.399,-0.179
-Chronos-Bolt,Toto-2.0-313m,0.0,0.0,0.0,-0.271,-0.38,-0.178
-Chronos-Bolt,Toto-2.0-22m,0.0,0.0,0.0,-0.207,-0.287,-0.139
-Chronos-Bolt,Chronos-2,0.0,0.0,0.0,-0.216,-0.349,-0.115
-Chronos-Bolt,Toto-1.0,0.05,0.0,0.15,-0.136,-0.223,-0.053
-Chronos-Bolt,Toto-2.0-4m,0.0,0.0,0.0,-0.136,-0.201,-0.083
-Chronos-Bolt,TiRex-2,0.05,0.0,0.15,-0.125,-0.197,-0.071
-Chronos-Bolt,TimesFM-2.5,0.1,0.0,0.25,-0.118,-0.174,-0.069
-Chronos-Bolt,TiRex,0.15,0.0,0.35,-0.083,-0.141,-0.031
-Chronos-Bolt,FlowState,0.3,0.149,0.5,-0.081,-0.231,0.004
-Chronos-Bolt,TabPFN-TS-3,0.4,0.2,0.6,-0.117,-0.293,0.001
-Chronos-Bolt,TabPFN-TS,0.45,0.25,0.65,-0.042,-0.117,0.028
-Chronos-Bolt,Moirai-2.0,0.25,0.1,0.45,-0.051,-0.106,-0.003
-Chronos-Bolt,PatchTST,0.5,0.3,0.7,-0.05,-0.235,0.06
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,Seasonal Naive,1.0,1.0,1.0,0.399,0.295,0.512
-Seasonal Naive,Toto-2.0-2.5B,0.0,0.0,0.0,-1.16,-1.888,-0.726
-Seasonal Naive,Toto-2.0-1B,0.0,0.0,0.0,-1.132,-1.83,-0.721
-Seasonal Naive,Toto-2.0-313m,0.0,0.0,0.0,-1.114,-1.794,-0.707
-Seasonal Naive,Toto-2.0-22m,0.0,0.0,0.0,-1.008,-1.587,-0.645
-Seasonal Naive,Chronos-2,0.0,0.0,0.0,-1.023,-1.609,-0.634
-Seasonal Naive,Toto-1.0,0.0,0.0,0.0,-0.89,-1.38,-0.588
-Seasonal Naive,Toto-2.0-4m,0.0,0.0,0.0,-0.89,-1.375,-0.572
-Seasonal Naive,TiRex-2,0.0,0.0,0.0,-0.871,-1.377,-0.55
-Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-0.86,-1.313,-0.572
-Seasonal Naive,TiRex,0.0,0.0,0.0,-0.802,-1.198,-0.539
-Seasonal Naive,FlowState,0.0,0.0,0.0,-0.798,-1.26,-0.483
-Seasonal Naive,TabPFN-TS-3,0.0,0.0,0.0,-0.859,-1.369,-0.521
-Seasonal Naive,TabPFN-TS,0.0,0.0,0.0,-0.733,-1.18,-0.436
-Seasonal Naive,Moirai-2.0,0.0,0.0,0.0,-0.748,-1.138,-0.499
-Seasonal Naive,PatchTST,0.1,0.0,0.225,-0.747,-1.237,-0.406
-Seasonal Naive,Chronos-Bolt,0.0,0.0,0.0,-0.664,-1.049,-0.418
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_cloud/pairwise_WQL.csv

@@ -1,290 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,Toto-2.0-1B,0.75,0.55,0.9,0.009,-0.004,0.026
-Toto-2.0-2.5B,Toto-2.0-313m,0.9,0.75,1.0,0.02,-0.002,0.053
-Toto-2.0-2.5B,Toto-2.0-22m,1.0,1.0,1.0,0.068,0.033,0.117
-Toto-2.0-2.5B,Chronos-2,0.95,0.85,1.0,0.063,0.029,0.097
-Toto-2.0-2.5B,Toto-1.0,1.0,1.0,1.0,0.129,0.058,0.225
-Toto-2.0-2.5B,Toto-2.0-4m,1.0,1.0,1.0,0.13,0.069,0.205
-Toto-2.0-2.5B,TiRex-2,1.0,1.0,1.0,0.14,0.077,0.222
-Toto-2.0-2.5B,TimesFM-2.5,1.0,1.0,1.0,0.146,0.095,0.204
-Toto-2.0-2.5B,TiRex,1.0,1.0,1.0,0.169,0.091,0.263
-Toto-2.0-2.5B,TabPFN-TS-3,0.95,0.85,1.0,0.131,0.047,0.222
-Toto-2.0-2.5B,FlowState,0.95,0.85,1.0,0.171,0.084,0.255
-Toto-2.0-2.5B,Moirai-2.0,1.0,1.0,1.0,0.204,0.129,0.288
-Toto-2.0-2.5B,PatchTST,0.95,0.85,1.0,0.231,0.124,0.326
-Toto-2.0-2.5B,TFT,1.0,1.0,1.0,0.303,0.177,0.432
-Toto-2.0-2.5B,Chronos-Bolt,1.0,1.0,1.0,0.26,0.189,0.332
-Toto-2.0-2.5B,Seasonal Naive,1.0,1.0,1.0,0.69,0.609,0.766
-Toto-2.0-1B,Toto-2.0-2.5B,0.25,0.1,0.45,-0.009,-0.027,0.004
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-313m,0.8,0.6,0.95,0.011,-0.002,0.03
-Toto-2.0-1B,Toto-2.0-22m,1.0,1.0,1.0,0.059,0.03,0.097
-Toto-2.0-1B,Chronos-2,0.95,0.85,1.0,0.055,0.005,0.095
-Toto-2.0-1B,Toto-1.0,1.0,1.0,1.0,0.121,0.056,0.205
-Toto-2.0-1B,Toto-2.0-4m,1.0,1.0,1.0,0.122,0.068,0.187
-Toto-2.0-1B,TiRex-2,1.0,1.0,1.0,0.132,0.076,0.205
-Toto-2.0-1B,TimesFM-2.5,1.0,1.0,1.0,0.138,0.091,0.191
-Toto-2.0-1B,TiRex,1.0,1.0,1.0,0.161,0.088,0.248
-Toto-2.0-1B,TabPFN-TS-3,0.95,0.85,1.0,0.123,0.025,0.223
-Toto-2.0-1B,FlowState,0.95,0.85,1.0,0.163,0.068,0.254
-Toto-2.0-1B,Moirai-2.0,1.0,1.0,1.0,0.197,0.125,0.279
-Toto-2.0-1B,PatchTST,0.95,0.85,1.0,0.224,0.107,0.322
-Toto-2.0-1B,TFT,1.0,1.0,1.0,0.297,0.176,0.423
-Toto-2.0-1B,Chronos-Bolt,1.0,1.0,1.0,0.253,0.186,0.32
-Toto-2.0-1B,Seasonal Naive,1.0,1.0,1.0,0.688,0.607,0.763
-Toto-2.0-313m,Toto-2.0-2.5B,0.1,0.0,0.25,-0.02,-0.056,0.002
-Toto-2.0-313m,Toto-2.0-1B,0.2,0.05,0.4,-0.011,-0.03,0.002
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,Toto-2.0-22m,1.0,1.0,1.0,0.049,0.028,0.073
-Toto-2.0-313m,Chronos-2,0.9,0.75,1.0,0.044,-0.025,0.093
-Toto-2.0-313m,Toto-1.0,1.0,1.0,1.0,0.111,0.054,0.181
-Toto-2.0-313m,Toto-2.0-4m,1.0,1.0,1.0,0.112,0.065,0.165
-Toto-2.0-313m,TiRex-2,1.0,1.0,1.0,0.123,0.074,0.182
-Toto-2.0-313m,TimesFM-2.5,1.0,1.0,1.0,0.128,0.087,0.182
-Toto-2.0-313m,TiRex,1.0,1.0,1.0,0.152,0.086,0.227
-Toto-2.0-313m,TabPFN-TS-3,0.95,0.85,1.0,0.114,-0.005,0.22
-Toto-2.0-313m,FlowState,0.95,0.85,1.0,0.154,0.045,0.251
-Toto-2.0-313m,Moirai-2.0,1.0,1.0,1.0,0.188,0.124,0.259
-Toto-2.0-313m,PatchTST,0.95,0.85,1.0,0.216,0.083,0.318
-Toto-2.0-313m,TFT,1.0,1.0,1.0,0.289,0.173,0.418
-Toto-2.0-313m,Chronos-Bolt,1.0,1.0,1.0,0.245,0.185,0.304
-Toto-2.0-313m,Seasonal Naive,1.0,1.0,1.0,0.684,0.602,0.763
-Toto-2.0-22m,Toto-2.0-2.5B,0.0,0.0,0.0,-0.073,-0.133,-0.034
-Toto-2.0-22m,Toto-2.0-1B,0.0,0.0,0.0,-0.063,-0.107,-0.031
-Toto-2.0-22m,Toto-2.0-313m,0.0,0.0,0.0,-0.052,-0.079,-0.029
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,Chronos-2,0.8,0.6,0.95,-0.005,-0.088,0.044
-Toto-2.0-22m,Toto-1.0,0.9,0.75,1.0,0.065,0.023,0.123
-Toto-2.0-22m,Toto-2.0-4m,1.0,1.0,1.0,0.066,0.036,0.1
-Toto-2.0-22m,TiRex-2,1.0,1.0,1.0,0.077,0.044,0.12
-Toto-2.0-22m,TimesFM-2.5,0.95,0.85,1.0,0.084,0.052,0.121
-Toto-2.0-22m,TiRex,0.95,0.85,1.0,0.108,0.057,0.168
-Toto-2.0-22m,TabPFN-TS-3,0.9,0.75,1.0,0.068,-0.074,0.168
-Toto-2.0-22m,FlowState,0.9,0.75,1.0,0.111,-0.022,0.213
-Toto-2.0-22m,Moirai-2.0,1.0,1.0,1.0,0.146,0.095,0.205
-Toto-2.0-22m,PatchTST,0.95,0.85,1.0,0.176,0.029,0.281
-Toto-2.0-22m,TFT,1.0,1.0,1.0,0.253,0.14,0.374
-Toto-2.0-22m,Chronos-Bolt,1.0,1.0,1.0,0.206,0.157,0.257
-Toto-2.0-22m,Seasonal Naive,1.0,1.0,1.0,0.668,0.584,0.745
-Chronos-2,Toto-2.0-2.5B,0.05,0.0,0.15,-0.068,-0.107,-0.03
-Chronos-2,Toto-2.0-1B,0.05,0.0,0.15,-0.058,-0.105,-0.005
-Chronos-2,Toto-2.0-313m,0.1,0.0,0.25,-0.046,-0.103,0.024
-Chronos-2,Toto-2.0-22m,0.2,0.05,0.4,0.005,-0.046,0.081
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,Toto-1.0,0.35,0.15,0.55,0.07,-0.014,0.185
-Chronos-2,Toto-2.0-4m,0.6,0.35,0.8,0.071,0.004,0.171
-Chronos-2,TiRex-2,0.8,0.6,0.95,0.082,0.016,0.185
-Chronos-2,TimesFM-2.5,0.75,0.55,0.9,0.088,0.033,0.155
-Chronos-2,TiRex,0.85,0.7,1.0,0.113,0.032,0.222
-Chronos-2,TabPFN-TS-3,0.9,0.75,1.0,0.072,0.011,0.147
-Chronos-2,FlowState,0.85,0.65,1.0,0.115,0.05,0.188
-Chronos-2,Moirai-2.0,1.0,1.0,1.0,0.151,0.066,0.248
-Chronos-2,PatchTST,0.85,0.7,1.0,0.18,0.08,0.27
-Chronos-2,TFT,0.95,0.85,1.0,0.256,0.118,0.395
-Chronos-2,Chronos-Bolt,1.0,1.0,1.0,0.21,0.134,0.3
-Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.669,0.582,0.746
-Toto-1.0,Toto-2.0-2.5B,0.0,0.0,0.0,-0.148,-0.291,-0.061
-Toto-1.0,Toto-2.0-1B,0.0,0.0,0.0,-0.137,-0.257,-0.06
-Toto-1.0,Toto-2.0-313m,0.0,0.0,0.0,-0.125,-0.222,-0.057
-Toto-1.0,Toto-2.0-22m,0.1,0.0,0.25,-0.07,-0.141,-0.024
-Toto-1.0,Chronos-2,0.65,0.45,0.85,-0.075,-0.227,0.014
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,Toto-2.0-4m,0.6,0.4,0.8,0.001,-0.04,0.028
-Toto-1.0,TiRex-2,0.8,0.65,0.95,0.013,-0.041,0.047
-Toto-1.0,TimesFM-2.5,0.75,0.55,0.95,0.02,-0.047,0.073
-Toto-1.0,TiRex,0.75,0.55,0.9,0.046,0.0,0.095
-Toto-1.0,TabPFN-TS-3,0.8,0.6,0.95,0.003,-0.211,0.127
-Toto-1.0,FlowState,0.75,0.55,0.9,0.049,-0.131,0.178
-Toto-1.0,Moirai-2.0,0.85,0.7,1.0,0.087,0.029,0.145
-Toto-1.0,PatchTST,0.9,0.75,1.0,0.118,-0.078,0.246
-Toto-1.0,TFT,1.0,1.0,1.0,0.2,0.108,0.294
-Toto-1.0,Chronos-Bolt,0.95,0.85,1.0,0.151,0.089,0.21
-Toto-1.0,Seasonal Naive,1.0,1.0,1.0,0.645,0.563,0.725
-Toto-2.0-4m,Toto-2.0-2.5B,0.0,0.0,0.0,-0.149,-0.258,-0.075
-Toto-2.0-4m,Toto-2.0-1B,0.0,0.0,0.0,-0.139,-0.23,-0.073
-Toto-2.0-4m,Toto-2.0-313m,0.0,0.0,0.0,-0.126,-0.198,-0.069
-Toto-2.0-4m,Toto-2.0-22m,0.0,0.0,0.0,-0.071,-0.112,-0.038
-Toto-2.0-4m,Chronos-2,0.4,0.2,0.65,-0.076,-0.207,-0.004
-Toto-2.0-4m,Toto-1.0,0.4,0.2,0.6,-0.001,-0.029,0.038
-Toto-2.0-4m,Toto-2.0-4m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-4m,TiRex-2,0.65,0.45,0.85,0.012,-0.009,0.034
-Toto-2.0-4m,TimesFM-2.5,0.6,0.4,0.8,0.019,-0.028,0.056
-Toto-2.0-4m,TiRex,0.8,0.649,0.95,0.045,0.016,0.082
-Toto-2.0-4m,TabPFN-TS-3,0.75,0.55,0.95,0.002,-0.182,0.109
-Toto-2.0-4m,FlowState,0.85,0.7,1.0,0.048,-0.128,0.162
-Toto-2.0-4m,Moirai-2.0,0.9,0.75,1.0,0.086,0.049,0.128
-Toto-2.0-4m,PatchTST,0.95,0.85,1.0,0.117,-0.066,0.232
-Toto-2.0-4m,TFT,0.9,0.75,1.0,0.2,0.09,0.31
-Toto-2.0-4m,Chronos-Bolt,1.0,1.0,1.0,0.15,0.107,0.197
-Toto-2.0-4m,Seasonal Naive,1.0,1.0,1.0,0.644,0.559,0.727
-TiRex-2,Toto-2.0-2.5B,0.0,0.0,0.0,-0.163,-0.286,-0.084
-TiRex-2,Toto-2.0-1B,0.0,0.0,0.0,-0.152,-0.258,-0.082
-TiRex-2,Toto-2.0-313m,0.0,0.0,0.0,-0.14,-0.222,-0.08
-TiRex-2,Toto-2.0-22m,0.0,0.0,0.0,-0.084,-0.136,-0.046
-TiRex-2,Chronos-2,0.2,0.05,0.4,-0.089,-0.227,-0.017
-TiRex-2,Toto-1.0,0.2,0.05,0.35,-0.013,-0.049,0.039
-TiRex-2,Toto-2.0-4m,0.35,0.15,0.55,-0.012,-0.035,0.009
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,TimesFM-2.5,0.65,0.45,0.85,0.007,-0.056,0.053
-TiRex-2,TiRex,0.65,0.45,0.85,0.034,0.004,0.075
-TiRex-2,TabPFN-TS-3,0.75,0.6,0.9,-0.01,-0.207,0.11
-TiRex-2,FlowState,0.75,0.55,0.95,0.036,-0.151,0.155
-TiRex-2,Moirai-2.0,0.95,0.85,1.0,0.075,0.041,0.122
-TiRex-2,PatchTST,0.9,0.75,1.0,0.106,-0.096,0.232
-TiRex-2,TFT,0.85,0.7,0.95,0.19,0.073,0.312
-TiRex-2,Chronos-Bolt,1.0,1.0,1.0,0.14,0.099,0.185
-TiRex-2,Seasonal Naive,1.0,1.0,1.0,0.64,0.55,0.728
-TimesFM-2.5,Toto-2.0-2.5B,0.0,0.0,0.0,-0.171,-0.256,-0.105
-TimesFM-2.5,Toto-2.0-1B,0.0,0.0,0.0,-0.16,-0.236,-0.1
-TimesFM-2.5,Toto-2.0-313m,0.0,0.0,0.0,-0.147,-0.223,-0.095
-TimesFM-2.5,Toto-2.0-22m,0.05,0.0,0.15,-0.091,-0.138,-0.055
-TimesFM-2.5,Chronos-2,0.25,0.1,0.45,-0.097,-0.183,-0.034
-TimesFM-2.5,Toto-1.0,0.25,0.05,0.45,-0.02,-0.079,0.045
-TimesFM-2.5,Toto-2.0-4m,0.4,0.2,0.6,-0.019,-0.059,0.027
-TimesFM-2.5,TiRex-2,0.35,0.15,0.55,-0.007,-0.056,0.053
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,TiRex,0.6,0.4,0.8,0.027,-0.018,0.086
-TimesFM-2.5,TabPFN-TS-3,0.6,0.4,0.8,-0.017,-0.149,0.071
-TimesFM-2.5,FlowState,0.7,0.5,0.9,0.03,-0.104,0.121
-TimesFM-2.5,Moirai-2.0,0.85,0.65,1.0,0.069,0.028,0.116
-TimesFM-2.5,PatchTST,0.85,0.7,1.0,0.1,-0.044,0.208
-TimesFM-2.5,TFT,0.8,0.6,0.95,0.184,0.06,0.307
-TimesFM-2.5,Chronos-Bolt,0.9,0.75,1.0,0.134,0.092,0.179
-TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.638,0.557,0.714
-TiRex,Toto-2.0-2.5B,0.0,0.0,0.0,-0.203,-0.356,-0.1
-TiRex,Toto-2.0-1B,0.0,0.0,0.0,-0.192,-0.33,-0.096
-TiRex,Toto-2.0-313m,0.0,0.0,0.0,-0.179,-0.294,-0.094
-TiRex,Toto-2.0-22m,0.05,0.0,0.15,-0.122,-0.202,-0.061
-TiRex,Chronos-2,0.15,0.0,0.3,-0.127,-0.285,-0.033
-TiRex,Toto-1.0,0.25,0.1,0.45,-0.048,-0.105,-0.0
-TiRex,Toto-2.0-4m,0.2,0.05,0.351,-0.047,-0.089,-0.016
-TiRex,TiRex-2,0.35,0.15,0.55,-0.035,-0.081,-0.004
-TiRex,TimesFM-2.5,0.4,0.2,0.6,-0.028,-0.095,0.018
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,TabPFN-TS-3,0.7,0.5,0.9,-0.045,-0.247,0.06
-TiRex,FlowState,0.7,0.5,0.9,0.003,-0.19,0.122
-TiRex,Moirai-2.0,0.9,0.75,1.0,0.043,0.019,0.07
-TiRex,PatchTST,0.8,0.6,0.95,0.075,-0.133,0.211
-TiRex,TFT,0.85,0.7,0.95,0.162,0.034,0.285
-TiRex,Chronos-Bolt,0.9,0.75,1.0,0.11,0.064,0.155
-TiRex,Seasonal Naive,1.0,1.0,1.0,0.627,0.54,0.71
-TabPFN-TS-3,Toto-2.0-2.5B,0.05,0.0,0.15,-0.151,-0.285,-0.049
-TabPFN-TS-3,Toto-2.0-1B,0.05,0.0,0.15,-0.141,-0.286,-0.025
-TabPFN-TS-3,Toto-2.0-313m,0.05,0.0,0.15,-0.128,-0.282,0.005
-TabPFN-TS-3,Toto-2.0-22m,0.1,0.0,0.25,-0.073,-0.202,0.069
-TabPFN-TS-3,Chronos-2,0.1,0.0,0.25,-0.078,-0.172,-0.012
-TabPFN-TS-3,Toto-1.0,0.2,0.05,0.4,-0.003,-0.146,0.175
-TabPFN-TS-3,Toto-2.0-4m,0.25,0.05,0.45,-0.002,-0.123,0.154
-TabPFN-TS-3,TiRex-2,0.25,0.1,0.4,0.01,-0.124,0.172
-TabPFN-TS-3,TimesFM-2.5,0.4,0.2,0.6,0.017,-0.077,0.13
-TabPFN-TS-3,TiRex,0.3,0.1,0.5,0.043,-0.064,0.198
-TabPFN-TS-3,TabPFN-TS-3,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS-3,FlowState,0.5,0.3,0.7,0.046,-0.042,0.123
-TabPFN-TS-3,Moirai-2.0,0.6,0.399,0.8,0.084,-0.013,0.224
-TabPFN-TS-3,PatchTST,0.7,0.5,0.9,0.115,0.011,0.208
-TabPFN-TS-3,TFT,0.7,0.5,0.9,0.198,0.019,0.365
-TabPFN-TS-3,Chronos-Bolt,0.85,0.65,1.0,0.148,0.036,0.276
-TabPFN-TS-3,Seasonal Naive,1.0,1.0,1.0,0.644,0.549,0.724
-FlowState,Toto-2.0-2.5B,0.05,0.0,0.15,-0.206,-0.343,-0.092
-FlowState,Toto-2.0-1B,0.05,0.0,0.15,-0.195,-0.34,-0.073
-FlowState,Toto-2.0-313m,0.05,0.0,0.15,-0.182,-0.334,-0.047
-FlowState,Toto-2.0-22m,0.1,0.0,0.25,-0.124,-0.271,0.021
-FlowState,Chronos-2,0.15,0.0,0.35,-0.13,-0.232,-0.053
-FlowState,Toto-1.0,0.25,0.1,0.45,-0.051,-0.217,0.116
-FlowState,Toto-2.0-4m,0.15,0.0,0.3,-0.05,-0.194,0.113
-FlowState,TiRex-2,0.25,0.05,0.45,-0.037,-0.184,0.131
-FlowState,TimesFM-2.5,0.3,0.1,0.5,-0.03,-0.137,0.094
-FlowState,TiRex,0.3,0.1,0.5,-0.003,-0.139,0.159
-FlowState,TabPFN-TS-3,0.5,0.3,0.7,-0.048,-0.141,0.04
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,Moirai-2.0,0.5,0.25,0.7,0.04,-0.089,0.189
-FlowState,PatchTST,0.6,0.4,0.8,0.073,-0.056,0.185
-FlowState,TFT,0.65,0.45,0.85,0.16,-0.028,0.323
-FlowState,Chronos-Bolt,0.8,0.649,0.95,0.107,0.023,0.228
-FlowState,Seasonal Naive,1.0,1.0,1.0,0.626,0.538,0.704
-Moirai-2.0,Toto-2.0-2.5B,0.0,0.0,0.0,-0.257,-0.404,-0.148
-Moirai-2.0,Toto-2.0-1B,0.0,0.0,0.0,-0.245,-0.387,-0.143
-Moirai-2.0,Toto-2.0-313m,0.0,0.0,0.0,-0.232,-0.35,-0.142
-Moirai-2.0,Toto-2.0-22m,0.0,0.0,0.0,-0.171,-0.257,-0.105
-Moirai-2.0,Chronos-2,0.0,0.0,0.0,-0.177,-0.33,-0.071
-Moirai-2.0,Toto-1.0,0.15,0.0,0.3,-0.095,-0.17,-0.03
-Moirai-2.0,Toto-2.0-4m,0.1,0.0,0.25,-0.094,-0.147,-0.052
-Moirai-2.0,TiRex-2,0.05,0.0,0.15,-0.081,-0.139,-0.043
-Moirai-2.0,TimesFM-2.5,0.15,0.0,0.35,-0.074,-0.131,-0.029
-Moirai-2.0,TiRex,0.1,0.0,0.25,-0.044,-0.075,-0.02
-Moirai-2.0,TabPFN-TS-3,0.4,0.2,0.601,-0.092,-0.288,0.013
-Moirai-2.0,FlowState,0.5,0.3,0.75,-0.042,-0.233,0.082
-Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
-Moirai-2.0,PatchTST,0.6,0.4,0.8,0.034,-0.175,0.172
-Moirai-2.0,TFT,0.7,0.5,0.9,0.124,-0.012,0.26
-Moirai-2.0,Chronos-Bolt,0.85,0.699,0.975,0.07,0.023,0.118
-Moirai-2.0,Seasonal Naive,1.0,1.0,1.0,0.611,0.523,0.693
-PatchTST,Toto-2.0-2.5B,0.05,0.0,0.15,-0.301,-0.483,-0.142
-PatchTST,Toto-2.0-1B,0.05,0.0,0.15,-0.289,-0.474,-0.119
-PatchTST,Toto-2.0-313m,0.05,0.0,0.15,-0.275,-0.467,-0.091
-PatchTST,Toto-2.0-22m,0.05,0.0,0.15,-0.213,-0.392,-0.029
-PatchTST,Chronos-2,0.15,0.0,0.3,-0.219,-0.369,-0.087
-PatchTST,Toto-1.0,0.1,0.0,0.25,-0.134,-0.327,0.072
-PatchTST,Toto-2.0-4m,0.05,0.0,0.15,-0.133,-0.303,0.062
-PatchTST,TiRex-2,0.1,0.0,0.25,-0.119,-0.302,0.088
-PatchTST,TimesFM-2.5,0.15,0.0,0.3,-0.112,-0.262,0.042
-PatchTST,TiRex,0.2,0.05,0.4,-0.081,-0.267,0.118
-PatchTST,TabPFN-TS-3,0.3,0.1,0.5,-0.13,-0.262,-0.011
-PatchTST,FlowState,0.4,0.2,0.6,-0.079,-0.227,0.053
-PatchTST,Moirai-2.0,0.4,0.2,0.6,-0.035,-0.208,0.149
-PatchTST,PatchTST,0.5,0.5,0.5,0.0,0.0,0.0
-PatchTST,TFT,0.425,0.225,0.625,0.093,-0.057,0.271
-PatchTST,Chronos-Bolt,0.6,0.4,0.8,0.037,-0.124,0.209
-PatchTST,Seasonal Naive,0.9,0.75,1.0,0.597,0.477,0.698
-TFT,Toto-2.0-2.5B,0.0,0.0,0.0,-0.435,-0.762,-0.215
-TFT,Toto-2.0-1B,0.0,0.0,0.0,-0.422,-0.733,-0.214
-TFT,Toto-2.0-313m,0.0,0.0,0.0,-0.407,-0.717,-0.209
-TFT,Toto-2.0-22m,0.0,0.0,0.0,-0.338,-0.598,-0.163
-TFT,Chronos-2,0.05,0.0,0.15,-0.344,-0.652,-0.133
-TFT,Toto-1.0,0.0,0.0,0.0,-0.251,-0.415,-0.121
-TFT,Toto-2.0-4m,0.1,0.0,0.25,-0.249,-0.449,-0.099
-TFT,TiRex-2,0.15,0.05,0.3,-0.234,-0.453,-0.079
-TFT,TimesFM-2.5,0.2,0.05,0.4,-0.226,-0.442,-0.064
-TFT,TiRex,0.15,0.05,0.3,-0.193,-0.399,-0.035
-TFT,TabPFN-TS-3,0.3,0.1,0.5,-0.247,-0.574,-0.019
-TFT,FlowState,0.35,0.15,0.55,-0.19,-0.477,0.027
-TFT,Moirai-2.0,0.3,0.1,0.5,-0.142,-0.351,0.012
-TFT,PatchTST,0.575,0.375,0.775,-0.103,-0.372,0.054
-TFT,TFT,0.5,0.5,0.5,0.0,0.0,0.0
-TFT,Chronos-Bolt,0.5,0.3,0.7,-0.062,-0.262,0.087
-TFT,Seasonal Naive,0.9,0.75,1.0,0.556,0.443,0.658
-Chronos-Bolt,Toto-2.0-2.5B,0.0,0.0,0.0,-0.351,-0.498,-0.233
-Chronos-Bolt,Toto-2.0-1B,0.0,0.0,0.0,-0.339,-0.471,-0.228
-Chronos-Bolt,Toto-2.0-313m,0.0,0.0,0.0,-0.325,-0.437,-0.227
-Chronos-Bolt,Toto-2.0-22m,0.0,0.0,0.0,-0.26,-0.345,-0.186
-Chronos-Bolt,Chronos-2,0.0,0.0,0.0,-0.266,-0.429,-0.154
-Chronos-Bolt,Toto-1.0,0.05,0.0,0.15,-0.177,-0.267,-0.098
-Chronos-Bolt,Toto-2.0-4m,0.0,0.0,0.0,-0.176,-0.246,-0.12
-Chronos-Bolt,TiRex-2,0.0,0.0,0.0,-0.162,-0.227,-0.11
-Chronos-Bolt,TimesFM-2.5,0.1,0.0,0.25,-0.154,-0.218,-0.101
-Chronos-Bolt,TiRex,0.1,0.0,0.25,-0.123,-0.183,-0.069
-Chronos-Bolt,TabPFN-TS-3,0.15,0.0,0.35,-0.174,-0.382,-0.037
-Chronos-Bolt,FlowState,0.2,0.05,0.351,-0.12,-0.295,-0.023
-Chronos-Bolt,Moirai-2.0,0.15,0.025,0.301,-0.075,-0.134,-0.024
-Chronos-Bolt,PatchTST,0.4,0.2,0.6,-0.039,-0.264,0.11
-Chronos-Bolt,TFT,0.5,0.3,0.7,0.059,-0.096,0.207
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,Seasonal Naive,1.0,1.0,1.0,0.582,0.486,0.675
-Seasonal Naive,Toto-2.0-2.5B,0.0,0.0,0.0,-2.229,-3.277,-1.556
-Seasonal Naive,Toto-2.0-1B,0.0,0.0,0.0,-2.201,-3.228,-1.546
-Seasonal Naive,Toto-2.0-313m,0.0,0.0,0.0,-2.166,-3.211,-1.516
-Seasonal Naive,Toto-2.0-22m,0.0,0.0,0.0,-2.011,-2.926,-1.406
-Seasonal Naive,Chronos-2,0.0,0.0,0.0,-2.025,-2.936,-1.394
-Seasonal Naive,Toto-1.0,0.0,0.0,0.0,-1.814,-2.639,-1.287
-Seasonal Naive,Toto-2.0-4m,0.0,0.0,0.0,-1.811,-2.664,-1.269
-Seasonal Naive,TiRex-2,0.0,0.0,0.0,-1.778,-2.67,-1.221
-Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-1.759,-2.495,-1.259
-Seasonal Naive,TiRex,0.0,0.0,0.0,-1.684,-2.448,-1.175
-Seasonal Naive,TabPFN-TS-3,0.0,0.0,0.0,-1.806,-2.622,-1.215
-Seasonal Naive,FlowState,0.0,0.0,0.0,-1.677,-2.381,-1.163
-Seasonal Naive,Moirai-2.0,0.0,0.0,0.0,-1.57,-2.259,-1.095
-Seasonal Naive,PatchTST,0.1,0.0,0.25,-1.482,-2.307,-0.914
-Seasonal Naive,TFT,0.1,0.0,0.25,-1.25,-1.926,-0.795
-Seasonal Naive,Chronos-Bolt,0.0,0.0,0.0,-1.39,-2.073,-0.945
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_econ/leaderboard_MASE.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-TiRex-2,89.50617283950616,40.553930524399625,0.0,0.11294837920086495,0.0,0.0
-Stat. Ensemble,79.320987654321,38.47702197421158,0.0,73.43481351955408,0.0,0.0
-Toto-2.0-22m,74.69135802469134,37.883510512986405,0.0,0.2300832338301921,0.0,0.0
-Toto-2.0-1B,72.83950617283949,37.647796213911036,0.0,2.4167769806179775,0.0,0.0
-Toto-2.0-313m,70.06172839506173,37.637104246897856,0.0,0.9865880503225806,0.0,0.0
-Toto-2.0-2.5B,69.7530864197531,37.649421436010044,0.0,5.236902611304615,0.0,0.0
-TiRex,67.59259259259261,36.87592044073875,0.0,0.16472977363175062,0.0,0.0
-Chronos-2,67.5925925925926,36.307128273958256,0.0,0.14791438772454144,0.0,0.0
-LightGBM,66.358024691358,36.739370201928836,0.20454036927361854,0.03409663050126502,0.0,0.0
-AutoETS,63.58024691358024,35.908870624227376,0.0,1.5253584038361796,0.0,0.0
-FlowState,62.34567901234568,35.21482359572895,0.0,0.8205954025996205,0.16666666666666666,0.0
-CatBoost,61.41975308641976,35.982559330359685,3.42108969184492,0.03905346701454776,0.0,0.0
-Toto-2.0-4m,56.48148148148149,35.180832137280916,0.0,0.1810118077664009,0.0,0.0
-Toto-1.0,56.172839506172835,32.41516602344565,0.0,5.0937543479594325,0.16666666666666666,0.0
-AutoARIMA,52.160493827160494,33.893658085803416,0.0,6.5345976113161015,0.0,0.0
-TabPFN-TS,48.76543209876543,34.19057001716027,0.0,52.326198869129215,0.0,0.0
-AutoTheta,48.456790123456784,32.52926186802178,0.0,0.9578271612919038,0.0,0.0
-Drift,46.29629629629629,29.639454067966152,0.0,0.4198026182352941,0.0,0.0
-TimesFM-2.5,45.98765432098766,32.83344751489832,0.0,0.3095206282094962,0.16666666666666666,0.0
-Chronos-Bolt,36.111111111111114,30.133730029400986,0.0,0.1587546411616528,0.0,0.0
-TabPFN-TS-3,36.11111111111111,28.575629786307356,0.0,190.9822121554963,0.0,0.0
-Moirai-2.0,35.49382716049383,28.236498726126015,0.0,0.21986280235955058,0.16666666666666666,0.0
-DeepAR,27.469135802469136,24.302560020818376,546.7685936688092,0.18274403532732447,0.0,0.0
-Sundial-Base,19.444444444444443,19.70951503418047,0.0,8.00438149490214,0.0,0.0
-PatchTST,14.506172839506174,15.279108700450617,310.3190003231231,0.1605401314516129,0.0,0.0
-Naive,13.271604938271608,15.593612422240255,0.0,0.46331807906862743,0.0,0.0
-TFT,11.111111111111112,9.838087249658834,445.02348117965687,0.18857640938013914,0.0,0.0
-Seasonal Naive,7.098765432098765,0.0,0.0,0.41450250024509805,0.0,0.0

tables/domain_econ/leaderboard_SQL.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-TiRex-2,92.90123456790123,41.37587435805797,0.0,0.11294837920086495,0.0,0.0
-Chronos-2,78.08641975308643,37.73601252203713,0.0,0.14791438772454144,0.0,0.0
-Toto-2.0-2.5B,78.08641975308642,38.54527045088485,0.0,5.236902611304615,0.0,0.0
-TiRex,77.77777777777779,38.16787226217255,0.0,0.16472977363175062,0.0,0.0
-Toto-2.0-1B,77.77777777777779,38.30540837943911,0.0,2.4167769806179775,0.0,0.0
-Toto-2.0-22m,77.46913580246914,38.28322277552283,0.0,0.2300832338301921,0.0,0.0
-Toto-2.0-313m,77.46913580246914,38.27714813601945,0.0,0.9865880503225806,0.0,0.0
-Stat. Ensemble,70.67901234567903,37.119576639717835,0.0,73.43481351955408,0.0,0.0
-FlowState,66.35802469135803,35.273957411546085,0.0,0.8205954025996205,0.16666666666666666,0.0
-Toto-2.0-4m,62.96296296296296,35.90432755342822,0.0,0.1810118077664009,0.0,0.0
-Toto-1.0,59.56790123456791,33.496371356107844,0.0,5.0937543479594325,0.16666666666666666,0.0
-TabPFN-TS,59.5679012345679,35.173459448094114,0.0,52.326198869129215,0.0,0.0
-AutoETS,56.79012345679012,29.18586393990128,0.0,1.5253584038361796,0.0,0.0
-TimesFM-2.5,50.92592592592594,32.772070331944484,0.0,0.3095206282094962,0.16666666666666666,0.0
-AutoARIMA,48.76543209876543,31.72145242450589,0.0,6.5345976113161015,0.0,0.0
-Chronos-Bolt,47.22222222222223,31.81815534740079,0.0,0.1587546411616528,0.0,0.0
-Moirai-2.0,40.74074074074074,29.079628766325204,0.0,0.21986280235955058,0.16666666666666666,0.0
-AutoTheta,40.123456790123456,29.61896808086114,0.0,0.9578271612919038,0.0,0.0
-Drift,39.50617283950618,25.58270375016218,0.0,0.4198026182352941,0.0,0.0
-TabPFN-TS-3,39.19753086419753,29.19971717461506,0.0,190.9822121554963,0.0,0.0
-DeepAR,37.03703703703703,25.12762288287479,546.7685936688092,0.18274403532732447,0.0,0.0
-LightGBM,27.777777777777775,24.325044506495818,0.20454036927361854,0.03409663050126502,0.0,0.0
-CatBoost,22.839506172839506,23.419716355230047,3.42108969184492,0.03905346701454776,0.0,0.0
-PatchTST,19.753086419753085,16.930294384775955,310.3190003231231,0.1605401314516129,0.0,0.0
-Sundial-Base,15.74074074074074,14.510260955147846,0.0,8.00438149490214,0.0,0.0
-Naive,13.88888888888889,11.510640002523509,0.0,0.46331807906862743,0.0,0.0
-TFT,13.580246913580249,9.329379481293765,445.02348117965687,0.18857640938013914,0.0,0.0
-Seasonal Naive,7.4074074074074066,0.0,0.0,0.41450250024509805,0.0,0.0

tables/domain_econ/leaderboard_WAPE.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-TiRex-2,87.96296296296296,42.13247790984753,0.0,0.11294837920086495,0.0,0.0
-Toto-2.0-1B,79.320987654321,38.80502192761649,0.0,2.4167769806179775,0.0,0.0
-Toto-2.0-2.5B,78.39506172839506,39.10703314170318,0.0,5.236902611304615,0.0,0.0
-Toto-2.0-313m,74.38271604938271,38.257695402459,0.0,0.9865880503225806,0.0,0.0
-Toto-2.0-22m,70.98765432098764,37.906655236674865,0.0,0.2300832338301921,0.0,0.0
-TiRex,68.82716049382715,37.758720587285445,0.0,0.16472977363175062,0.0,0.0
-Stat. Ensemble,64.50617283950618,38.177219528557146,0.0,73.43481351955408,0.0,0.0
-Chronos-2,63.271604938271594,36.558735189016225,0.0,0.14791438772454144,0.0,0.0
-Toto-1.0,58.95061728395062,33.97875884401389,0.0,5.0937543479594325,0.16666666666666666,0.0
-TimesFM-2.5,58.64197530864198,35.89256072267927,0.0,0.3095206282094962,0.16666666666666666,0.0
-TabPFN-TS,58.0246913580247,36.531743334435674,0.0,52.326198869129215,0.0,0.0
-FlowState,57.098765432098766,37.645403955852096,0.0,0.8205954025996205,0.16666666666666666,0.0
-CatBoost,55.24691358024691,35.20082715344605,3.42108969184492,0.03905346701454776,0.0,0.0
-Toto-2.0-4m,53.70370370370371,33.31225235226658,0.0,0.1810118077664009,0.0,0.0
-AutoETS,53.703703703703695,34.84116662551825,0.0,1.5253584038361796,0.0,0.0
-LightGBM,52.160493827160494,35.02206834104291,0.20454036927361854,0.03409663050126502,0.0,0.0
-AutoARIMA,48.76543209876543,35.732170334358024,0.0,6.5345976113161015,0.0,0.0
-Chronos-Bolt,45.37037037037037,30.478143266802604,0.0,0.1587546411616528,0.0,0.0
-TabPFN-TS-3,44.1358024691358,29.457560079978773,0.0,190.9822121554963,0.0,0.0
-Moirai-2.0,43.51851851851852,28.277512977220987,0.0,0.21986280235955058,0.16666666666666666,0.0
-Drift,41.66666666666666,28.435824921980835,0.0,0.4198026182352941,0.0,0.0
-AutoTheta,41.66666666666666,31.812923074763923,0.0,0.9578271612919038,0.0,0.0
-Naive,19.444444444444446,15.872310498117715,0.0,0.46331807906862743,0.0,0.0
-Sundial-Base,18.827160493827154,17.737235971841127,0.0,8.00438149490214,0.0,0.0
-PatchTST,17.59259259259259,15.619782622761335,310.3190003231231,0.1605401314516129,0.0,0.0
-DeepAR,17.59259259259259,19.60425306556468,546.7685936688092,0.18274403532732447,0.0,0.0
-TFT,15.432098765432098,6.946074243338563,445.02348117965687,0.18857640938013914,0.0,0.0
-Seasonal Naive,10.80246913580247,0.0,0.0,0.41450250024509805,0.0,0.0

tables/domain_econ/leaderboard_WQL.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-TiRex-2,89.50617283950616,45.53906787899109,0.0,0.11294837920086495,0.0,0.0
-Toto-2.0-1B,81.17283950617283,42.35200647023204,0.0,2.4167769806179775,0.0,0.0
-Toto-2.0-2.5B,79.93827160493827,42.8032329067254,0.0,5.236902611304615,0.0,0.0
-Toto-2.0-313m,75.61728395061728,42.088190864136244,0.0,0.9865880503225806,0.0,0.0
-Toto-2.0-22m,75.0,42.320942130283335,0.0,0.2300832338301921,0.0,0.0
-TiRex,75.0,42.09146596586096,0.0,0.16472977363175062,0.0,0.0
-Chronos-2,70.06172839506173,40.960757337476025,0.0,0.14791438772454144,0.0,0.0
-FlowState,64.81481481481482,40.9054936267241,0.0,0.8205954025996205,0.16666666666666666,0.0
-TabPFN-TS,62.65432098765431,40.20371520247606,0.0,52.326198869129215,0.0,0.0
-Toto-1.0,62.34567901234568,38.100769058535434,0.0,5.0937543479594325,0.16666666666666666,0.0
-TimesFM-2.5,61.111111111111114,39.266493040907115,0.0,0.3095206282094962,0.16666666666666666,0.0
-Toto-2.0-4m,60.493827160493844,38.36462827294697,0.0,0.1810118077664009,0.0,0.0
-Stat. Ensemble,58.333333333333336,37.992090519620156,0.0,73.43481351955408,0.0,0.0
-Chronos-Bolt,52.77777777777777,35.534952430792764,0.0,0.1587546411616528,0.0,0.0
-AutoETS,52.160493827160494,36.76571988294681,0.0,1.5253584038361796,0.0,0.0
-TabPFN-TS-3,49.691358024691354,34.00880337940215,0.0,190.9822121554963,0.0,0.0
-Moirai-2.0,47.83950617283951,32.793225265991246,0.0,0.21986280235955058,0.16666666666666666,0.0
-AutoARIMA,46.60493827160494,34.44615311952015,0.0,6.5345976113161015,0.0,0.0
-AutoTheta,37.345679012345684,29.146207850323268,0.0,0.9578271612919038,0.0,0.0
-Drift,31.481481481481477,23.828649343246187,0.0,0.4198026182352941,0.0,0.0
-LightGBM,26.851851851851844,25.89068156049532,0.20454036927361854,0.03409663050126502,0.0,0.0
-CatBoost,26.851851851851844,26.0945614678313,3.42108969184492,0.03905346701454776,0.0,0.0
-DeepAR,26.234567901234566,21.869167576579297,546.7685936688092,0.18274403532732447,0.0,0.0
-PatchTST,22.8395061728395,19.911167839333967,310.3190003231231,0.1605401314516129,0.0,0.0
-Sundial-Base,18.827160493827154,17.532849869365606,0.0,8.00438149490214,0.0,0.0
-TFT,16.666666666666664,9.939963215759995,445.02348117965687,0.18857640938013914,0.0,0.0
-Naive,16.358024691358022,11.371958531244664,0.0,0.46331807906862743,0.0,0.0
-Seasonal Naive,11.419753086419755,0.0,0.0,0.41450250024509805,0.0,0.0

tables/domain_econ/pairwise_MASE.csv

@@ -1,290 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,Stat. Ensemble,0.583,0.25,0.833,0.034,-0.011,0.076
-TiRex-2,Toto-2.0-22m,0.75,0.5,0.917,0.043,0.018,0.069
-TiRex-2,Toto-2.0-1B,0.833,0.583,1.0,0.047,0.018,0.074
-TiRex-2,Toto-2.0-313m,0.833,0.583,1.0,0.047,0.02,0.07
-TiRex-2,Toto-2.0-2.5B,0.833,0.583,1.0,0.047,0.015,0.075
-TiRex-2,Chronos-2,0.833,0.583,1.0,0.067,0.014,0.124
-TiRex-2,TiRex,1.0,1.0,1.0,0.058,0.032,0.092
-TiRex-2,LightGBM,0.917,0.75,1.0,0.06,0.015,0.103
-TiRex-2,AutoETS,0.917,0.75,1.0,0.072,0.036,0.112
-TiRex-2,FlowState,0.833,0.583,1.0,0.082,0.013,0.144
-TiRex-2,CatBoost,0.833,0.583,1.0,0.071,0.024,0.117
-TiRex-2,Toto-1.0,0.833,0.583,1.0,0.12,0.051,0.194
-TiRex-2,Toto-2.0-4m,0.917,0.75,1.0,0.083,0.049,0.122
-TiRex-2,AutoARIMA,0.917,0.75,1.0,0.101,0.036,0.173
-TiRex-2,Chronos-Bolt,1.0,1.0,1.0,0.149,0.095,0.205
-TiRex-2,Seasonal Naive,1.0,1.0,1.0,0.406,0.298,0.505
-Stat. Ensemble,TiRex-2,0.417,0.167,0.75,-0.035,-0.083,0.011
-Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
-Stat. Ensemble,Toto-2.0-22m,0.5,0.248,0.75,0.01,-0.034,0.052
-Stat. Ensemble,Toto-2.0-1B,0.5,0.25,0.75,0.013,-0.041,0.068
-Stat. Ensemble,Toto-2.0-313m,0.583,0.25,0.833,0.013,-0.039,0.064
-Stat. Ensemble,Toto-2.0-2.5B,0.667,0.417,0.917,0.013,-0.041,0.064
-Stat. Ensemble,Chronos-2,0.75,0.5,1.0,0.034,-0.014,0.087
-Stat. Ensemble,TiRex,0.75,0.5,1.0,0.025,-0.023,0.072
-Stat. Ensemble,LightGBM,0.75,0.5,1.0,0.027,-0.0,0.06
-Stat. Ensemble,AutoETS,0.75,0.5,1.0,0.04,0.016,0.067
-Stat. Ensemble,FlowState,0.667,0.417,0.917,0.05,-0.001,0.104
-Stat. Ensemble,CatBoost,0.75,0.5,1.0,0.039,0.005,0.073
-Stat. Ensemble,Toto-1.0,0.75,0.417,1.0,0.09,0.024,0.151
-Stat. Ensemble,Toto-2.0-4m,0.667,0.333,0.917,0.051,0.007,0.097
-Stat. Ensemble,AutoARIMA,0.833,0.583,1.0,0.069,0.021,0.135
-Stat. Ensemble,Chronos-Bolt,0.917,0.75,1.0,0.119,0.068,0.168
-Stat. Ensemble,Seasonal Naive,1.0,1.0,1.0,0.385,0.289,0.476
-Toto-2.0-22m,TiRex-2,0.25,0.083,0.5,-0.045,-0.074,-0.018
-Toto-2.0-22m,Stat. Ensemble,0.5,0.25,0.752,-0.01,-0.055,0.033
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,Toto-2.0-1B,0.417,0.167,0.667,0.004,-0.028,0.04
-Toto-2.0-22m,Toto-2.0-313m,0.583,0.333,0.833,0.004,-0.023,0.031
-Toto-2.0-22m,Toto-2.0-2.5B,0.583,0.333,0.833,0.004,-0.029,0.034
-Toto-2.0-22m,Chronos-2,0.583,0.25,0.833,0.025,-0.041,0.081
-Toto-2.0-22m,TiRex,0.583,0.25,0.833,0.016,-0.02,0.048
-Toto-2.0-22m,LightGBM,0.667,0.417,0.917,0.018,-0.021,0.053
-Toto-2.0-22m,AutoETS,0.667,0.333,0.917,0.031,-0.008,0.068
-Toto-2.0-22m,FlowState,0.667,0.417,0.917,0.041,-0.025,0.105
-Toto-2.0-22m,CatBoost,0.667,0.417,0.917,0.03,-0.012,0.069
-Toto-2.0-22m,Toto-1.0,0.75,0.5,1.0,0.081,0.012,0.155
-Toto-2.0-22m,Toto-2.0-4m,1.0,1.0,1.0,0.042,0.025,0.061
-Toto-2.0-22m,AutoARIMA,0.667,0.417,0.917,0.06,-0.015,0.145
-Toto-2.0-22m,Chronos-Bolt,1.0,1.0,1.0,0.111,0.063,0.16
-Toto-2.0-22m,Seasonal Naive,1.0,1.0,1.0,0.379,0.266,0.482
-Toto-2.0-1B,TiRex-2,0.167,0.0,0.417,-0.049,-0.08,-0.018
-Toto-2.0-1B,Stat. Ensemble,0.5,0.25,0.75,-0.013,-0.073,0.039
-Toto-2.0-1B,Toto-2.0-22m,0.583,0.333,0.833,-0.004,-0.041,0.028
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-313m,0.667,0.417,0.917,0.0,-0.011,0.011
-Toto-2.0-1B,Toto-2.0-2.5B,0.583,0.333,0.833,-0.0,-0.013,0.013
-Toto-2.0-1B,Chronos-2,0.5,0.25,0.752,0.021,-0.027,0.076
-Toto-2.0-1B,TiRex,0.667,0.417,0.917,0.012,-0.019,0.044
-Toto-2.0-1B,LightGBM,0.583,0.333,0.833,0.014,-0.046,0.063
-Toto-2.0-1B,AutoETS,0.667,0.417,0.917,0.027,-0.016,0.071
-Toto-2.0-1B,FlowState,0.667,0.417,0.917,0.038,-0.045,0.096
-Toto-2.0-1B,CatBoost,0.75,0.5,1.0,0.026,-0.035,0.074
-Toto-2.0-1B,Toto-1.0,0.583,0.25,0.833,0.077,0.011,0.152
-Toto-2.0-1B,Toto-2.0-4m,0.833,0.583,1.0,0.038,-0.006,0.081
-Toto-2.0-1B,AutoARIMA,0.833,0.583,1.0,0.057,-0.021,0.126
-Toto-2.0-1B,Chronos-Bolt,0.833,0.583,1.0,0.108,0.058,0.154
-Toto-2.0-1B,Seasonal Naive,0.917,0.75,1.0,0.376,0.262,0.473
-Toto-2.0-313m,TiRex-2,0.167,0.0,0.417,-0.049,-0.076,-0.021
-Toto-2.0-313m,Stat. Ensemble,0.417,0.167,0.75,-0.014,-0.068,0.037
-Toto-2.0-313m,Toto-2.0-22m,0.417,0.167,0.667,-0.004,-0.032,0.023
-Toto-2.0-313m,Toto-2.0-1B,0.333,0.083,0.583,-0.0,-0.011,0.011
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,Toto-2.0-2.5B,0.5,0.25,0.75,-0.0,-0.009,0.01
-Toto-2.0-313m,Chronos-2,0.417,0.167,0.75,0.021,-0.03,0.075
-Toto-2.0-313m,TiRex,0.583,0.333,0.833,0.012,-0.013,0.041
-Toto-2.0-313m,LightGBM,0.667,0.417,0.917,0.014,-0.041,0.063
-Toto-2.0-313m,AutoETS,0.5,0.25,0.752,0.027,-0.011,0.069
-Toto-2.0-313m,FlowState,0.667,0.417,0.917,0.037,-0.043,0.1
-Toto-2.0-313m,CatBoost,0.667,0.417,0.917,0.026,-0.03,0.075
-Toto-2.0-313m,Toto-1.0,0.583,0.25,0.833,0.077,0.006,0.155
-Toto-2.0-313m,Toto-2.0-4m,0.667,0.417,0.917,0.038,0.001,0.08
-Toto-2.0-313m,AutoARIMA,0.75,0.5,1.0,0.057,-0.022,0.132
-Toto-2.0-313m,Chronos-Bolt,0.917,0.75,1.0,0.107,0.058,0.157
-Toto-2.0-313m,Seasonal Naive,1.0,1.0,1.0,0.376,0.262,0.475
-Toto-2.0-2.5B,TiRex-2,0.167,0.0,0.417,-0.049,-0.082,-0.015
-Toto-2.0-2.5B,Stat. Ensemble,0.333,0.083,0.583,-0.013,-0.068,0.039
-Toto-2.0-2.5B,Toto-2.0-22m,0.417,0.167,0.667,-0.004,-0.035,0.028
-Toto-2.0-2.5B,Toto-2.0-1B,0.417,0.167,0.667,0.0,-0.014,0.013
-Toto-2.0-2.5B,Toto-2.0-313m,0.5,0.25,0.75,0.0,-0.01,0.009
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,Chronos-2,0.417,0.167,0.75,0.021,-0.024,0.072
-Toto-2.0-2.5B,TiRex,0.583,0.333,0.833,0.012,-0.011,0.037
-Toto-2.0-2.5B,LightGBM,0.667,0.417,0.917,0.014,-0.043,0.067
-Toto-2.0-2.5B,AutoETS,0.583,0.333,0.833,0.027,-0.011,0.068
-Toto-2.0-2.5B,FlowState,0.667,0.417,0.917,0.038,-0.043,0.103
-Toto-2.0-2.5B,CatBoost,0.667,0.417,0.917,0.026,-0.033,0.076
-Toto-2.0-2.5B,Toto-1.0,0.583,0.25,0.833,0.077,0.001,0.158
-Toto-2.0-2.5B,Toto-2.0-4m,0.667,0.417,0.917,0.038,-0.002,0.085
-Toto-2.0-2.5B,AutoARIMA,0.75,0.5,1.0,0.057,-0.023,0.135
-Toto-2.0-2.5B,Chronos-Bolt,0.917,0.75,1.0,0.108,0.058,0.156
-Toto-2.0-2.5B,Seasonal Naive,0.917,0.75,1.0,0.376,0.263,0.471
-Chronos-2,TiRex-2,0.167,0.0,0.417,-0.071,-0.141,-0.014
-Chronos-2,Stat. Ensemble,0.25,0.0,0.5,-0.035,-0.095,0.014
-Chronos-2,Toto-2.0-22m,0.417,0.167,0.75,-0.025,-0.088,0.039
-Chronos-2,Toto-2.0-1B,0.5,0.248,0.75,-0.022,-0.082,0.027
-Chronos-2,Toto-2.0-313m,0.583,0.25,0.833,-0.021,-0.081,0.029
-Chronos-2,Toto-2.0-2.5B,0.583,0.25,0.833,-0.022,-0.077,0.024
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,TiRex,0.417,0.167,0.667,-0.009,-0.045,0.026
-Chronos-2,LightGBM,0.5,0.25,0.75,-0.007,-0.068,0.055
-Chronos-2,AutoETS,0.5,0.25,0.75,0.006,-0.027,0.041
-Chronos-2,FlowState,0.5,0.25,0.75,0.017,-0.064,0.092
-Chronos-2,CatBoost,0.583,0.333,0.833,0.005,-0.055,0.067
-Chronos-2,Toto-1.0,0.583,0.333,0.833,0.058,-0.037,0.145
-Chronos-2,Toto-2.0-4m,0.583,0.333,0.833,0.017,-0.054,0.091
-Chronos-2,AutoARIMA,0.667,0.417,0.917,0.037,-0.046,0.122
-Chronos-2,Chronos-Bolt,1.0,1.0,1.0,0.088,0.044,0.143
-Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.363,0.264,0.451
-TiRex,TiRex-2,0.0,0.0,0.0,-0.062,-0.101,-0.033
-TiRex,Stat. Ensemble,0.25,0.0,0.5,-0.026,-0.078,0.023
-TiRex,Toto-2.0-22m,0.417,0.167,0.75,-0.016,-0.051,0.019
-TiRex,Toto-2.0-1B,0.333,0.083,0.583,-0.012,-0.046,0.018
-TiRex,Toto-2.0-313m,0.417,0.167,0.667,-0.012,-0.043,0.012
-TiRex,Toto-2.0-2.5B,0.417,0.167,0.667,-0.012,-0.038,0.011
-TiRex,Chronos-2,0.583,0.333,0.833,0.009,-0.026,0.043
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,LightGBM,0.5,0.25,0.75,0.002,-0.051,0.049
-TiRex,AutoETS,0.5,0.25,0.75,0.015,-0.013,0.045
-TiRex,FlowState,0.583,0.333,0.833,0.026,-0.05,0.091
-TiRex,CatBoost,0.75,0.5,1.0,0.014,-0.041,0.062
-TiRex,Toto-1.0,0.583,0.333,0.833,0.066,-0.019,0.149
-TiRex,Toto-2.0-4m,0.583,0.333,0.833,0.026,-0.02,0.076
-TiRex,AutoARIMA,0.667,0.417,0.917,0.045,-0.033,0.133
-TiRex,Chronos-Bolt,0.917,0.75,1.0,0.097,0.05,0.149
-TiRex,Seasonal Naive,1.0,1.0,1.0,0.369,0.261,0.466
-LightGBM,TiRex-2,0.083,0.0,0.25,-0.064,-0.114,-0.016
-LightGBM,Stat. Ensemble,0.25,0.0,0.5,-0.028,-0.064,0.0
-LightGBM,Toto-2.0-22m,0.333,0.083,0.583,-0.018,-0.056,0.02
-LightGBM,Toto-2.0-1B,0.417,0.167,0.667,-0.015,-0.068,0.044
-LightGBM,Toto-2.0-313m,0.333,0.083,0.583,-0.014,-0.067,0.04
-LightGBM,Toto-2.0-2.5B,0.333,0.083,0.583,-0.015,-0.072,0.042
-LightGBM,Chronos-2,0.5,0.25,0.75,0.007,-0.059,0.064
-LightGBM,TiRex,0.5,0.25,0.75,-0.002,-0.051,0.049
-LightGBM,LightGBM,0.5,0.5,0.5,0.0,0.0,0.0
-LightGBM,AutoETS,0.667,0.417,0.917,0.013,-0.03,0.049
-LightGBM,FlowState,0.5,0.25,0.75,0.024,-0.019,0.072
-LightGBM,CatBoost,0.75,0.5,1.0,0.012,-0.002,0.026
-LightGBM,Toto-1.0,0.667,0.333,0.917,0.064,-0.009,0.132
-LightGBM,Toto-2.0-4m,0.5,0.25,0.75,0.024,-0.016,0.063
-LightGBM,AutoARIMA,0.5,0.25,0.75,0.043,-0.012,0.11
-LightGBM,Chronos-Bolt,0.917,0.75,1.0,0.095,0.053,0.136
-LightGBM,Seasonal Naive,1.0,1.0,1.0,0.367,0.267,0.458
-AutoETS,TiRex-2,0.083,0.0,0.25,-0.078,-0.126,-0.037
-AutoETS,Stat. Ensemble,0.25,0.0,0.5,-0.042,-0.072,-0.016
-AutoETS,Toto-2.0-22m,0.333,0.083,0.667,-0.032,-0.073,0.008
-AutoETS,Toto-2.0-1B,0.333,0.083,0.583,-0.028,-0.076,0.015
-AutoETS,Toto-2.0-313m,0.5,0.248,0.75,-0.028,-0.074,0.011
-AutoETS,Toto-2.0-2.5B,0.417,0.167,0.667,-0.028,-0.073,0.011
-AutoETS,Chronos-2,0.5,0.25,0.75,-0.006,-0.043,0.026
-AutoETS,TiRex,0.5,0.25,0.75,-0.015,-0.047,0.013
-AutoETS,LightGBM,0.333,0.083,0.583,-0.013,-0.052,0.029
-AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
-AutoETS,FlowState,0.583,0.333,0.833,0.011,-0.051,0.077
-AutoETS,CatBoost,0.417,0.167,0.667,-0.001,-0.04,0.039
-AutoETS,Toto-1.0,0.583,0.333,0.833,0.052,-0.025,0.122
-AutoETS,Toto-2.0-4m,0.583,0.25,0.833,0.011,-0.035,0.059
-AutoETS,AutoARIMA,0.667,0.417,0.917,0.03,-0.036,0.112
-AutoETS,Chronos-Bolt,0.833,0.583,1.0,0.083,0.041,0.127
-AutoETS,Seasonal Naive,1.0,1.0,1.0,0.359,0.256,0.456
-FlowState,TiRex-2,0.167,0.0,0.417,-0.09,-0.168,-0.013
-FlowState,Stat. Ensemble,0.333,0.083,0.583,-0.053,-0.117,0.001
-FlowState,Toto-2.0-22m,0.333,0.083,0.583,-0.043,-0.117,0.025
-FlowState,Toto-2.0-1B,0.333,0.083,0.583,-0.039,-0.107,0.043
-FlowState,Toto-2.0-313m,0.333,0.083,0.583,-0.039,-0.112,0.041
-FlowState,Toto-2.0-2.5B,0.333,0.083,0.583,-0.039,-0.114,0.041
-FlowState,Chronos-2,0.5,0.25,0.75,-0.017,-0.102,0.06
-FlowState,TiRex,0.417,0.167,0.667,-0.026,-0.1,0.048
-FlowState,LightGBM,0.5,0.25,0.75,-0.024,-0.077,0.019
-FlowState,AutoETS,0.417,0.167,0.667,-0.011,-0.083,0.049
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,CatBoost,0.667,0.417,0.917,-0.012,-0.06,0.028
-FlowState,Toto-1.0,0.583,0.292,0.833,0.041,-0.047,0.127
-FlowState,Toto-2.0-4m,0.5,0.25,0.75,0.001,-0.075,0.068
-FlowState,AutoARIMA,0.583,0.333,0.833,0.02,-0.017,0.055
-FlowState,Chronos-Bolt,0.833,0.625,1.0,0.073,0.02,0.125
-FlowState,Seasonal Naive,1.0,1.0,1.0,0.352,0.265,0.429
-CatBoost,TiRex-2,0.167,0.0,0.417,-0.077,-0.133,-0.024
-CatBoost,Stat. Ensemble,0.25,0.0,0.5,-0.041,-0.078,-0.005
-CatBoost,Toto-2.0-22m,0.333,0.083,0.583,-0.031,-0.074,0.012
-CatBoost,Toto-2.0-1B,0.25,0.0,0.5,-0.027,-0.08,0.034
-CatBoost,Toto-2.0-313m,0.333,0.083,0.583,-0.027,-0.081,0.029
-CatBoost,Toto-2.0-2.5B,0.333,0.083,0.583,-0.027,-0.083,0.032
-CatBoost,Chronos-2,0.417,0.167,0.667,-0.005,-0.071,0.052
-CatBoost,TiRex,0.25,0.0,0.5,-0.014,-0.066,0.039
-CatBoost,LightGBM,0.25,0.0,0.5,-0.012,-0.026,0.002
-CatBoost,AutoETS,0.583,0.333,0.833,0.001,-0.041,0.039
-CatBoost,FlowState,0.333,0.083,0.583,0.012,-0.029,0.057
-CatBoost,CatBoost,0.5,0.5,0.5,0.0,0.0,0.0
-CatBoost,Toto-1.0,0.667,0.333,0.917,0.053,-0.022,0.121
-CatBoost,Toto-2.0-4m,0.5,0.25,0.75,0.012,-0.033,0.054
-CatBoost,AutoARIMA,0.583,0.25,0.833,0.032,-0.023,0.093
-CatBoost,Chronos-Bolt,0.917,0.75,1.0,0.084,0.046,0.12
-CatBoost,Seasonal Naive,1.0,1.0,1.0,0.36,0.26,0.448
-Toto-1.0,TiRex-2,0.167,0.0,0.417,-0.137,-0.24,-0.054
-Toto-1.0,Stat. Ensemble,0.25,0.0,0.583,-0.099,-0.177,-0.024
-Toto-1.0,Toto-2.0-22m,0.25,0.0,0.5,-0.088,-0.183,-0.012
-Toto-1.0,Toto-2.0-1B,0.417,0.167,0.75,-0.084,-0.179,-0.012
-Toto-1.0,Toto-2.0-313m,0.417,0.167,0.75,-0.084,-0.184,-0.006
-Toto-1.0,Toto-2.0-2.5B,0.417,0.167,0.75,-0.084,-0.188,-0.001
-Toto-1.0,Chronos-2,0.417,0.167,0.667,-0.061,-0.169,0.035
-Toto-1.0,TiRex,0.417,0.167,0.667,-0.071,-0.175,0.019
-Toto-1.0,LightGBM,0.333,0.083,0.667,-0.068,-0.152,0.009
-Toto-1.0,AutoETS,0.417,0.167,0.667,-0.055,-0.139,0.025
-Toto-1.0,FlowState,0.417,0.167,0.708,-0.043,-0.146,0.045
-Toto-1.0,CatBoost,0.333,0.083,0.667,-0.056,-0.138,0.021
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,Toto-2.0-4m,0.583,0.333,0.833,-0.043,-0.126,0.025
-Toto-1.0,AutoARIMA,0.583,0.333,0.833,-0.022,-0.108,0.05
-Toto-1.0,Chronos-Bolt,0.75,0.5,0.958,0.033,-0.034,0.097
-Toto-1.0,Seasonal Naive,0.917,0.75,1.0,0.324,0.198,0.433
-Toto-2.0-4m,TiRex-2,0.083,0.0,0.25,-0.09,-0.139,-0.051
-Toto-2.0-4m,Stat. Ensemble,0.333,0.083,0.667,-0.054,-0.108,-0.007
-Toto-2.0-4m,Toto-2.0-22m,0.0,0.0,0.0,-0.044,-0.065,-0.026
-Toto-2.0-4m,Toto-2.0-1B,0.167,0.0,0.417,-0.04,-0.088,0.006
-Toto-2.0-4m,Toto-2.0-313m,0.333,0.083,0.583,-0.039,-0.087,-0.001
-Toto-2.0-4m,Toto-2.0-2.5B,0.333,0.083,0.583,-0.04,-0.093,0.002
-Toto-2.0-4m,Chronos-2,0.417,0.167,0.667,-0.018,-0.1,0.051
-Toto-2.0-4m,TiRex,0.417,0.167,0.667,-0.027,-0.082,0.019
-Toto-2.0-4m,LightGBM,0.5,0.25,0.75,-0.025,-0.068,0.016
-Toto-2.0-4m,AutoETS,0.417,0.167,0.75,-0.011,-0.063,0.034
-Toto-2.0-4m,FlowState,0.5,0.25,0.75,-0.001,-0.073,0.07
-Toto-2.0-4m,CatBoost,0.5,0.25,0.75,-0.013,-0.057,0.032
-Toto-2.0-4m,Toto-1.0,0.417,0.167,0.667,0.041,-0.025,0.112
-Toto-2.0-4m,Toto-2.0-4m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-4m,AutoARIMA,0.5,0.25,0.75,0.019,-0.063,0.108
-Toto-2.0-4m,Chronos-Bolt,0.667,0.417,0.917,0.072,0.02,0.128
-Toto-2.0-4m,Seasonal Naive,0.917,0.75,1.0,0.352,0.226,0.462
-AutoARIMA,TiRex-2,0.083,0.0,0.25,-0.112,-0.209,-0.037
-AutoARIMA,Stat. Ensemble,0.167,0.0,0.417,-0.074,-0.156,-0.022
-AutoARIMA,Toto-2.0-22m,0.333,0.083,0.583,-0.064,-0.169,0.015
-AutoARIMA,Toto-2.0-1B,0.167,0.0,0.417,-0.06,-0.145,0.02
-AutoARIMA,Toto-2.0-313m,0.25,0.0,0.5,-0.06,-0.152,0.021
-AutoARIMA,Toto-2.0-2.5B,0.25,0.0,0.5,-0.06,-0.156,0.022
-AutoARIMA,Chronos-2,0.333,0.083,0.583,-0.038,-0.139,0.044
-AutoARIMA,TiRex,0.333,0.083,0.583,-0.047,-0.154,0.032
-AutoARIMA,LightGBM,0.5,0.25,0.75,-0.045,-0.124,0.012
-AutoARIMA,AutoETS,0.333,0.083,0.583,-0.031,-0.126,0.035
-AutoARIMA,FlowState,0.417,0.167,0.667,-0.02,-0.058,0.017
-AutoARIMA,CatBoost,0.417,0.167,0.75,-0.033,-0.102,0.023
-AutoARIMA,Toto-1.0,0.417,0.167,0.667,0.022,-0.052,0.097
-AutoARIMA,Toto-2.0-4m,0.5,0.25,0.75,-0.02,-0.121,0.059
-AutoARIMA,AutoARIMA,0.5,0.5,0.5,0.0,0.0,0.0
-AutoARIMA,Chronos-Bolt,0.667,0.417,0.917,0.054,-0.009,0.113
-AutoARIMA,Seasonal Naive,1.0,1.0,1.0,0.339,0.256,0.422
-Chronos-Bolt,TiRex-2,0.0,0.0,0.0,-0.175,-0.258,-0.106
-Chronos-Bolt,Stat. Ensemble,0.083,0.0,0.25,-0.136,-0.202,-0.073
-Chronos-Bolt,Toto-2.0-22m,0.0,0.0,0.0,-0.125,-0.191,-0.068
-Chronos-Bolt,Toto-2.0-1B,0.167,0.0,0.417,-0.121,-0.182,-0.062
-Chronos-Bolt,Toto-2.0-313m,0.083,0.0,0.25,-0.12,-0.186,-0.062
-Chronos-Bolt,Toto-2.0-2.5B,0.083,0.0,0.25,-0.121,-0.185,-0.061
-Chronos-Bolt,Chronos-2,0.0,0.0,0.0,-0.097,-0.167,-0.046
-Chronos-Bolt,TiRex,0.083,0.0,0.25,-0.107,-0.175,-0.053
-Chronos-Bolt,LightGBM,0.083,0.0,0.25,-0.104,-0.157,-0.056
-Chronos-Bolt,AutoETS,0.167,0.0,0.417,-0.09,-0.145,-0.043
-Chronos-Bolt,FlowState,0.167,0.0,0.375,-0.078,-0.143,-0.02
-Chronos-Bolt,CatBoost,0.083,0.0,0.25,-0.091,-0.136,-0.049
-Chronos-Bolt,Toto-1.0,0.25,0.042,0.5,-0.034,-0.107,0.033
-Chronos-Bolt,Toto-2.0-4m,0.333,0.083,0.583,-0.078,-0.146,-0.021
-Chronos-Bolt,AutoARIMA,0.333,0.083,0.583,-0.057,-0.128,0.009
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,Seasonal Naive,0.833,0.583,1.0,0.301,0.198,0.389
-Seasonal Naive,TiRex-2,0.0,0.0,0.0,-0.682,-1.021,-0.425
-Seasonal Naive,Stat. Ensemble,0.0,0.0,0.0,-0.625,-0.907,-0.407
-Seasonal Naive,Toto-2.0-22m,0.0,0.0,0.0,-0.61,-0.932,-0.362
-Seasonal Naive,Toto-2.0-1B,0.083,0.0,0.25,-0.604,-0.897,-0.355
-Seasonal Naive,Toto-2.0-313m,0.0,0.0,0.0,-0.604,-0.904,-0.354
-Seasonal Naive,Toto-2.0-2.5B,0.083,0.0,0.25,-0.604,-0.891,-0.357
-Seasonal Naive,Chronos-2,0.0,0.0,0.0,-0.57,-0.821,-0.358
-Seasonal Naive,TiRex,0.0,0.0,0.0,-0.584,-0.872,-0.353
-Seasonal Naive,LightGBM,0.0,0.0,0.0,-0.581,-0.845,-0.364
-Seasonal Naive,AutoETS,0.0,0.0,0.0,-0.56,-0.837,-0.345
-Seasonal Naive,FlowState,0.0,0.0,0.0,-0.544,-0.752,-0.36
-Seasonal Naive,CatBoost,0.0,0.0,0.0,-0.562,-0.812,-0.352
-Seasonal Naive,Toto-1.0,0.083,0.0,0.25,-0.48,-0.763,-0.247
-Seasonal Naive,Toto-2.0-4m,0.083,0.0,0.25,-0.543,-0.858,-0.292
-Seasonal Naive,AutoARIMA,0.0,0.0,0.0,-0.513,-0.73,-0.344
-Seasonal Naive,Chronos-Bolt,0.167,0.0,0.417,-0.431,-0.638,-0.246
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_econ/pairwise_SQL.csv

@@ -1,290 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,Toto-2.0-1B,0.833,0.583,1.0,0.05,0.019,0.077
-TiRex-2,TiRex,1.0,1.0,1.0,0.052,0.026,0.086
-TiRex-2,Toto-2.0-2.5B,0.833,0.583,1.0,0.046,0.014,0.077
-TiRex-2,Chronos-2,0.917,0.75,1.0,0.058,0.014,0.109
-TiRex-2,Toto-2.0-22m,0.75,0.5,0.917,0.05,0.023,0.079
-TiRex-2,Toto-2.0-313m,0.833,0.583,1.0,0.05,0.022,0.076
-TiRex-2,Stat. Ensemble,0.833,0.583,1.0,0.068,0.024,0.107
-TiRex-2,FlowState,0.833,0.583,1.0,0.094,0.027,0.152
-TiRex-2,Toto-2.0-4m,0.917,0.75,1.0,0.085,0.049,0.126
-TiRex-2,Toto-1.0,1.0,1.0,1.0,0.118,0.061,0.181
-TiRex-2,TabPFN-TS,0.833,0.583,1.0,0.096,0.05,0.138
-TiRex-2,AutoETS,1.0,1.0,1.0,0.172,0.075,0.301
-TiRex-2,AutoARIMA,0.917,0.75,1.0,0.141,0.074,0.215
-TiRex-2,TimesFM-2.5,0.917,0.75,1.0,0.128,0.08,0.174
-TiRex-2,Chronos-Bolt,1.0,1.0,1.0,0.14,0.09,0.195
-TiRex-2,Seasonal Naive,1.0,1.0,1.0,0.414,0.318,0.502
-Toto-2.0-1B,TiRex-2,0.167,0.0,0.417,-0.052,-0.083,-0.019
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,TiRex,0.5,0.25,0.75,0.002,-0.025,0.032
-Toto-2.0-1B,Toto-2.0-2.5B,0.417,0.167,0.667,-0.004,-0.018,0.01
-Toto-2.0-1B,Chronos-2,0.417,0.167,0.75,0.009,-0.036,0.055
-Toto-2.0-1B,Toto-2.0-22m,0.5,0.167,0.75,0.0,-0.03,0.027
-Toto-2.0-1B,Toto-2.0-313m,0.583,0.333,0.833,0.0,-0.016,0.014
-Toto-2.0-1B,Stat. Ensemble,0.75,0.5,1.0,0.019,-0.04,0.068
-Toto-2.0-1B,FlowState,0.75,0.5,1.0,0.047,-0.032,0.1
-Toto-2.0-1B,Toto-2.0-4m,0.833,0.583,1.0,0.037,-0.006,0.08
-Toto-2.0-1B,Toto-1.0,0.75,0.5,1.0,0.072,0.013,0.134
-Toto-2.0-1B,TabPFN-TS,0.833,0.583,1.0,0.048,-0.007,0.097
-Toto-2.0-1B,AutoETS,0.75,0.5,1.0,0.129,0.018,0.268
-Toto-2.0-1B,AutoARIMA,0.833,0.583,1.0,0.096,0.016,0.174
-Toto-2.0-1B,TimesFM-2.5,0.917,0.75,1.0,0.082,0.045,0.115
-Toto-2.0-1B,Chronos-Bolt,0.833,0.583,1.0,0.095,0.048,0.139
-Toto-2.0-1B,Seasonal Naive,0.917,0.75,1.0,0.383,0.278,0.469
-TiRex,TiRex-2,0.0,0.0,0.0,-0.055,-0.094,-0.027
-TiRex,Toto-2.0-1B,0.5,0.25,0.75,-0.002,-0.033,0.024
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,Toto-2.0-2.5B,0.5,0.25,0.75,-0.006,-0.031,0.017
-TiRex,Chronos-2,0.667,0.417,0.917,0.007,-0.028,0.036
-TiRex,Toto-2.0-22m,0.5,0.25,0.833,-0.002,-0.037,0.033
-TiRex,Toto-2.0-313m,0.417,0.167,0.667,-0.002,-0.03,0.024
-TiRex,Stat. Ensemble,0.75,0.5,1.0,0.017,-0.034,0.06
-TiRex,FlowState,0.833,0.583,1.0,0.045,-0.023,0.098
-TiRex,Toto-2.0-4m,0.667,0.415,0.917,0.035,-0.011,0.083
-TiRex,Toto-1.0,0.667,0.333,0.917,0.07,-0.008,0.143
-TiRex,TabPFN-TS,0.833,0.583,1.0,0.046,0.002,0.086
-TiRex,AutoETS,0.75,0.5,1.0,0.127,0.025,0.268
-TiRex,AutoARIMA,0.833,0.583,1.0,0.094,0.019,0.181
-TiRex,TimesFM-2.5,0.917,0.75,1.0,0.08,0.038,0.122
-TiRex,Chronos-Bolt,0.917,0.75,1.0,0.093,0.05,0.141
-TiRex,Seasonal Naive,1.0,1.0,1.0,0.382,0.282,0.467
-Toto-2.0-2.5B,TiRex-2,0.167,0.0,0.417,-0.048,-0.084,-0.015
-Toto-2.0-2.5B,Toto-2.0-1B,0.583,0.333,0.833,0.004,-0.011,0.018
-Toto-2.0-2.5B,TiRex,0.5,0.25,0.75,0.006,-0.017,0.03
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,Chronos-2,0.417,0.167,0.75,0.013,-0.029,0.057
-Toto-2.0-2.5B,Toto-2.0-22m,0.583,0.25,0.833,0.004,-0.024,0.036
-Toto-2.0-2.5B,Toto-2.0-313m,0.583,0.331,0.833,0.004,-0.006,0.014
-Toto-2.0-2.5B,Stat. Ensemble,0.583,0.333,0.833,0.023,-0.033,0.071
-Toto-2.0-2.5B,FlowState,0.667,0.417,0.917,0.051,-0.024,0.108
-Toto-2.0-2.5B,Toto-2.0-4m,0.667,0.417,0.917,0.041,0.0,0.089
-Toto-2.0-2.5B,Toto-1.0,0.75,0.5,1.0,0.076,0.006,0.146
-Toto-2.0-2.5B,TabPFN-TS,0.75,0.5,1.0,0.052,0.005,0.095
-Toto-2.0-2.5B,AutoETS,0.833,0.583,1.0,0.132,0.027,0.27
-Toto-2.0-2.5B,AutoARIMA,0.833,0.583,1.0,0.1,0.018,0.186
-Toto-2.0-2.5B,TimesFM-2.5,0.917,0.75,1.0,0.086,0.05,0.122
-Toto-2.0-2.5B,Chronos-Bolt,0.917,0.75,1.0,0.099,0.05,0.146
-Toto-2.0-2.5B,Seasonal Naive,1.0,1.0,1.0,0.385,0.285,0.47
-Chronos-2,TiRex-2,0.083,0.0,0.25,-0.062,-0.123,-0.014
-Chronos-2,Toto-2.0-1B,0.583,0.25,0.833,-0.009,-0.059,0.035
-Chronos-2,TiRex,0.333,0.083,0.583,-0.007,-0.037,0.027
-Chronos-2,Toto-2.0-2.5B,0.583,0.25,0.833,-0.013,-0.06,0.028
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,Toto-2.0-22m,0.5,0.167,0.833,-0.009,-0.065,0.049
-Chronos-2,Toto-2.0-313m,0.5,0.167,0.833,-0.009,-0.06,0.036
-Chronos-2,Stat. Ensemble,0.833,0.583,1.0,0.01,-0.042,0.051
-Chronos-2,FlowState,0.667,0.417,0.917,0.038,-0.034,0.106
-Chronos-2,Toto-2.0-4m,0.667,0.415,0.917,0.029,-0.035,0.098
-Chronos-2,Toto-1.0,0.667,0.333,0.917,0.064,-0.021,0.141
-Chronos-2,TabPFN-TS,0.75,0.5,1.0,0.04,0.005,0.072
-Chronos-2,AutoETS,0.75,0.5,1.0,0.121,0.02,0.261
-Chronos-2,AutoARIMA,0.75,0.5,1.0,0.088,0.009,0.174
-Chronos-2,TimesFM-2.5,0.917,0.75,1.0,0.074,0.039,0.111
-Chronos-2,Chronos-Bolt,1.0,1.0,1.0,0.087,0.043,0.142
-Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.377,0.286,0.457
-Toto-2.0-22m,TiRex-2,0.25,0.083,0.5,-0.053,-0.086,-0.024
-Toto-2.0-22m,Toto-2.0-1B,0.5,0.25,0.833,-0.0,-0.028,0.029
-Toto-2.0-22m,TiRex,0.5,0.167,0.75,0.002,-0.034,0.036
-Toto-2.0-22m,Toto-2.0-2.5B,0.417,0.167,0.75,-0.004,-0.038,0.023
-Toto-2.0-22m,Chronos-2,0.5,0.167,0.833,0.009,-0.051,0.061
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,Toto-2.0-313m,0.417,0.167,0.75,0.0,-0.025,0.023
-Toto-2.0-22m,Stat. Ensemble,0.667,0.417,0.917,0.019,-0.03,0.062
-Toto-2.0-22m,FlowState,0.583,0.333,0.833,0.046,-0.012,0.098
-Toto-2.0-22m,Toto-2.0-4m,0.833,0.583,1.0,0.037,0.019,0.057
-Toto-2.0-22m,Toto-1.0,0.667,0.417,0.917,0.072,0.016,0.131
-Toto-2.0-22m,TabPFN-TS,0.667,0.417,0.917,0.048,-0.011,0.096
-Toto-2.0-22m,AutoETS,0.833,0.583,1.0,0.128,0.025,0.268
-Toto-2.0-22m,AutoARIMA,0.75,0.5,1.0,0.096,0.021,0.181
-Toto-2.0-22m,TimesFM-2.5,0.917,0.75,1.0,0.082,0.025,0.13
-Toto-2.0-22m,Chronos-Bolt,1.0,1.0,1.0,0.095,0.055,0.138
-Toto-2.0-22m,Seasonal Naive,1.0,1.0,1.0,0.383,0.284,0.473
-Toto-2.0-313m,TiRex-2,0.167,0.0,0.417,-0.053,-0.082,-0.023
-Toto-2.0-313m,Toto-2.0-1B,0.417,0.167,0.667,-0.0,-0.015,0.015
-Toto-2.0-313m,TiRex,0.583,0.333,0.833,0.002,-0.025,0.029
-Toto-2.0-313m,Toto-2.0-2.5B,0.417,0.167,0.669,-0.004,-0.014,0.006
-Toto-2.0-313m,Chronos-2,0.5,0.167,0.833,0.009,-0.038,0.056
-Toto-2.0-313m,Toto-2.0-22m,0.583,0.25,0.833,-0.0,-0.024,0.024
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,Stat. Ensemble,0.667,0.417,0.917,0.018,-0.031,0.064
-Toto-2.0-313m,FlowState,0.667,0.417,0.917,0.046,-0.02,0.099
-Toto-2.0-313m,Toto-2.0-4m,0.667,0.417,0.917,0.037,0.001,0.079
-Toto-2.0-313m,Toto-1.0,0.667,0.417,0.917,0.072,0.005,0.139
-Toto-2.0-313m,TabPFN-TS,0.75,0.5,1.0,0.048,0.0,0.09
-Toto-2.0-313m,AutoETS,0.75,0.5,1.0,0.128,0.025,0.267
-Toto-2.0-313m,AutoARIMA,0.833,0.583,1.0,0.096,0.02,0.177
-Toto-2.0-313m,TimesFM-2.5,0.917,0.75,1.0,0.082,0.041,0.12
-Toto-2.0-313m,Chronos-Bolt,0.917,0.75,1.0,0.095,0.047,0.142
-Toto-2.0-313m,Seasonal Naive,1.0,1.0,1.0,0.383,0.283,0.468
-Stat. Ensemble,TiRex-2,0.167,0.0,0.417,-0.073,-0.119,-0.024
-Stat. Ensemble,Toto-2.0-1B,0.25,0.0,0.5,-0.019,-0.072,0.039
-Stat. Ensemble,TiRex,0.25,0.0,0.5,-0.017,-0.064,0.033
-Stat. Ensemble,Toto-2.0-2.5B,0.417,0.167,0.667,-0.023,-0.076,0.032
-Stat. Ensemble,Chronos-2,0.167,0.0,0.417,-0.01,-0.053,0.04
-Stat. Ensemble,Toto-2.0-22m,0.333,0.083,0.583,-0.019,-0.066,0.029
-Stat. Ensemble,Toto-2.0-313m,0.333,0.083,0.583,-0.019,-0.069,0.03
-Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
-Stat. Ensemble,FlowState,0.5,0.167,0.75,0.029,-0.016,0.073
-Stat. Ensemble,Toto-2.0-4m,0.417,0.167,0.667,0.019,-0.029,0.073
-Stat. Ensemble,Toto-1.0,0.667,0.333,0.917,0.054,-0.012,0.118
-Stat. Ensemble,TabPFN-TS,0.75,0.5,1.0,0.03,-0.01,0.063
-Stat. Ensemble,AutoETS,0.667,0.417,0.917,0.112,0.011,0.257
-Stat. Ensemble,AutoARIMA,0.833,0.583,1.0,0.079,0.03,0.146
-Stat. Ensemble,TimesFM-2.5,0.833,0.583,1.0,0.065,0.013,0.121
-Stat. Ensemble,Chronos-Bolt,0.917,0.75,1.0,0.078,0.024,0.131
-Stat. Ensemble,Seasonal Naive,1.0,1.0,1.0,0.371,0.288,0.452
-FlowState,TiRex-2,0.167,0.0,0.417,-0.104,-0.179,-0.028
-FlowState,Toto-2.0-1B,0.25,0.0,0.5,-0.049,-0.112,0.031
-FlowState,TiRex,0.167,0.0,0.417,-0.047,-0.109,0.023
-FlowState,Toto-2.0-2.5B,0.333,0.083,0.583,-0.053,-0.121,0.024
-FlowState,Chronos-2,0.333,0.083,0.583,-0.04,-0.118,0.033
-FlowState,Toto-2.0-22m,0.417,0.167,0.667,-0.049,-0.109,0.012
-FlowState,Toto-2.0-313m,0.333,0.083,0.583,-0.049,-0.109,0.02
-FlowState,Stat. Ensemble,0.5,0.25,0.833,-0.029,-0.079,0.016
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,Toto-2.0-4m,0.5,0.25,0.75,-0.01,-0.079,0.052
-FlowState,Toto-1.0,0.583,0.292,0.833,0.027,-0.057,0.11
-FlowState,TabPFN-TS,0.583,0.333,0.833,0.002,-0.065,0.055
-FlowState,AutoETS,0.583,0.333,0.833,0.086,-0.042,0.243
-FlowState,AutoARIMA,0.75,0.5,1.0,0.052,0.005,0.102
-FlowState,TimesFM-2.5,0.667,0.417,0.875,0.037,-0.024,0.11
-FlowState,Chronos-Bolt,0.833,0.625,1.0,0.051,-0.002,0.101
-FlowState,Seasonal Naive,1.0,1.0,1.0,0.353,0.274,0.424
-Toto-2.0-4m,TiRex-2,0.083,0.0,0.25,-0.093,-0.144,-0.052
-Toto-2.0-4m,Toto-2.0-1B,0.167,0.0,0.417,-0.039,-0.087,0.006
-Toto-2.0-4m,TiRex,0.333,0.083,0.585,-0.037,-0.091,0.011
-Toto-2.0-4m,Toto-2.0-2.5B,0.333,0.083,0.583,-0.043,-0.097,-0.0
-Toto-2.0-4m,Chronos-2,0.333,0.083,0.585,-0.029,-0.108,0.034
-Toto-2.0-4m,Toto-2.0-22m,0.167,0.0,0.417,-0.039,-0.06,-0.019
-Toto-2.0-4m,Toto-2.0-313m,0.333,0.083,0.583,-0.038,-0.086,-0.001
-Toto-2.0-4m,Stat. Ensemble,0.583,0.333,0.833,-0.019,-0.079,0.028
-Toto-2.0-4m,FlowState,0.5,0.25,0.75,0.01,-0.055,0.073
-Toto-2.0-4m,Toto-2.0-4m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-4m,Toto-1.0,0.417,0.167,0.667,0.036,-0.022,0.097
-Toto-2.0-4m,TabPFN-TS,0.583,0.333,0.833,0.011,-0.067,0.07
-Toto-2.0-4m,AutoETS,0.75,0.5,1.0,0.095,-0.02,0.241
-Toto-2.0-4m,AutoARIMA,0.583,0.333,0.833,0.061,-0.023,0.155
-Toto-2.0-4m,TimesFM-2.5,0.667,0.417,0.917,0.047,-0.027,0.112
-Toto-2.0-4m,Chronos-Bolt,0.667,0.417,0.917,0.06,0.01,0.112
-Toto-2.0-4m,Seasonal Naive,0.917,0.75,1.0,0.359,0.246,0.458
-Toto-1.0,TiRex-2,0.0,0.0,0.0,-0.134,-0.221,-0.065
-Toto-1.0,Toto-2.0-1B,0.25,0.0,0.5,-0.078,-0.155,-0.013
-Toto-1.0,TiRex,0.333,0.083,0.667,-0.076,-0.167,0.008
-Toto-1.0,Toto-2.0-2.5B,0.25,0.0,0.5,-0.082,-0.171,-0.006
-Toto-1.0,Chronos-2,0.333,0.083,0.667,-0.068,-0.164,0.021
-Toto-1.0,Toto-2.0-22m,0.333,0.083,0.583,-0.078,-0.151,-0.017
-Toto-1.0,Toto-2.0-313m,0.333,0.083,0.583,-0.077,-0.162,-0.005
-Toto-1.0,Stat. Ensemble,0.333,0.083,0.667,-0.058,-0.134,0.012
-Toto-1.0,FlowState,0.417,0.167,0.708,-0.027,-0.124,0.054
-Toto-1.0,Toto-2.0-4m,0.583,0.333,0.833,-0.038,-0.107,0.022
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,TabPFN-TS,0.667,0.417,0.917,-0.026,-0.134,0.065
-Toto-1.0,AutoETS,0.5,0.25,0.752,0.061,-0.086,0.229
-Toto-1.0,AutoARIMA,0.667,0.417,0.917,0.026,-0.059,0.101
-Toto-1.0,TimesFM-2.5,0.75,0.5,0.958,0.011,-0.075,0.076
-Toto-1.0,Chronos-Bolt,0.667,0.417,0.875,0.025,-0.031,0.083
-Toto-1.0,Seasonal Naive,0.917,0.75,1.0,0.335,0.215,0.436
-TabPFN-TS,TiRex-2,0.167,0.0,0.417,-0.106,-0.16,-0.053
-TabPFN-TS,Toto-2.0-1B,0.167,0.0,0.417,-0.051,-0.107,0.007
-TabPFN-TS,TiRex,0.167,0.0,0.417,-0.048,-0.094,-0.002
-TabPFN-TS,Toto-2.0-2.5B,0.25,0.0,0.5,-0.055,-0.105,-0.005
-TabPFN-TS,Chronos-2,0.25,0.0,0.5,-0.041,-0.077,-0.005
-TabPFN-TS,Toto-2.0-22m,0.333,0.083,0.583,-0.05,-0.106,0.011
-TabPFN-TS,Toto-2.0-313m,0.25,0.0,0.5,-0.05,-0.099,-0.0
-TabPFN-TS,Stat. Ensemble,0.25,0.0,0.5,-0.031,-0.067,0.009
-TabPFN-TS,FlowState,0.417,0.167,0.667,-0.002,-0.058,0.061
-TabPFN-TS,Toto-2.0-4m,0.417,0.167,0.667,-0.011,-0.075,0.062
-TabPFN-TS,Toto-1.0,0.333,0.083,0.583,0.025,-0.069,0.118
-TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS,AutoETS,0.5,0.167,0.75,0.085,-0.026,0.234
-TabPFN-TS,AutoARIMA,0.667,0.415,0.917,0.051,-0.02,0.134
-TabPFN-TS,TimesFM-2.5,0.583,0.333,0.833,0.036,-0.012,0.086
-TabPFN-TS,Chronos-Bolt,0.5,0.25,0.75,0.049,-0.015,0.114
-TabPFN-TS,Seasonal Naive,1.0,1.0,1.0,0.352,0.266,0.435
-AutoETS,TiRex-2,0.0,0.0,0.0,-0.208,-0.431,-0.081
-AutoETS,Toto-2.0-1B,0.25,0.0,0.5,-0.148,-0.366,-0.018
-AutoETS,TiRex,0.25,0.0,0.5,-0.145,-0.367,-0.025
-AutoETS,Toto-2.0-2.5B,0.167,0.0,0.417,-0.152,-0.369,-0.028
-AutoETS,Chronos-2,0.25,0.0,0.5,-0.137,-0.354,-0.02
-AutoETS,Toto-2.0-22m,0.167,0.0,0.417,-0.147,-0.367,-0.026
-AutoETS,Toto-2.0-313m,0.25,0.0,0.5,-0.147,-0.365,-0.025
-AutoETS,Stat. Ensemble,0.333,0.083,0.583,-0.126,-0.345,-0.012
-AutoETS,FlowState,0.417,0.167,0.667,-0.094,-0.322,0.04
-AutoETS,Toto-2.0-4m,0.25,0.0,0.5,-0.105,-0.317,0.019
-AutoETS,Toto-1.0,0.5,0.248,0.75,-0.065,-0.298,0.08
-AutoETS,TabPFN-TS,0.5,0.25,0.833,-0.092,-0.306,0.025
-AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
-AutoETS,AutoARIMA,0.5,0.167,0.75,-0.037,-0.271,0.112
-AutoETS,TimesFM-2.5,0.5,0.25,0.75,-0.053,-0.259,0.072
-AutoETS,Chronos-Bolt,0.75,0.5,1.0,-0.039,-0.251,0.086
-AutoETS,Seasonal Naive,0.917,0.75,1.0,0.292,0.084,0.43
-AutoARIMA,TiRex-2,0.083,0.0,0.25,-0.165,-0.274,-0.08
-AutoARIMA,Toto-2.0-1B,0.167,0.0,0.417,-0.107,-0.211,-0.017
-AutoARIMA,TiRex,0.167,0.0,0.417,-0.104,-0.221,-0.019
-AutoARIMA,Toto-2.0-2.5B,0.167,0.0,0.417,-0.111,-0.228,-0.019
-AutoARIMA,Chronos-2,0.25,0.0,0.5,-0.097,-0.21,-0.009
-AutoARIMA,Toto-2.0-22m,0.25,0.0,0.5,-0.106,-0.221,-0.021
-AutoARIMA,Toto-2.0-313m,0.167,0.0,0.417,-0.106,-0.216,-0.02
-AutoARIMA,Stat. Ensemble,0.167,0.0,0.417,-0.086,-0.171,-0.031
-AutoARIMA,FlowState,0.25,0.0,0.5,-0.055,-0.113,-0.005
-AutoARIMA,Toto-2.0-4m,0.417,0.167,0.667,-0.065,-0.184,0.022
-AutoARIMA,Toto-1.0,0.333,0.083,0.583,-0.027,-0.113,0.056
-AutoARIMA,TabPFN-TS,0.333,0.083,0.585,-0.053,-0.154,0.02
-AutoARIMA,AutoETS,0.5,0.25,0.833,0.036,-0.126,0.213
-AutoARIMA,AutoARIMA,0.5,0.5,0.5,0.0,0.0,0.0
-AutoARIMA,TimesFM-2.5,0.417,0.167,0.667,-0.016,-0.097,0.062
-AutoARIMA,Chronos-Bolt,0.417,0.167,0.667,-0.001,-0.08,0.069
-AutoARIMA,Seasonal Naive,1.0,1.0,1.0,0.317,0.242,0.396
-TimesFM-2.5,TiRex-2,0.083,0.0,0.25,-0.147,-0.211,-0.087
-TimesFM-2.5,Toto-2.0-1B,0.083,0.0,0.25,-0.09,-0.13,-0.047
-TimesFM-2.5,TiRex,0.083,0.0,0.25,-0.087,-0.139,-0.039
-TimesFM-2.5,Toto-2.0-2.5B,0.083,0.0,0.25,-0.094,-0.139,-0.053
-TimesFM-2.5,Chronos-2,0.083,0.0,0.25,-0.08,-0.124,-0.041
-TimesFM-2.5,Toto-2.0-22m,0.083,0.0,0.25,-0.089,-0.15,-0.026
-TimesFM-2.5,Toto-2.0-313m,0.083,0.0,0.25,-0.089,-0.136,-0.042
-TimesFM-2.5,Stat. Ensemble,0.167,0.0,0.417,-0.069,-0.137,-0.014
-TimesFM-2.5,FlowState,0.333,0.125,0.583,-0.039,-0.124,0.024
-TimesFM-2.5,Toto-2.0-4m,0.333,0.083,0.583,-0.049,-0.126,0.026
-TimesFM-2.5,Toto-1.0,0.25,0.042,0.5,-0.011,-0.082,0.07
-TimesFM-2.5,TabPFN-TS,0.417,0.167,0.667,-0.037,-0.094,0.012
-TimesFM-2.5,AutoETS,0.5,0.25,0.75,0.051,-0.077,0.205
-TimesFM-2.5,AutoARIMA,0.583,0.333,0.833,0.015,-0.066,0.089
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,Chronos-Bolt,0.583,0.333,0.833,0.014,-0.034,0.072
-TimesFM-2.5,Seasonal Naive,0.917,0.75,1.0,0.328,0.224,0.407
-Chronos-Bolt,TiRex-2,0.0,0.0,0.0,-0.163,-0.242,-0.099
-Chronos-Bolt,Toto-2.0-1B,0.167,0.0,0.417,-0.105,-0.162,-0.05
-Chronos-Bolt,TiRex,0.083,0.0,0.25,-0.103,-0.164,-0.052
-Chronos-Bolt,Toto-2.0-2.5B,0.083,0.0,0.25,-0.109,-0.171,-0.053
-Chronos-Bolt,Chronos-2,0.0,0.0,0.0,-0.095,-0.165,-0.044
-Chronos-Bolt,Toto-2.0-22m,0.0,0.0,0.0,-0.105,-0.159,-0.058
-Chronos-Bolt,Toto-2.0-313m,0.083,0.0,0.25,-0.105,-0.165,-0.049
-Chronos-Bolt,Stat. Ensemble,0.083,0.0,0.25,-0.084,-0.151,-0.024
-Chronos-Bolt,FlowState,0.167,0.0,0.375,-0.053,-0.113,0.002
-Chronos-Bolt,Toto-2.0-4m,0.333,0.083,0.583,-0.064,-0.126,-0.01
-Chronos-Bolt,Toto-1.0,0.333,0.125,0.583,-0.025,-0.09,0.03
-Chronos-Bolt,TabPFN-TS,0.5,0.25,0.75,-0.052,-0.128,0.014
-Chronos-Bolt,AutoETS,0.25,0.0,0.5,0.037,-0.094,0.201
-Chronos-Bolt,AutoARIMA,0.583,0.333,0.833,0.001,-0.074,0.074
-Chronos-Bolt,TimesFM-2.5,0.417,0.167,0.667,-0.014,-0.077,0.032
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,Seasonal Naive,0.917,0.75,1.0,0.318,0.219,0.402
-Seasonal Naive,TiRex-2,0.0,0.0,0.0,-0.706,-1.009,-0.467
-Seasonal Naive,Toto-2.0-1B,0.083,0.0,0.25,-0.621,-0.884,-0.386
-Seasonal Naive,TiRex,0.0,0.0,0.0,-0.617,-0.877,-0.392
-Seasonal Naive,Toto-2.0-2.5B,0.0,0.0,0.0,-0.627,-0.887,-0.398
-Seasonal Naive,Chronos-2,0.0,0.0,0.0,-0.606,-0.842,-0.401
-Seasonal Naive,Toto-2.0-22m,0.0,0.0,0.0,-0.62,-0.898,-0.396
-Seasonal Naive,Toto-2.0-313m,0.0,0.0,0.0,-0.62,-0.881,-0.394
-Seasonal Naive,Stat. Ensemble,0.0,0.0,0.0,-0.59,-0.824,-0.404
-Seasonal Naive,FlowState,0.0,0.0,0.0,-0.545,-0.736,-0.377
-Seasonal Naive,Toto-2.0-4m,0.083,0.0,0.25,-0.56,-0.847,-0.326
-Seasonal Naive,Toto-1.0,0.083,0.0,0.25,-0.504,-0.774,-0.274
-Seasonal Naive,TabPFN-TS,0.0,0.0,0.0,-0.543,-0.769,-0.363
-Seasonal Naive,AutoETS,0.083,0.0,0.25,-0.412,-0.755,-0.091
-Seasonal Naive,AutoARIMA,0.0,0.0,0.0,-0.465,-0.656,-0.319
-Seasonal Naive,TimesFM-2.5,0.083,0.0,0.25,-0.487,-0.686,-0.288
-Seasonal Naive,Chronos-Bolt,0.083,0.0,0.25,-0.467,-0.673,-0.28
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_econ/pairwise_WAPE.csv

@@ -1,290 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,Toto-2.0-1B,0.583,0.333,0.833,0.054,-0.019,0.135
-TiRex-2,Toto-2.0-2.5B,0.583,0.25,0.833,0.05,-0.021,0.117
-TiRex-2,Toto-2.0-313m,0.75,0.5,1.0,0.063,-0.007,0.135
-TiRex-2,Toto-2.0-22m,0.667,0.417,0.917,0.068,0.017,0.127
-TiRex-2,TiRex,0.917,0.75,1.0,0.07,0.023,0.119
-TiRex-2,Chronos-2,0.75,0.5,1.0,0.088,0.017,0.151
-TiRex-2,Stat. Ensemble,0.833,0.583,1.0,0.064,-0.008,0.14
-TiRex-2,Toto-1.0,0.917,0.75,1.0,0.124,0.043,0.2
-TiRex-2,TimesFM-2.5,0.917,0.75,1.0,0.097,0.043,0.154
-TiRex-2,CatBoost,0.833,0.583,1.0,0.107,-0.003,0.217
-TiRex-2,TabPFN-TS,0.75,0.5,1.0,0.088,0.001,0.173
-TiRex-2,FlowState,0.917,0.75,1.0,0.072,-0.004,0.126
-TiRex-2,AutoETS,0.917,0.75,1.0,0.112,0.051,0.185
-TiRex-2,Toto-2.0-4m,0.917,0.75,1.0,0.132,0.068,0.203
-TiRex-2,Chronos-Bolt,1.0,1.0,1.0,0.168,0.089,0.254
-TiRex-2,Seasonal Naive,1.0,1.0,1.0,0.421,0.305,0.538
-Toto-2.0-1B,TiRex-2,0.417,0.167,0.667,-0.058,-0.156,0.019
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-2.5B,0.5,0.25,0.75,-0.005,-0.023,0.01
-Toto-2.0-1B,Toto-2.0-313m,0.667,0.417,0.917,0.009,-0.017,0.033
-Toto-2.0-1B,Toto-2.0-22m,0.833,0.583,1.0,0.014,-0.085,0.08
-Toto-2.0-1B,TiRex,0.833,0.583,1.0,0.017,-0.022,0.044
-Toto-2.0-1B,Chronos-2,0.75,0.5,1.0,0.035,-0.015,0.078
-Toto-2.0-1B,Stat. Ensemble,0.75,0.5,1.0,0.01,-0.138,0.106
-Toto-2.0-1B,Toto-1.0,0.667,0.417,0.917,0.073,-0.013,0.157
-Toto-2.0-1B,TimesFM-2.5,0.75,0.5,0.917,0.045,-0.002,0.093
-Toto-2.0-1B,CatBoost,0.75,0.5,1.0,0.056,-0.124,0.175
-Toto-2.0-1B,TabPFN-TS,0.75,0.5,1.0,0.036,-0.112,0.136
-Toto-2.0-1B,FlowState,0.75,0.5,1.0,0.019,-0.152,0.114
-Toto-2.0-1B,AutoETS,0.75,0.5,1.0,0.061,-0.038,0.14
-Toto-2.0-1B,Toto-2.0-4m,0.917,0.75,1.0,0.082,-0.005,0.154
-Toto-2.0-1B,Chronos-Bolt,0.833,0.583,1.0,0.12,0.045,0.197
-Toto-2.0-1B,Seasonal Naive,0.917,0.75,1.0,0.388,0.248,0.515
-Toto-2.0-2.5B,TiRex-2,0.417,0.167,0.75,-0.052,-0.132,0.021
-Toto-2.0-2.5B,Toto-2.0-1B,0.5,0.25,0.75,0.005,-0.01,0.022
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,Toto-2.0-313m,0.667,0.417,0.917,0.014,-0.007,0.033
-Toto-2.0-2.5B,Toto-2.0-22m,0.833,0.583,1.0,0.019,-0.065,0.083
-Toto-2.0-2.5B,TiRex,0.75,0.5,1.0,0.022,-0.004,0.046
-Toto-2.0-2.5B,Chronos-2,0.667,0.417,0.917,0.04,0.0,0.076
-Toto-2.0-2.5B,Stat. Ensemble,0.75,0.5,1.0,0.015,-0.114,0.104
-Toto-2.0-2.5B,Toto-1.0,0.667,0.417,0.917,0.078,-0.001,0.164
-Toto-2.0-2.5B,TimesFM-2.5,0.75,0.5,0.917,0.05,0.012,0.094
-Toto-2.0-2.5B,CatBoost,0.75,0.5,1.0,0.06,-0.104,0.172
-Toto-2.0-2.5B,TabPFN-TS,0.75,0.5,1.0,0.041,-0.09,0.131
-Toto-2.0-2.5B,FlowState,0.75,0.5,1.0,0.023,-0.13,0.115
-Toto-2.0-2.5B,AutoETS,0.75,0.5,1.0,0.065,-0.017,0.138
-Toto-2.0-2.5B,Toto-2.0-4m,0.917,0.75,1.0,0.087,0.01,0.16
-Toto-2.0-2.5B,Chronos-Bolt,0.833,0.583,1.0,0.124,0.054,0.199
-Toto-2.0-2.5B,Seasonal Naive,0.917,0.75,1.0,0.391,0.26,0.511
-Toto-2.0-313m,TiRex-2,0.25,0.0,0.5,-0.067,-0.156,0.007
-Toto-2.0-313m,Toto-2.0-1B,0.333,0.083,0.583,-0.009,-0.034,0.017
-Toto-2.0-313m,Toto-2.0-2.5B,0.333,0.083,0.583,-0.014,-0.034,0.007
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,Toto-2.0-22m,0.667,0.417,0.917,0.006,-0.071,0.063
-Toto-2.0-313m,TiRex,0.583,0.333,0.833,0.008,-0.021,0.035
-Toto-2.0-313m,Chronos-2,0.583,0.333,0.833,0.027,-0.018,0.066
-Toto-2.0-313m,Stat. Ensemble,0.75,0.5,1.0,0.001,-0.131,0.091
-Toto-2.0-313m,Toto-1.0,0.667,0.417,0.917,0.065,-0.011,0.147
-Toto-2.0-313m,TimesFM-2.5,0.667,0.417,0.917,0.037,-0.004,0.079
-Toto-2.0-313m,CatBoost,0.833,0.583,1.0,0.047,-0.108,0.154
-Toto-2.0-313m,TabPFN-TS,0.75,0.5,1.0,0.027,-0.108,0.124
-Toto-2.0-313m,FlowState,0.75,0.5,1.0,0.01,-0.142,0.106
-Toto-2.0-313m,AutoETS,0.667,0.417,0.917,0.052,-0.025,0.119
-Toto-2.0-313m,Toto-2.0-4m,0.833,0.583,1.0,0.074,0.005,0.14
-Toto-2.0-313m,Chronos-Bolt,0.833,0.583,1.0,0.112,0.053,0.179
-Toto-2.0-313m,Seasonal Naive,0.917,0.75,1.0,0.383,0.252,0.506
-Toto-2.0-22m,TiRex-2,0.333,0.083,0.583,-0.073,-0.145,-0.018
-Toto-2.0-22m,Toto-2.0-1B,0.167,0.0,0.417,-0.015,-0.086,0.078
-Toto-2.0-22m,Toto-2.0-2.5B,0.167,0.0,0.417,-0.02,-0.091,0.061
-Toto-2.0-22m,Toto-2.0-313m,0.333,0.083,0.583,-0.006,-0.067,0.066
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,TiRex,0.5,0.248,0.75,0.002,-0.05,0.058
-Toto-2.0-22m,Chronos-2,0.75,0.5,1.0,0.021,-0.055,0.091
-Toto-2.0-22m,Stat. Ensemble,0.583,0.333,0.833,-0.004,-0.084,0.066
-Toto-2.0-22m,Toto-1.0,0.75,0.5,1.0,0.059,-0.005,0.12
-Toto-2.0-22m,TimesFM-2.5,0.667,0.417,0.917,0.031,-0.046,0.105
-Toto-2.0-22m,CatBoost,0.583,0.333,0.833,0.042,-0.064,0.136
-Toto-2.0-22m,TabPFN-TS,0.583,0.333,0.833,0.022,-0.074,0.112
-Toto-2.0-22m,FlowState,0.667,0.417,0.917,0.004,-0.084,0.08
-Toto-2.0-22m,AutoETS,0.833,0.583,1.0,0.047,-0.016,0.095
-Toto-2.0-22m,Toto-2.0-4m,1.0,1.0,1.0,0.069,0.048,0.092
-Toto-2.0-22m,Chronos-Bolt,0.917,0.75,1.0,0.107,0.057,0.155
-Toto-2.0-22m,Seasonal Naive,0.917,0.75,1.0,0.379,0.262,0.497
-TiRex,TiRex-2,0.083,0.0,0.25,-0.076,-0.135,-0.023
-TiRex,Toto-2.0-1B,0.167,0.0,0.417,-0.017,-0.046,0.022
-TiRex,Toto-2.0-2.5B,0.25,0.0,0.5,-0.022,-0.048,0.004
-TiRex,Toto-2.0-313m,0.417,0.167,0.667,-0.008,-0.036,0.021
-TiRex,Toto-2.0-22m,0.5,0.25,0.752,-0.002,-0.061,0.048
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,Chronos-2,0.667,0.333,0.917,0.019,-0.026,0.055
-TiRex,Stat. Ensemble,0.583,0.333,0.833,-0.007,-0.118,0.073
-TiRex,Toto-1.0,0.5,0.25,0.833,0.057,-0.011,0.131
-TiRex,TimesFM-2.5,0.833,0.667,1.0,0.029,-0.01,0.066
-TiRex,CatBoost,0.667,0.417,0.917,0.039,-0.111,0.151
-TiRex,TabPFN-TS,0.75,0.5,1.0,0.019,-0.098,0.11
-TiRex,FlowState,0.667,0.417,0.917,0.002,-0.132,0.081
-TiRex,AutoETS,0.667,0.417,0.917,0.045,-0.022,0.113
-TiRex,Toto-2.0-4m,0.75,0.5,1.0,0.067,0.006,0.127
-TiRex,Chronos-Bolt,0.917,0.75,1.0,0.105,0.043,0.176
-TiRex,Seasonal Naive,0.917,0.75,1.0,0.378,0.252,0.503
-Chronos-2,TiRex-2,0.25,0.0,0.5,-0.096,-0.178,-0.018
-Chronos-2,Toto-2.0-1B,0.25,0.0,0.5,-0.037,-0.085,0.015
-Chronos-2,Toto-2.0-2.5B,0.333,0.083,0.583,-0.042,-0.082,-0.0
-Chronos-2,Toto-2.0-313m,0.417,0.167,0.667,-0.028,-0.07,0.018
-Chronos-2,Toto-2.0-22m,0.25,0.0,0.5,-0.022,-0.1,0.052
-Chronos-2,TiRex,0.333,0.083,0.667,-0.019,-0.059,0.025
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,Stat. Ensemble,0.667,0.417,0.917,-0.026,-0.142,0.05
-Chronos-2,Toto-1.0,0.5,0.25,0.833,0.039,-0.047,0.129
-Chronos-2,TimesFM-2.5,0.5,0.167,0.75,0.01,-0.025,0.05
-Chronos-2,CatBoost,0.583,0.333,0.833,0.021,-0.142,0.136
-Chronos-2,TabPFN-TS,0.667,0.417,0.917,0.0,-0.134,0.102
-Chronos-2,FlowState,0.583,0.333,0.833,-0.017,-0.169,0.081
-Chronos-2,AutoETS,0.667,0.417,0.917,0.026,-0.04,0.085
-Chronos-2,Toto-2.0-4m,0.583,0.333,0.833,0.049,-0.031,0.135
-Chronos-2,Chronos-Bolt,0.75,0.5,1.0,0.087,0.014,0.175
-Chronos-2,Seasonal Naive,0.917,0.75,1.0,0.366,0.237,0.489
-Stat. Ensemble,TiRex-2,0.167,0.0,0.417,-0.068,-0.163,0.008
-Stat. Ensemble,Toto-2.0-1B,0.25,0.0,0.5,-0.01,-0.119,0.121
-Stat. Ensemble,Toto-2.0-2.5B,0.25,0.0,0.5,-0.015,-0.116,0.103
-Stat. Ensemble,Toto-2.0-313m,0.25,0.0,0.5,-0.001,-0.1,0.116
-Stat. Ensemble,Toto-2.0-22m,0.417,0.167,0.667,0.004,-0.071,0.077
-Stat. Ensemble,TiRex,0.417,0.167,0.667,0.007,-0.079,0.105
-Stat. Ensemble,Chronos-2,0.333,0.083,0.583,0.026,-0.052,0.124
-Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
-Stat. Ensemble,Toto-1.0,0.583,0.25,0.833,0.064,-0.025,0.153
-Stat. Ensemble,TimesFM-2.5,0.5,0.25,0.75,0.036,-0.044,0.138
-Stat. Ensemble,CatBoost,0.5,0.25,0.75,0.046,-0.019,0.117
-Stat. Ensemble,TabPFN-TS,0.583,0.333,0.833,0.026,-0.033,0.082
-Stat. Ensemble,FlowState,0.667,0.417,0.917,0.009,-0.049,0.064
-Stat. Ensemble,AutoETS,0.75,0.5,1.0,0.051,0.006,0.104
-Stat. Ensemble,Toto-2.0-4m,0.583,0.333,0.833,0.073,-0.009,0.154
-Stat. Ensemble,Chronos-Bolt,0.75,0.5,1.0,0.111,0.016,0.202
-Stat. Ensemble,Seasonal Naive,1.0,1.0,1.0,0.382,0.284,0.478
-Toto-1.0,TiRex-2,0.083,0.0,0.25,-0.141,-0.249,-0.045
-Toto-1.0,Toto-2.0-1B,0.333,0.083,0.583,-0.079,-0.187,0.013
-Toto-1.0,Toto-2.0-2.5B,0.333,0.083,0.583,-0.084,-0.196,0.001
-Toto-1.0,Toto-2.0-313m,0.333,0.083,0.583,-0.069,-0.173,0.011
-Toto-1.0,Toto-2.0-22m,0.25,0.0,0.5,-0.063,-0.136,0.005
-Toto-1.0,TiRex,0.5,0.167,0.75,-0.061,-0.151,0.011
-Toto-1.0,Chronos-2,0.5,0.167,0.75,-0.041,-0.149,0.045
-Toto-1.0,Stat. Ensemble,0.417,0.167,0.75,-0.068,-0.181,0.024
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,TimesFM-2.5,0.583,0.333,0.833,-0.03,-0.139,0.05
-Toto-1.0,CatBoost,0.583,0.25,0.833,-0.019,-0.168,0.102
-Toto-1.0,TabPFN-TS,0.583,0.333,0.833,-0.04,-0.192,0.084
-Toto-1.0,FlowState,0.5,0.25,0.75,-0.059,-0.205,0.059
-Toto-1.0,AutoETS,0.5,0.25,0.75,-0.013,-0.1,0.062
-Toto-1.0,Toto-2.0-4m,0.5,0.248,0.75,0.01,-0.051,0.066
-Toto-1.0,Chronos-Bolt,0.75,0.542,0.958,0.05,0.006,0.093
-Toto-1.0,Seasonal Naive,0.917,0.75,1.0,0.34,0.203,0.463
-TimesFM-2.5,TiRex-2,0.083,0.0,0.25,-0.108,-0.182,-0.045
-TimesFM-2.5,Toto-2.0-1B,0.25,0.083,0.5,-0.048,-0.103,0.002
-TimesFM-2.5,Toto-2.0-2.5B,0.25,0.083,0.5,-0.053,-0.103,-0.012
-TimesFM-2.5,Toto-2.0-313m,0.333,0.083,0.583,-0.038,-0.085,0.004
-TimesFM-2.5,Toto-2.0-22m,0.333,0.083,0.583,-0.032,-0.118,0.044
-TimesFM-2.5,TiRex,0.167,0.0,0.333,-0.03,-0.071,0.01
-TimesFM-2.5,Chronos-2,0.5,0.25,0.833,-0.011,-0.052,0.025
-TimesFM-2.5,Stat. Ensemble,0.5,0.25,0.75,-0.037,-0.161,0.042
-TimesFM-2.5,Toto-1.0,0.417,0.167,0.667,0.029,-0.053,0.122
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,CatBoost,0.667,0.417,0.917,0.011,-0.151,0.126
-TimesFM-2.5,TabPFN-TS,0.5,0.25,0.75,-0.01,-0.144,0.086
-TimesFM-2.5,FlowState,0.417,0.167,0.667,-0.028,-0.174,0.06
-TimesFM-2.5,AutoETS,0.583,0.331,0.833,0.016,-0.058,0.087
-TimesFM-2.5,Toto-2.0-4m,0.583,0.333,0.833,0.039,-0.044,0.124
-TimesFM-2.5,Chronos-Bolt,0.667,0.417,0.875,0.078,0.002,0.167
-TimesFM-2.5,Seasonal Naive,0.917,0.75,1.0,0.359,0.235,0.479
-CatBoost,TiRex-2,0.167,0.0,0.417,-0.12,-0.278,0.003
-CatBoost,Toto-2.0-1B,0.25,0.0,0.5,-0.059,-0.212,0.11
-CatBoost,Toto-2.0-2.5B,0.25,0.0,0.5,-0.064,-0.208,0.094
-CatBoost,Toto-2.0-313m,0.167,0.0,0.417,-0.05,-0.181,0.097
-CatBoost,Toto-2.0-22m,0.417,0.167,0.667,-0.044,-0.157,0.06
-CatBoost,TiRex,0.333,0.083,0.583,-0.041,-0.178,0.1
-CatBoost,Chronos-2,0.417,0.167,0.667,-0.021,-0.157,0.125
-CatBoost,Stat. Ensemble,0.5,0.25,0.75,-0.048,-0.133,0.018
-CatBoost,Toto-1.0,0.417,0.167,0.75,0.019,-0.114,0.144
-CatBoost,TimesFM-2.5,0.333,0.083,0.583,-0.011,-0.145,0.131
-CatBoost,CatBoost,0.5,0.5,0.5,0.0,0.0,0.0
-CatBoost,TabPFN-TS,0.5,0.25,0.75,-0.021,-0.113,0.061
-CatBoost,FlowState,0.5,0.25,0.75,-0.039,-0.146,0.029
-CatBoost,AutoETS,0.583,0.25,0.833,0.006,-0.085,0.101
-CatBoost,Toto-2.0-4m,0.583,0.25,0.833,0.028,-0.083,0.129
-CatBoost,Chronos-Bolt,0.583,0.25,0.833,0.068,-0.042,0.181
-CatBoost,Seasonal Naive,1.0,1.0,1.0,0.352,0.249,0.443
-TabPFN-TS,TiRex-2,0.25,0.0,0.5,-0.097,-0.209,-0.001
-TabPFN-TS,Toto-2.0-1B,0.25,0.0,0.5,-0.037,-0.158,0.101
-TabPFN-TS,Toto-2.0-2.5B,0.25,0.0,0.5,-0.042,-0.151,0.082
-TabPFN-TS,Toto-2.0-313m,0.25,0.0,0.5,-0.028,-0.142,0.097
-TabPFN-TS,Toto-2.0-22m,0.417,0.167,0.667,-0.022,-0.126,0.069
-TabPFN-TS,TiRex,0.25,0.0,0.5,-0.02,-0.124,0.089
-TabPFN-TS,Chronos-2,0.333,0.083,0.583,-0.0,-0.113,0.119
-TabPFN-TS,Stat. Ensemble,0.417,0.167,0.667,-0.027,-0.089,0.032
-TabPFN-TS,Toto-1.0,0.417,0.167,0.667,0.039,-0.092,0.161
-TabPFN-TS,TimesFM-2.5,0.5,0.25,0.75,0.01,-0.095,0.126
-TabPFN-TS,CatBoost,0.5,0.25,0.75,0.021,-0.065,0.101
-TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS,FlowState,0.333,0.083,0.583,-0.018,-0.086,0.053
-TabPFN-TS,AutoETS,0.667,0.417,0.917,0.026,-0.063,0.099
-TabPFN-TS,Toto-2.0-4m,0.583,0.331,0.833,0.048,-0.067,0.151
-TabPFN-TS,Chronos-Bolt,0.583,0.331,0.833,0.087,-0.047,0.2
-TabPFN-TS,Seasonal Naive,1.0,1.0,1.0,0.365,0.273,0.457
-FlowState,TiRex-2,0.083,0.0,0.25,-0.078,-0.144,0.004
-FlowState,Toto-2.0-1B,0.25,0.0,0.5,-0.019,-0.129,0.132
-FlowState,Toto-2.0-2.5B,0.25,0.0,0.5,-0.024,-0.13,0.115
-FlowState,Toto-2.0-313m,0.25,0.0,0.5,-0.01,-0.119,0.124
-FlowState,Toto-2.0-22m,0.333,0.083,0.583,-0.004,-0.087,0.077
-FlowState,TiRex,0.333,0.083,0.583,-0.002,-0.088,0.117
-FlowState,Chronos-2,0.417,0.167,0.667,0.017,-0.088,0.144
-FlowState,Stat. Ensemble,0.333,0.083,0.583,-0.009,-0.068,0.047
-FlowState,Toto-1.0,0.5,0.25,0.75,0.056,-0.062,0.17
-FlowState,TimesFM-2.5,0.583,0.333,0.833,0.027,-0.064,0.149
-FlowState,CatBoost,0.5,0.25,0.75,0.038,-0.03,0.127
-FlowState,TabPFN-TS,0.667,0.417,0.917,0.018,-0.056,0.079
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,AutoETS,0.5,0.25,0.75,0.043,-0.045,0.131
-FlowState,Toto-2.0-4m,0.417,0.167,0.667,0.065,-0.028,0.157
-FlowState,Chronos-Bolt,0.583,0.332,0.833,0.103,-0.011,0.214
-FlowState,Seasonal Naive,0.917,0.75,1.0,0.376,0.258,0.488
-AutoETS,TiRex-2,0.083,0.0,0.25,-0.126,-0.227,-0.054
-AutoETS,Toto-2.0-1B,0.25,0.0,0.5,-0.065,-0.163,0.036
-AutoETS,Toto-2.0-2.5B,0.25,0.0,0.5,-0.07,-0.16,0.017
-AutoETS,Toto-2.0-313m,0.333,0.083,0.583,-0.055,-0.135,0.025
-AutoETS,Toto-2.0-22m,0.167,0.0,0.417,-0.049,-0.105,0.016
-AutoETS,TiRex,0.333,0.083,0.583,-0.047,-0.127,0.022
-AutoETS,Chronos-2,0.333,0.083,0.583,-0.027,-0.093,0.039
-AutoETS,Stat. Ensemble,0.25,0.0,0.5,-0.054,-0.115,-0.006
-AutoETS,Toto-1.0,0.5,0.25,0.75,0.013,-0.066,0.091
-AutoETS,TimesFM-2.5,0.417,0.167,0.669,-0.016,-0.095,0.055
-AutoETS,CatBoost,0.417,0.167,0.75,-0.006,-0.113,0.079
-AutoETS,TabPFN-TS,0.333,0.083,0.583,-0.027,-0.11,0.059
-AutoETS,FlowState,0.5,0.25,0.75,-0.045,-0.151,0.043
-AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
-AutoETS,Toto-2.0-4m,0.417,0.167,0.667,0.023,-0.034,0.101
-AutoETS,Chronos-Bolt,0.667,0.333,0.917,0.063,-0.003,0.135
-AutoETS,Seasonal Naive,1.0,1.0,1.0,0.348,0.248,0.455
-Toto-2.0-4m,TiRex-2,0.083,0.0,0.25,-0.152,-0.255,-0.073
-Toto-2.0-4m,Toto-2.0-1B,0.083,0.0,0.25,-0.09,-0.182,0.005
-Toto-2.0-4m,Toto-2.0-2.5B,0.083,0.0,0.25,-0.095,-0.19,-0.011
-Toto-2.0-4m,Toto-2.0-313m,0.167,0.0,0.417,-0.08,-0.163,-0.005
-Toto-2.0-4m,Toto-2.0-22m,0.0,0.0,0.0,-0.074,-0.101,-0.051
-Toto-2.0-4m,TiRex,0.25,0.0,0.5,-0.071,-0.145,-0.006
-Toto-2.0-4m,Chronos-2,0.417,0.167,0.667,-0.051,-0.155,0.03
-Toto-2.0-4m,Stat. Ensemble,0.417,0.167,0.667,-0.079,-0.182,0.009
-Toto-2.0-4m,Toto-1.0,0.5,0.25,0.752,-0.01,-0.071,0.048
-Toto-2.0-4m,TimesFM-2.5,0.417,0.167,0.667,-0.04,-0.142,0.043
-Toto-2.0-4m,CatBoost,0.417,0.167,0.75,-0.029,-0.148,0.077
-Toto-2.0-4m,TabPFN-TS,0.417,0.167,0.669,-0.051,-0.178,0.063
-Toto-2.0-4m,FlowState,0.583,0.333,0.833,-0.069,-0.186,0.027
-Toto-2.0-4m,AutoETS,0.583,0.333,0.833,-0.023,-0.112,0.033
-Toto-2.0-4m,Toto-2.0-4m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-4m,Chronos-Bolt,0.75,0.5,1.0,0.041,0.002,0.082
-Toto-2.0-4m,Seasonal Naive,0.917,0.75,1.0,0.333,0.197,0.46
-Chronos-Bolt,TiRex-2,0.0,0.0,0.0,-0.201,-0.34,-0.098
-Chronos-Bolt,Toto-2.0-1B,0.167,0.0,0.417,-0.136,-0.246,-0.047
-Chronos-Bolt,Toto-2.0-2.5B,0.167,0.0,0.417,-0.142,-0.249,-0.058
-Chronos-Bolt,Toto-2.0-313m,0.167,0.0,0.417,-0.126,-0.218,-0.055
-Chronos-Bolt,Toto-2.0-22m,0.083,0.0,0.25,-0.12,-0.184,-0.061
-Chronos-Bolt,TiRex,0.083,0.0,0.25,-0.117,-0.213,-0.045
-Chronos-Bolt,Chronos-2,0.25,0.0,0.5,-0.096,-0.213,-0.014
-Chronos-Bolt,Stat. Ensemble,0.25,0.0,0.5,-0.125,-0.253,-0.016
-Chronos-Bolt,Toto-1.0,0.25,0.042,0.458,-0.053,-0.102,-0.006
-Chronos-Bolt,TimesFM-2.5,0.333,0.125,0.583,-0.084,-0.2,-0.002
-Chronos-Bolt,CatBoost,0.417,0.167,0.75,-0.073,-0.221,0.041
-Chronos-Bolt,TabPFN-TS,0.417,0.167,0.669,-0.095,-0.249,0.045
-Chronos-Bolt,FlowState,0.417,0.167,0.668,-0.115,-0.272,0.01
-Chronos-Bolt,AutoETS,0.333,0.083,0.667,-0.067,-0.156,0.003
-Chronos-Bolt,Toto-2.0-4m,0.25,0.0,0.5,-0.042,-0.089,-0.002
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,Seasonal Naive,0.833,0.583,1.0,0.305,0.17,0.432
-Seasonal Naive,TiRex-2,0.0,0.0,0.0,-0.728,-1.165,-0.439
-Seasonal Naive,Toto-2.0-1B,0.083,0.0,0.25,-0.634,-1.063,-0.329
-Seasonal Naive,Toto-2.0-2.5B,0.083,0.0,0.25,-0.642,-1.045,-0.352
-Seasonal Naive,Toto-2.0-313m,0.083,0.0,0.25,-0.62,-1.022,-0.337
-Seasonal Naive,Toto-2.0-22m,0.083,0.0,0.25,-0.61,-0.988,-0.356
-Seasonal Naive,TiRex,0.083,0.0,0.25,-0.607,-1.014,-0.337
-Seasonal Naive,Chronos-2,0.083,0.0,0.25,-0.576,-0.957,-0.311
-Seasonal Naive,Stat. Ensemble,0.0,0.0,0.0,-0.618,-0.915,-0.396
-Seasonal Naive,Toto-1.0,0.083,0.0,0.25,-0.515,-0.863,-0.255
-Seasonal Naive,TimesFM-2.5,0.083,0.0,0.25,-0.56,-0.92,-0.308
-Seasonal Naive,CatBoost,0.0,0.0,0.0,-0.543,-0.796,-0.331
-Seasonal Naive,TabPFN-TS,0.0,0.0,0.0,-0.576,-0.842,-0.375
-Seasonal Naive,FlowState,0.083,0.0,0.25,-0.604,-0.954,-0.348
-Seasonal Naive,AutoETS,0.0,0.0,0.0,-0.535,-0.834,-0.33
-Seasonal Naive,Toto-2.0-4m,0.083,0.0,0.25,-0.5,-0.851,-0.245
-Seasonal Naive,Chronos-Bolt,0.167,0.0,0.417,-0.438,-0.76,-0.205
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_econ/pairwise_WQL.csv

@@ -1,257 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,Toto-2.0-1B,0.667,0.333,0.917,0.055,-0.019,0.139
-TiRex-2,Toto-2.0-2.5B,0.583,0.25,0.833,0.048,-0.025,0.117
-TiRex-2,Toto-2.0-313m,0.833,0.583,1.0,0.06,-0.008,0.128
-TiRex-2,TiRex,0.917,0.75,1.0,0.06,0.02,0.102
-TiRex-2,Toto-2.0-22m,0.75,0.5,0.917,0.056,-0.002,0.12
-TiRex-2,Chronos-2,0.833,0.583,1.0,0.078,0.01,0.141
-TiRex-2,FlowState,0.917,0.75,1.0,0.078,-0.002,0.138
-TiRex-2,Toto-1.0,0.917,0.75,1.0,0.12,0.047,0.19
-TiRex-2,TabPFN-TS,0.667,0.417,0.917,0.089,0.016,0.164
-TiRex-2,TimesFM-2.5,0.917,0.75,1.0,0.103,0.049,0.166
-TiRex-2,Toto-2.0-4m,0.917,0.75,1.0,0.116,0.049,0.192
-TiRex-2,Stat. Ensemble,0.833,0.583,1.0,0.122,0.04,0.196
-TiRex-2,Chronos-Bolt,1.0,1.0,1.0,0.155,0.081,0.238
-TiRex-2,AutoETS,0.917,0.75,1.0,0.139,0.08,0.207
-TiRex-2,Seasonal Naive,1.0,1.0,1.0,0.455,0.337,0.57
-Toto-2.0-1B,TiRex-2,0.333,0.083,0.667,-0.059,-0.161,0.019
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-2.5B,0.333,0.083,0.583,-0.008,-0.037,0.017
-Toto-2.0-1B,Toto-2.0-313m,0.833,0.583,1.0,0.005,-0.033,0.035
-Toto-2.0-1B,TiRex,0.667,0.417,0.917,0.004,-0.047,0.042
-Toto-2.0-1B,Toto-2.0-22m,0.833,0.583,1.0,0.001,-0.102,0.066
-Toto-2.0-1B,Chronos-2,0.75,0.5,1.0,0.024,-0.03,0.068
-Toto-2.0-1B,FlowState,0.833,0.583,1.0,0.024,-0.148,0.118
-Toto-2.0-1B,Toto-1.0,0.75,0.5,1.0,0.069,-0.007,0.141
-Toto-2.0-1B,TabPFN-TS,0.833,0.583,1.0,0.036,-0.093,0.128
-Toto-2.0-1B,TimesFM-2.5,0.75,0.5,0.917,0.051,0.008,0.092
-Toto-2.0-1B,Toto-2.0-4m,0.833,0.583,1.0,0.065,-0.05,0.147
-Toto-2.0-1B,Stat. Ensemble,0.75,0.5,1.0,0.07,-0.103,0.189
-Toto-2.0-1B,Chronos-Bolt,0.917,0.75,1.0,0.106,0.031,0.179
-Toto-2.0-1B,AutoETS,0.75,0.5,1.0,0.088,-0.019,0.161
-Toto-2.0-1B,Seasonal Naive,0.917,0.75,1.0,0.424,0.268,0.551
-Toto-2.0-2.5B,TiRex-2,0.417,0.167,0.75,-0.05,-0.132,0.024
-Toto-2.0-2.5B,Toto-2.0-1B,0.667,0.417,0.917,0.008,-0.017,0.035
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,Toto-2.0-313m,0.667,0.417,0.917,0.012,-0.006,0.031
-Toto-2.0-2.5B,TiRex,0.5,0.25,0.752,0.012,-0.023,0.05
-Toto-2.0-2.5B,Toto-2.0-22m,0.667,0.417,0.917,0.008,-0.067,0.071
-Toto-2.0-2.5B,Chronos-2,0.667,0.417,0.917,0.031,-0.005,0.066
-Toto-2.0-2.5B,FlowState,0.75,0.5,1.0,0.032,-0.113,0.118
-Toto-2.0-2.5B,Toto-1.0,0.75,0.5,1.0,0.076,0.004,0.152
-Toto-2.0-2.5B,TabPFN-TS,0.75,0.5,1.0,0.043,-0.062,0.119
-Toto-2.0-2.5B,TimesFM-2.5,0.75,0.5,1.0,0.058,0.023,0.098
-Toto-2.0-2.5B,Toto-2.0-4m,0.833,0.583,1.0,0.072,-0.015,0.154
-Toto-2.0-2.5B,Stat. Ensemble,0.75,0.5,1.0,0.078,-0.064,0.184
-Toto-2.0-2.5B,Chronos-Bolt,0.833,0.583,1.0,0.113,0.048,0.183
-Toto-2.0-2.5B,AutoETS,0.75,0.5,1.0,0.095,0.016,0.157
-Toto-2.0-2.5B,Seasonal Naive,0.917,0.75,1.0,0.428,0.293,0.546
-Toto-2.0-313m,TiRex-2,0.167,0.0,0.417,-0.063,-0.147,0.008
-Toto-2.0-313m,Toto-2.0-1B,0.167,0.0,0.417,-0.005,-0.036,0.032
-Toto-2.0-313m,Toto-2.0-2.5B,0.333,0.083,0.583,-0.013,-0.032,0.006
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,TiRex,0.667,0.417,0.917,-0.0,-0.036,0.031
-Toto-2.0-313m,Toto-2.0-22m,0.75,0.5,1.0,-0.004,-0.07,0.045
-Toto-2.0-313m,Chronos-2,0.583,0.333,0.833,0.019,-0.026,0.058
-Toto-2.0-313m,FlowState,0.75,0.5,1.0,0.02,-0.121,0.107
-Toto-2.0-313m,Toto-1.0,0.75,0.5,1.0,0.064,0.003,0.132
-Toto-2.0-313m,TabPFN-TS,0.667,0.417,0.917,0.032,-0.07,0.111
-Toto-2.0-313m,TimesFM-2.5,0.75,0.5,1.0,0.046,0.006,0.086
-Toto-2.0-313m,Toto-2.0-4m,0.833,0.583,1.0,0.06,-0.02,0.135
-Toto-2.0-313m,Stat. Ensemble,0.75,0.5,1.0,0.066,-0.074,0.17
-Toto-2.0-313m,Chronos-Bolt,0.833,0.583,1.0,0.102,0.048,0.161
-Toto-2.0-313m,AutoETS,0.75,0.5,1.0,0.084,0.01,0.142
-Toto-2.0-313m,Seasonal Naive,0.917,0.75,1.0,0.421,0.285,0.539
-TiRex,TiRex-2,0.083,0.0,0.25,-0.063,-0.114,-0.021
-TiRex,Toto-2.0-1B,0.333,0.083,0.583,-0.005,-0.044,0.045
-TiRex,Toto-2.0-2.5B,0.5,0.248,0.75,-0.012,-0.052,0.022
-TiRex,Toto-2.0-313m,0.333,0.083,0.583,0.0,-0.031,0.034
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,Toto-2.0-22m,0.417,0.167,0.667,-0.004,-0.057,0.046
-TiRex,Chronos-2,0.583,0.333,0.833,0.019,-0.029,0.058
-TiRex,FlowState,0.75,0.5,1.0,0.02,-0.099,0.09
-TiRex,Toto-1.0,0.667,0.333,0.917,0.064,0.009,0.124
-TiRex,TabPFN-TS,0.75,0.5,1.0,0.032,-0.059,0.112
-TiRex,TimesFM-2.5,0.833,0.667,1.0,0.047,0.005,0.084
-TiRex,Toto-2.0-4m,0.75,0.5,1.0,0.06,-0.009,0.128
-TiRex,Stat. Ensemble,0.75,0.5,1.0,0.066,-0.055,0.161
-TiRex,Chronos-Bolt,0.917,0.75,1.0,0.102,0.047,0.167
-TiRex,AutoETS,0.833,0.583,1.0,0.084,0.017,0.145
-TiRex,Seasonal Naive,1.0,1.0,1.0,0.421,0.287,0.546
-Toto-2.0-22m,TiRex-2,0.25,0.083,0.5,-0.059,-0.136,0.002
-Toto-2.0-22m,Toto-2.0-1B,0.167,0.0,0.417,-0.001,-0.071,0.093
-Toto-2.0-22m,Toto-2.0-2.5B,0.333,0.083,0.583,-0.008,-0.076,0.063
-Toto-2.0-22m,Toto-2.0-313m,0.25,0.0,0.5,0.004,-0.047,0.066
-Toto-2.0-22m,TiRex,0.583,0.333,0.833,0.004,-0.048,0.054
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,Chronos-2,0.75,0.5,1.0,0.023,-0.054,0.089
-Toto-2.0-22m,FlowState,0.583,0.333,0.833,0.024,-0.06,0.092
-Toto-2.0-22m,Toto-1.0,0.833,0.583,1.0,0.068,0.015,0.122
-Toto-2.0-22m,TabPFN-TS,0.583,0.333,0.833,0.035,-0.049,0.113
-Toto-2.0-22m,TimesFM-2.5,0.75,0.5,1.0,0.05,-0.027,0.127
-Toto-2.0-22m,Toto-2.0-4m,1.0,1.0,1.0,0.064,0.041,0.091
-Toto-2.0-22m,Stat. Ensemble,0.667,0.417,0.917,0.07,-0.032,0.161
-Toto-2.0-22m,Chronos-Bolt,0.917,0.75,1.0,0.105,0.063,0.147
-Toto-2.0-22m,AutoETS,0.917,0.75,1.0,0.088,0.02,0.13
-Toto-2.0-22m,Seasonal Naive,0.917,0.75,1.0,0.423,0.3,0.539
-Chronos-2,TiRex-2,0.167,0.0,0.417,-0.084,-0.164,-0.01
-Chronos-2,Toto-2.0-1B,0.25,0.0,0.5,-0.024,-0.072,0.029
-Chronos-2,Toto-2.0-2.5B,0.333,0.083,0.583,-0.032,-0.07,0.005
-Chronos-2,Toto-2.0-313m,0.417,0.167,0.667,-0.019,-0.061,0.025
-Chronos-2,TiRex,0.417,0.167,0.667,-0.02,-0.062,0.028
-Chronos-2,Toto-2.0-22m,0.25,0.0,0.5,-0.024,-0.098,0.052
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,FlowState,0.583,0.333,0.833,0.001,-0.142,0.096
-Chronos-2,Toto-1.0,0.5,0.25,0.833,0.046,-0.028,0.132
-Chronos-2,TabPFN-TS,0.667,0.417,0.917,0.013,-0.089,0.095
-Chronos-2,TimesFM-2.5,0.667,0.333,0.917,0.028,-0.008,0.061
-Chronos-2,Toto-2.0-4m,0.667,0.415,0.917,0.042,-0.047,0.135
-Chronos-2,Stat. Ensemble,0.833,0.583,1.0,0.048,-0.082,0.141
-Chronos-2,Chronos-Bolt,0.667,0.417,0.917,0.084,0.014,0.167
-Chronos-2,AutoETS,0.917,0.75,1.0,0.066,0.004,0.112
-Chronos-2,Seasonal Naive,0.917,0.75,1.0,0.41,0.281,0.527
-FlowState,TiRex-2,0.083,0.0,0.25,-0.085,-0.16,0.002
-FlowState,Toto-2.0-1B,0.167,0.0,0.417,-0.025,-0.134,0.129
-FlowState,Toto-2.0-2.5B,0.25,0.0,0.5,-0.033,-0.134,0.102
-FlowState,Toto-2.0-313m,0.25,0.0,0.5,-0.02,-0.119,0.108
-FlowState,TiRex,0.25,0.0,0.5,-0.02,-0.099,0.09
-FlowState,Toto-2.0-22m,0.417,0.167,0.667,-0.025,-0.101,0.057
-FlowState,Chronos-2,0.417,0.167,0.667,-0.001,-0.106,0.124
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,Toto-1.0,0.583,0.332,0.833,0.045,-0.064,0.156
-FlowState,TabPFN-TS,0.667,0.417,0.917,0.012,-0.07,0.076
-FlowState,TimesFM-2.5,0.583,0.333,0.833,0.027,-0.07,0.156
-FlowState,Toto-2.0-4m,0.5,0.25,0.75,0.041,-0.039,0.119
-FlowState,Stat. Ensemble,0.583,0.333,0.833,0.047,-0.025,0.119
-FlowState,Chronos-Bolt,0.583,0.332,0.833,0.083,-0.022,0.187
-FlowState,AutoETS,0.667,0.417,0.917,0.065,-0.019,0.146
-FlowState,Seasonal Naive,0.917,0.75,1.0,0.409,0.289,0.52
-Toto-1.0,TiRex-2,0.083,0.0,0.25,-0.137,-0.234,-0.049
-Toto-1.0,Toto-2.0-1B,0.25,0.0,0.5,-0.074,-0.164,0.007
-Toto-1.0,Toto-2.0-2.5B,0.25,0.0,0.5,-0.082,-0.179,-0.004
-Toto-1.0,Toto-2.0-313m,0.25,0.0,0.5,-0.069,-0.151,-0.003
-Toto-1.0,TiRex,0.333,0.083,0.667,-0.069,-0.142,-0.009
-Toto-1.0,Toto-2.0-22m,0.167,0.0,0.417,-0.073,-0.139,-0.015
-Toto-1.0,Chronos-2,0.5,0.167,0.75,-0.048,-0.153,0.028
-Toto-1.0,FlowState,0.417,0.167,0.668,-0.047,-0.184,0.06
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,TabPFN-TS,0.583,0.333,0.833,-0.035,-0.158,0.074
-Toto-1.0,TimesFM-2.5,0.583,0.333,0.833,-0.019,-0.113,0.05
-Toto-1.0,Toto-2.0-4m,0.583,0.333,0.833,-0.004,-0.072,0.047
-Toto-1.0,Stat. Ensemble,0.583,0.333,0.833,0.002,-0.131,0.109
-Toto-1.0,Chronos-Bolt,0.833,0.667,1.0,0.04,0.003,0.076
-Toto-1.0,AutoETS,0.667,0.417,0.917,0.021,-0.072,0.095
-Toto-1.0,Seasonal Naive,0.833,0.583,1.0,0.381,0.237,0.506
-TabPFN-TS,TiRex-2,0.333,0.083,0.583,-0.098,-0.197,-0.016
-TabPFN-TS,Toto-2.0-1B,0.167,0.0,0.417,-0.037,-0.147,0.085
-TabPFN-TS,Toto-2.0-2.5B,0.25,0.0,0.5,-0.045,-0.135,0.059
-TabPFN-TS,Toto-2.0-313m,0.333,0.083,0.583,-0.033,-0.125,0.065
-TabPFN-TS,TiRex,0.25,0.0,0.5,-0.033,-0.126,0.056
-TabPFN-TS,Toto-2.0-22m,0.417,0.167,0.667,-0.037,-0.127,0.046
-TabPFN-TS,Chronos-2,0.333,0.083,0.583,-0.013,-0.105,0.082
-TabPFN-TS,FlowState,0.333,0.083,0.583,-0.012,-0.082,0.066
-TabPFN-TS,Toto-1.0,0.417,0.167,0.667,0.034,-0.08,0.137
-TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS,TimesFM-2.5,0.5,0.25,0.75,0.015,-0.08,0.115
-TabPFN-TS,Toto-2.0-4m,0.583,0.331,0.833,0.03,-0.068,0.123
-TabPFN-TS,Stat. Ensemble,0.5,0.25,0.833,0.036,-0.043,0.12
-TabPFN-TS,Chronos-Bolt,0.583,0.331,0.833,0.072,-0.043,0.173
-TabPFN-TS,AutoETS,0.75,0.5,1.0,0.054,-0.021,0.112
-TabPFN-TS,Seasonal Naive,1.0,1.0,1.0,0.402,0.302,0.502
-TimesFM-2.5,TiRex-2,0.083,0.0,0.25,-0.115,-0.199,-0.052
-TimesFM-2.5,Toto-2.0-1B,0.25,0.083,0.5,-0.054,-0.101,-0.008
-TimesFM-2.5,Toto-2.0-2.5B,0.25,0.0,0.5,-0.062,-0.108,-0.023
-TimesFM-2.5,Toto-2.0-313m,0.25,0.0,0.5,-0.049,-0.094,-0.006
-TimesFM-2.5,TiRex,0.167,0.0,0.333,-0.049,-0.092,-0.005
-TimesFM-2.5,Toto-2.0-22m,0.25,0.0,0.5,-0.053,-0.146,0.027
-TimesFM-2.5,Chronos-2,0.333,0.083,0.667,-0.029,-0.064,0.008
-TimesFM-2.5,FlowState,0.417,0.167,0.667,-0.028,-0.185,0.066
-TimesFM-2.5,Toto-1.0,0.417,0.167,0.667,0.019,-0.052,0.102
-TimesFM-2.5,TabPFN-TS,0.5,0.25,0.75,-0.016,-0.13,0.074
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,Toto-2.0-4m,0.5,0.25,0.75,0.015,-0.091,0.11
-TimesFM-2.5,Stat. Ensemble,0.667,0.417,0.917,0.021,-0.12,0.113
-TimesFM-2.5,Chronos-Bolt,0.583,0.333,0.833,0.058,-0.015,0.143
-TimesFM-2.5,AutoETS,0.75,0.5,1.0,0.04,-0.045,0.104
-TimesFM-2.5,Seasonal Naive,0.917,0.75,1.0,0.393,0.257,0.517
-Toto-2.0-4m,TiRex-2,0.083,0.0,0.25,-0.132,-0.238,-0.051
-Toto-2.0-4m,Toto-2.0-1B,0.167,0.0,0.417,-0.069,-0.172,0.048
-Toto-2.0-4m,Toto-2.0-2.5B,0.167,0.0,0.417,-0.078,-0.182,0.015
-Toto-2.0-4m,Toto-2.0-313m,0.167,0.0,0.417,-0.064,-0.156,0.019
-Toto-2.0-4m,TiRex,0.25,0.0,0.5,-0.064,-0.147,0.009
-Toto-2.0-4m,Toto-2.0-22m,0.0,0.0,0.0,-0.069,-0.101,-0.043
-Toto-2.0-4m,Chronos-2,0.333,0.083,0.585,-0.044,-0.156,0.045
-Toto-2.0-4m,FlowState,0.5,0.25,0.75,-0.043,-0.135,0.037
-Toto-2.0-4m,Toto-1.0,0.417,0.167,0.667,0.004,-0.049,0.067
-Toto-2.0-4m,TabPFN-TS,0.417,0.167,0.669,-0.031,-0.14,0.063
-Toto-2.0-4m,TimesFM-2.5,0.5,0.25,0.75,-0.015,-0.124,0.083
-Toto-2.0-4m,Toto-2.0-4m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-4m,Stat. Ensemble,0.667,0.417,0.917,0.006,-0.12,0.107
-Toto-2.0-4m,Chronos-Bolt,0.75,0.5,1.0,0.044,0.007,0.091
-Toto-2.0-4m,AutoETS,0.75,0.5,1.0,0.025,-0.068,0.081
-Toto-2.0-4m,Seasonal Naive,0.917,0.75,1.0,0.384,0.244,0.506
-Stat. Ensemble,TiRex-2,0.167,0.0,0.417,-0.139,-0.244,-0.042
-Stat. Ensemble,Toto-2.0-1B,0.25,0.0,0.5,-0.076,-0.232,0.093
-Stat. Ensemble,Toto-2.0-2.5B,0.25,0.0,0.5,-0.084,-0.226,0.061
-Stat. Ensemble,Toto-2.0-313m,0.25,0.0,0.5,-0.071,-0.205,0.069
-Stat. Ensemble,TiRex,0.25,0.0,0.5,-0.071,-0.192,0.052
-Stat. Ensemble,Toto-2.0-22m,0.333,0.083,0.583,-0.075,-0.192,0.031
-Stat. Ensemble,Chronos-2,0.167,0.0,0.417,-0.05,-0.164,0.076
-Stat. Ensemble,FlowState,0.417,0.167,0.667,-0.049,-0.135,0.025
-Stat. Ensemble,Toto-1.0,0.417,0.167,0.667,-0.002,-0.122,0.116
-Stat. Ensemble,TabPFN-TS,0.5,0.167,0.75,-0.037,-0.136,0.042
-Stat. Ensemble,TimesFM-2.5,0.333,0.083,0.583,-0.021,-0.127,0.107
-Stat. Ensemble,Toto-2.0-4m,0.333,0.083,0.583,-0.006,-0.12,0.107
-Stat. Ensemble,Stat. Ensemble,0.5,0.5,0.5,0.0,0.0,0.0
-Stat. Ensemble,Chronos-Bolt,0.417,0.167,0.667,0.038,-0.083,0.155
-Stat. Ensemble,AutoETS,0.417,0.167,0.667,0.019,-0.068,0.095
-Stat. Ensemble,Seasonal Naive,1.0,1.0,1.0,0.38,0.283,0.482
-Chronos-Bolt,TiRex-2,0.0,0.0,0.0,-0.184,-0.312,-0.088
-Chronos-Bolt,Toto-2.0-1B,0.083,0.0,0.25,-0.118,-0.219,-0.032
-Chronos-Bolt,Toto-2.0-2.5B,0.167,0.0,0.417,-0.127,-0.224,-0.051
-Chronos-Bolt,Toto-2.0-313m,0.167,0.0,0.417,-0.113,-0.192,-0.051
-Chronos-Bolt,TiRex,0.083,0.0,0.25,-0.113,-0.2,-0.049
-Chronos-Bolt,Toto-2.0-22m,0.083,0.0,0.25,-0.118,-0.172,-0.068
-Chronos-Bolt,Chronos-2,0.333,0.083,0.583,-0.092,-0.2,-0.014
-Chronos-Bolt,FlowState,0.417,0.167,0.668,-0.091,-0.23,0.021
-Chronos-Bolt,Toto-1.0,0.167,0.0,0.333,-0.041,-0.083,-0.003
-Chronos-Bolt,TabPFN-TS,0.417,0.167,0.669,-0.078,-0.208,0.042
-Chronos-Bolt,TimesFM-2.5,0.417,0.167,0.667,-0.061,-0.167,0.014
-Chronos-Bolt,Toto-2.0-4m,0.25,0.0,0.5,-0.046,-0.101,-0.007
-Chronos-Bolt,Stat. Ensemble,0.583,0.333,0.833,-0.04,-0.184,0.077
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,AutoETS,0.583,0.333,0.833,-0.019,-0.125,0.057
-Chronos-Bolt,Seasonal Naive,0.833,0.583,1.0,0.355,0.212,0.48
-AutoETS,TiRex-2,0.083,0.0,0.25,-0.161,-0.26,-0.087
-AutoETS,Toto-2.0-1B,0.25,0.0,0.5,-0.097,-0.192,0.019
-AutoETS,Toto-2.0-2.5B,0.25,0.0,0.5,-0.106,-0.186,-0.016
-AutoETS,Toto-2.0-313m,0.25,0.0,0.5,-0.092,-0.165,-0.01
-AutoETS,TiRex,0.167,0.0,0.417,-0.092,-0.169,-0.018
-AutoETS,Toto-2.0-22m,0.083,0.0,0.25,-0.096,-0.149,-0.02
-AutoETS,Chronos-2,0.083,0.0,0.25,-0.071,-0.126,-0.004
-AutoETS,FlowState,0.333,0.083,0.583,-0.07,-0.17,0.018
-AutoETS,Toto-1.0,0.333,0.083,0.583,-0.022,-0.104,0.067
-AutoETS,TabPFN-TS,0.25,0.0,0.5,-0.057,-0.126,0.021
-AutoETS,TimesFM-2.5,0.25,0.0,0.5,-0.041,-0.116,0.043
-AutoETS,Toto-2.0-4m,0.25,0.0,0.5,-0.026,-0.088,0.063
-AutoETS,Stat. Ensemble,0.583,0.333,0.833,-0.02,-0.105,0.064
-AutoETS,Chronos-Bolt,0.417,0.167,0.667,0.019,-0.06,0.111
-AutoETS,AutoETS,0.5,0.5,0.5,0.0,0.0,0.0
-AutoETS,Seasonal Naive,0.917,0.75,1.0,0.368,0.243,0.486
-Seasonal Naive,TiRex-2,0.0,0.0,0.0,-0.836,-1.325,-0.508
-Seasonal Naive,Toto-2.0-1B,0.083,0.0,0.25,-0.735,-1.226,-0.367
-Seasonal Naive,Toto-2.0-2.5B,0.083,0.0,0.25,-0.748,-1.202,-0.414
-Seasonal Naive,Toto-2.0-313m,0.083,0.0,0.25,-0.727,-1.169,-0.398
-Seasonal Naive,TiRex,0.0,0.0,0.0,-0.727,-1.204,-0.402
-Seasonal Naive,Toto-2.0-22m,0.083,0.0,0.25,-0.734,-1.169,-0.429
-Seasonal Naive,Chronos-2,0.083,0.0,0.25,-0.694,-1.116,-0.391
-Seasonal Naive,FlowState,0.083,0.0,0.25,-0.692,-1.082,-0.407
-Seasonal Naive,Toto-1.0,0.167,0.0,0.417,-0.616,-1.022,-0.311
-Seasonal Naive,TabPFN-TS,0.0,0.0,0.0,-0.672,-1.007,-0.432
-Seasonal Naive,TimesFM-2.5,0.083,0.0,0.25,-0.647,-1.071,-0.346
-Seasonal Naive,Toto-2.0-4m,0.083,0.0,0.25,-0.622,-1.024,-0.323
-Seasonal Naive,Stat. Ensemble,0.0,0.0,0.0,-0.613,-0.931,-0.394
-Seasonal Naive,Chronos-Bolt,0.167,0.0,0.417,-0.551,-0.924,-0.269
-Seasonal Naive,AutoETS,0.083,0.0,0.25,-0.581,-0.947,-0.321
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_energy/leaderboard_MASE.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-Chronos-2,84.75783475783474,35.398351985937104,0.0,3.4120501715909093,0.0,0.0
-Toto-2.0-1B,77.35042735042735,27.64063711794009,0.0,3.1623076374715904,0.0,0.0
-Toto-2.0-2.5B,77.20797720797721,27.403361161284135,0.0,6.4650776003125,0.0,0.0
-TabPFN-TS-3,75.92592592592594,34.00489490838103,0.0,822.0435218492969,0.0,0.0
-TiRex-2,75.7834757834758,32.34547171146631,0.0,1.0366915774648078,0.0,0.0
-Toto-2.0-313m,74.92877492877491,27.247610226794162,0.0,1.5456846913541669,0.0,0.0
-TiRex,66.52421652421651,25.111125954829205,0.0,1.3324642875,0.038461538461538464,0.0
-TabPFN-TS,64.52991452991454,29.948417313219487,0.0,308.48925294219475,0.0,0.0
-TimesFM-2.5,63.817663817663814,24.470577229456005,0.0,35.73234459616477,0.15384615384615385,0.0
-Toto-2.0-22m,63.10541310541311,25.222517255488896,0.0,0.7798815821022727,0.0,0.0
-Chronos-Bolt,60.25641025641026,24.79493112223894,0.0,1.1602838375000002,0.0,0.0
-FlowState,58.974358974358964,24.74097538777954,0.0,3.7859752799626865,0.15384615384615385,0.0
-Moirai-2.0,57.692307692307686,23.276855703905884,0.0,2.549116965535714,0.3076923076923077,0.0
-Sundial-Base,54.98575498575499,25.973733886600225,0.0,8.734264116875,0.038461538461538464,0.0
-Toto-1.0,54.98575498575499,22.17352687153604,0.0,64.32606581959577,0.15384615384615385,0.0
-Toto-2.0-4m,54.7008547008547,21.834602126597346,0.0,0.7024468823376624,0.0,0.0
-TFT,47.86324786324787,24.332626654075018,7067.210990843215,5.868696277689394,0.0,0.0
-DeepAR,42.52136752136752,20.515410969632153,13498.838423148572,8.687442574285715,0.0,11.538461538461538
-PatchTST,39.743589743589745,18.853426287300014,7221.856288165601,6.349855852499999,0.0,0.0
-CatBoost,39.60113960113959,17.15191259995018,498.1807509,5.586804820681818,0.0,0.0
-LightGBM,36.75213675213675,14.854815383201469,47.29828941238095,4.303395228143939,0.0,0.0
-Stat. Ensemble,27.27920227920228,4.447406228151163,0.0,2051.548594149911,0.0,7.6923076923076925
-AutoARIMA,26.139601139601137,2.212327431466543,0.0,1885.5145473599553,0.0,7.6923076923076925
-Seasonal Naive,21.652421652421648,0.0,0.0,1.042975715,0.0,0.0
-AutoTheta,20.085470085470085,1.1815956958414753,0.0,6.6345268946875,0.0,0.0
-AutoETS,15.242165242165239,-34.97549884253801,0.0,13.387819541051137,0.0,0.0
-Naive,12.606837606837603,-44.773921203129,0.0,1.0805920684374999,0.0,0.0
-Drift,4.985754985754986,-52.29912347479908,0.0,1.081847729375,0.0,0.0

tables/domain_energy/leaderboard_SQL.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-Chronos-2,85.6125356125356,43.696037899366445,0.0,3.4120501715909093,0.0,0.0
-Toto-2.0-1B,81.05413105413105,37.19233498724061,0.0,3.1623076374715904,0.0,0.0
-TiRex-2,80.34188034188034,40.955040522328076,0.0,1.0366915774648078,0.0,0.0
-Toto-2.0-2.5B,80.34188034188034,36.942973998246586,0.0,6.4650776003125,0.0,0.0
-TabPFN-TS-3,77.92022792022793,42.12648526492014,0.0,822.0435218492969,0.0,0.0
-Toto-2.0-313m,77.4928774928775,36.69282240000613,0.0,1.5456846913541669,0.0,0.0
-TiRex,70.94017094017097,34.44791484004565,0.0,1.3324642875,0.038461538461538464,0.0
-Toto-2.0-22m,68.23361823361823,34.72199927167168,0.0,0.7798815821022727,0.0,0.0
-TabPFN-TS,68.0911680911681,38.63838178079146,0.0,308.48925294219475,0.0,0.0
-TimesFM-2.5,64.81481481481481,33.040194549839576,0.0,35.73234459616477,0.15384615384615385,0.0
-FlowState,60.25641025641024,32.4100685185642,0.0,3.7859752799626865,0.15384615384615385,0.0
-Chronos-Bolt,58.974358974358985,32.881689430291104,0.0,1.1602838375000002,0.0,0.0
-Moirai-2.0,57.83475783475783,31.52282472603488,0.0,2.549116965535714,0.3076923076923077,0.0
-Toto-2.0-4m,57.12250712250713,31.473352334477845,0.0,0.7024468823376624,0.0,0.0
-Toto-1.0,56.41025641025641,31.112045696230428,0.0,64.32606581959577,0.15384615384615385,0.0
-TFT,52.70655270655271,32.085719324643314,7067.210990843215,5.868696277689394,0.0,0.0
-Sundial-Base,45.15669515669515,28.52842311909273,0.0,8.734264116875,0.038461538461538464,0.0
-DeepAR,43.94586894586894,26.66949092254881,13498.838423148572,8.687442574285715,0.0,11.538461538461538
-PatchTST,43.01994301994302,25.60679591439182,7221.856288165601,6.349855852499999,0.0,0.0
-AutoARIMA,29.700854700854695,9.139931178596383,0.0,1885.5145473599553,0.0,7.6923076923076925
-Stat. Ensemble,27.136752136752136,6.196332966589502,0.0,2051.548594149911,0.0,7.6923076923076925
-CatBoost,25.64102564102563,8.874064288365757,498.1807509,5.586804820681818,0.0,0.0
-LightGBM,22.649572649572647,6.34745033907752,47.29828941238095,4.303395228143939,0.0,0.0
-Seasonal Naive,19.08831908831909,0.0,0.0,1.042975715,0.0,0.0
-AutoETS,17.66381766381766,-30.210229740669558,0.0,13.387819541051137,0.0,0.0
-AutoTheta,15.811965811965809,-10.643501874241924,0.0,6.6345268946875,0.0,0.0
-Naive,8.903133903133902,-60.57154490567112,0.0,1.0805920684374999,0.0,0.0
-Drift,3.133903133903134,-67.3016518958006,0.0,1.081847729375,0.0,0.0

tables/domain_energy/leaderboard_WAPE.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-Chronos-2,82.62108262108262,37.557901536977845,0.0,3.4120501715909093,0.0,0.0
-Toto-2.0-1B,76.06837606837607,31.032868019309202,0.0,3.1623076374715904,0.0,0.0
-Toto-2.0-313m,75.64102564102564,30.705322754813878,0.0,1.5456846913541669,0.0,0.0
-Toto-2.0-2.5B,73.78917378917377,30.308651726585033,0.0,6.4650776003125,0.0,0.0
-TiRex-2,71.36752136752136,34.43124058342566,0.0,1.0366915774648078,0.0,0.0
-TabPFN-TS-3,70.7977207977208,34.61666637481101,0.0,822.0435218492969,0.0,0.0
-Toto-2.0-22m,65.24216524216523,28.863859566477203,0.0,0.7798815821022727,0.0,0.0
-TiRex,62.25071225071225,27.322662354204475,0.0,1.3324642875,0.038461538461538464,0.0
-TimesFM-2.5,60.68376068376068,26.65794953458317,0.0,35.73234459616477,0.15384615384615385,0.0
-TabPFN-TS,60.541310541310544,30.36322876478197,0.0,308.48925294219475,0.0,0.0
-Chronos-Bolt,57.122507122507116,26.606852502371968,0.0,1.1602838375000002,0.0,0.0
-Moirai-2.0,56.837606837606835,25.99988075597758,0.0,2.549116965535714,0.3076923076923077,0.0
-FlowState,53.84615384615385,26.89142712985859,0.0,3.7859752799626865,0.15384615384615385,0.0
-Sundial-Base,53.13390313390314,28.265544600882,0.0,8.734264116875,0.038461538461538464,0.0
-Toto-1.0,51.85185185185185,24.207524581618266,0.0,64.32606581959577,0.15384615384615385,0.0
-TFT,50.142450142450144,26.59412613673687,7067.210990843215,5.868696277689394,0.0,0.0
-Toto-2.0-4m,49.43019943019942,23.82250300845572,0.0,0.7024468823376624,0.0,0.0
-PatchTST,43.73219373219374,20.65325504182872,7221.856288165601,6.349855852499999,0.0,0.0
-DeepAR,41.95156695156697,21.82047445619971,13498.838423148572,8.687442574285715,0.0,11.538461538461538
-LightGBM,41.3105413105413,20.63835609604817,47.29828941238095,4.303395228143939,0.0,0.0
-CatBoost,40.028490028490026,20.174610152005823,498.1807509,5.586804820681818,0.0,0.0
-Stat. Ensemble,33.97435897435897,8.430993583997726,0.0,2051.548594149911,0.0,7.6923076923076925
-AutoARIMA,25.28490028490028,3.8316800542679386,0.0,1885.5145473599553,0.0,7.6923076923076925
-AutoETS,22.93447293447294,-24.06197476117884,0.0,13.387819541051137,0.0,0.0
-Naive,22.578347578347575,-29.595393529303713,0.0,1.0805920684374999,0.0,0.0
-AutoTheta,22.222222222222218,4.200265666572001,0.0,6.6345268946875,0.0,0.0
-Seasonal Naive,20.08547008547008,0.0,0.0,1.042975715,0.0,0.0
-Drift,14.529914529914533,-36.91555319026642,0.0,1.081847729375,0.0,0.0

tables/domain_energy/leaderboard_WQL.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-Chronos-2,85.32763532763533,45.99295404026385,0.0,3.4120501715909093,0.0,0.0
-Toto-2.0-1B,82.6210826210826,40.95974538328001,0.0,3.1623076374715904,0.0,0.0
-Toto-2.0-2.5B,80.19943019943021,40.25120913531922,0.0,6.4650776003125,0.0,0.0
-Toto-2.0-313m,80.1994301994302,40.431908864449696,0.0,1.5456846913541669,0.0,0.0
-TiRex-2,78.20512820512819,43.430525812131435,0.0,1.0366915774648078,0.0,0.0
-TabPFN-TS-3,74.92877492877494,43.103980194426214,0.0,822.0435218492969,0.0,0.0
-Toto-2.0-22m,70.37037037037037,38.501099243397576,0.0,0.7798815821022727,0.0,0.0
-TiRex,68.66096866096866,37.015923795326046,0.0,1.3324642875,0.038461538461538464,0.0
-TabPFN-TS,66.66666666666669,39.634990899313024,0.0,308.48925294219475,0.0,0.0
-TimesFM-2.5,62.96296296296296,35.74711028493935,0.0,35.73234459616477,0.15384615384615385,0.0
-FlowState,58.68945868945868,35.238708603025636,0.0,3.7859752799626865,0.15384615384615385,0.0
-Chronos-Bolt,58.4045584045584,35.346534587472554,0.0,1.1602838375000002,0.0,0.0
-Moirai-2.0,57.692307692307686,34.54029716114274,0.0,2.549116965535714,0.3076923076923077,0.0
-Toto-2.0-4m,55.55555555555555,33.916952411684484,0.0,0.7024468823376624,0.0,0.0
-Toto-1.0,54.84330484330483,33.68160197994784,0.0,64.32606581959577,0.15384615384615385,0.0
-TFT,53.27635327635329,34.858358688960024,7067.210990843215,5.868696277689394,0.0,0.0
-Sundial-Base,45.29914529914529,31.420585268607393,0.0,8.734264116875,0.038461538461538464,0.0
-PatchTST,44.58689458689459,28.17762114987711,7221.856288165601,6.349855852499999,0.0,0.0
-DeepAR,42.8062678062678,28.82551876839535,13498.838423148572,8.687442574285715,0.0,11.538461538461538
-LightGBM,30.484330484330478,13.804281918946282,47.29828941238095,4.303395228143939,0.0,0.0
-Stat. Ensemble,29.558404558404554,11.001763956139254,0.0,2051.548594149911,0.0,7.6923076923076925
-AutoARIMA,28.133903133903132,10.956865003323434,0.0,1885.5145473599553,0.0,7.6923076923076925
-CatBoost,26.638176638176635,13.30060154143199,498.1807509,5.586804820681818,0.0,0.0
-Seasonal Naive,16.80911680911681,0.0,0.0,1.042975715,0.0,0.0
-AutoETS,16.666666666666664,-24.269495322854407,0.0,13.387819541051137,0.0,0.0
-AutoTheta,16.23931623931624,-4.896832310667398,0.0,6.6345268946875,0.0,0.0
-Naive,9.615384615384617,-50.976730476610335,0.0,1.0805920684374999,0.0,0.0
-Drift,4.5584045584045585,-57.44553171159505,0.0,1.081847729375,0.0,0.0

tables/domain_energy/pairwise_MASE.csv

@@ -1,257 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,Toto-2.0-2.5B,0.654,0.462,0.808,0.11,0.043,0.177
-Chronos-2,Toto-2.0-1B,0.577,0.385,0.769,0.107,0.04,0.174
-Chronos-2,Toto-2.0-313m,0.654,0.462,0.846,0.112,0.04,0.182
-Chronos-2,TiRex-2,0.577,0.385,0.769,0.045,0.001,0.092
-Chronos-2,TabPFN-TS-3,0.654,0.462,0.846,0.021,-0.014,0.058
-Chronos-2,TiRex,0.769,0.615,0.923,0.137,0.066,0.203
-Chronos-2,TabPFN-TS,0.769,0.615,0.923,0.078,0.038,0.118
-Chronos-2,TimesFM-2.5,0.769,0.577,0.923,0.145,0.072,0.212
-Chronos-2,Toto-2.0-22m,0.885,0.769,1.0,0.136,0.072,0.201
-Chronos-2,FlowState,0.846,0.692,0.962,0.142,0.073,0.202
-Chronos-2,Chronos-Bolt,0.962,0.885,1.0,0.141,0.078,0.202
-Chronos-2,Moirai-2.0,0.923,0.808,1.0,0.158,0.092,0.222
-Chronos-2,Toto-1.0,0.846,0.692,0.962,0.17,0.105,0.237
-Chronos-2,Sundial-Base,0.846,0.692,0.962,0.127,0.069,0.195
-Chronos-2,Seasonal Naive,0.962,0.885,1.0,0.354,0.278,0.422
-Toto-2.0-2.5B,Chronos-2,0.346,0.192,0.538,-0.124,-0.214,-0.045
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,Toto-2.0-1B,0.5,0.346,0.692,-0.003,-0.011,0.004
-Toto-2.0-2.5B,Toto-2.0-313m,0.615,0.423,0.808,0.002,-0.013,0.016
-Toto-2.0-2.5B,TiRex-2,0.5,0.308,0.692,-0.073,-0.162,-0.001
-Toto-2.0-2.5B,TabPFN-TS-3,0.462,0.269,0.654,-0.1,-0.208,-0.003
-Toto-2.0-2.5B,TiRex,0.692,0.5,0.846,0.031,0.007,0.055
-Toto-2.0-2.5B,TabPFN-TS,0.654,0.462,0.846,-0.036,-0.133,0.042
-Toto-2.0-2.5B,TimesFM-2.5,0.692,0.5,0.846,0.039,0.01,0.071
-Toto-2.0-2.5B,Toto-2.0-22m,0.808,0.654,0.962,0.029,0.016,0.042
-Toto-2.0-2.5B,FlowState,0.808,0.654,0.923,0.035,-0.0,0.067
-Toto-2.0-2.5B,Chronos-Bolt,0.846,0.692,0.962,0.035,0.005,0.062
-Toto-2.0-2.5B,Moirai-2.0,0.846,0.692,0.962,0.054,0.028,0.083
-Toto-2.0-2.5B,Toto-1.0,0.808,0.654,0.962,0.067,0.04,0.101
-Toto-2.0-2.5B,Sundial-Base,0.769,0.615,0.923,0.019,-0.071,0.108
-Toto-2.0-2.5B,Seasonal Naive,0.962,0.885,1.0,0.274,0.211,0.335
-Toto-2.0-1B,Chronos-2,0.423,0.231,0.615,-0.12,-0.211,-0.042
-Toto-2.0-1B,Toto-2.0-2.5B,0.5,0.308,0.654,0.003,-0.004,0.011
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-313m,0.5,0.308,0.692,0.005,-0.008,0.019
-Toto-2.0-1B,TiRex-2,0.615,0.423,0.808,-0.07,-0.162,0.004
-Toto-2.0-1B,TabPFN-TS-3,0.423,0.231,0.615,-0.096,-0.205,0.001
-Toto-2.0-1B,TiRex,0.654,0.462,0.808,0.034,0.011,0.059
-Toto-2.0-1B,TabPFN-TS,0.615,0.423,0.808,-0.033,-0.13,0.048
-Toto-2.0-1B,TimesFM-2.5,0.769,0.577,0.923,0.042,0.012,0.074
-Toto-2.0-1B,Toto-2.0-22m,0.846,0.692,0.962,0.032,0.02,0.046
-Toto-2.0-1B,FlowState,0.769,0.615,0.923,0.039,0.004,0.069
-Toto-2.0-1B,Chronos-Bolt,0.846,0.692,0.962,0.038,0.007,0.066
-Toto-2.0-1B,Moirai-2.0,0.846,0.692,0.962,0.057,0.034,0.083
-Toto-2.0-1B,Toto-1.0,0.808,0.654,0.923,0.07,0.043,0.102
-Toto-2.0-1B,Sundial-Base,0.731,0.577,0.885,0.023,-0.068,0.11
-Toto-2.0-1B,Seasonal Naive,0.923,0.808,1.0,0.276,0.21,0.34
-Toto-2.0-313m,Chronos-2,0.346,0.154,0.538,-0.126,-0.222,-0.042
-Toto-2.0-313m,Toto-2.0-2.5B,0.385,0.192,0.577,-0.002,-0.016,0.013
-Toto-2.0-313m,Toto-2.0-1B,0.5,0.308,0.692,-0.005,-0.019,0.008
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,TiRex-2,0.5,0.308,0.692,-0.075,-0.172,0.001
-Toto-2.0-313m,TabPFN-TS-3,0.462,0.269,0.654,-0.102,-0.213,-0.002
-Toto-2.0-313m,TiRex,0.615,0.423,0.808,0.029,0.011,0.048
-Toto-2.0-313m,TabPFN-TS,0.654,0.462,0.846,-0.039,-0.142,0.043
-Toto-2.0-313m,TimesFM-2.5,0.692,0.5,0.847,0.037,0.012,0.062
-Toto-2.0-313m,Toto-2.0-22m,0.731,0.538,0.885,0.027,0.014,0.041
-Toto-2.0-313m,FlowState,0.769,0.615,0.923,0.033,0.002,0.062
-Toto-2.0-313m,Chronos-Bolt,0.731,0.576,0.885,0.033,0.004,0.06
-Toto-2.0-313m,Moirai-2.0,0.769,0.577,0.923,0.052,0.025,0.08
-Toto-2.0-313m,Toto-1.0,0.731,0.538,0.885,0.065,0.037,0.096
-Toto-2.0-313m,Sundial-Base,0.808,0.654,0.962,0.017,-0.072,0.099
-Toto-2.0-313m,Seasonal Naive,0.923,0.808,1.0,0.272,0.206,0.336
-TiRex-2,Chronos-2,0.423,0.231,0.615,-0.047,-0.101,-0.001
-TiRex-2,Toto-2.0-2.5B,0.5,0.308,0.692,0.068,0.001,0.14
-TiRex-2,Toto-2.0-1B,0.385,0.192,0.577,0.065,-0.004,0.139
-TiRex-2,Toto-2.0-313m,0.5,0.308,0.692,0.07,-0.001,0.147
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,TabPFN-TS-3,0.5,0.308,0.692,-0.025,-0.087,0.028
-TiRex-2,TiRex,0.769,0.615,0.923,0.097,0.031,0.165
-TiRex-2,TabPFN-TS,0.654,0.462,0.846,0.034,-0.02,0.085
-TiRex-2,TimesFM-2.5,0.654,0.462,0.808,0.104,0.032,0.177
-TiRex-2,Toto-2.0-22m,0.577,0.385,0.769,0.095,0.029,0.163
-TiRex-2,FlowState,0.731,0.577,0.885,0.101,0.03,0.169
-TiRex-2,Chronos-Bolt,0.654,0.462,0.846,0.1,0.031,0.175
-TiRex-2,Moirai-2.0,0.692,0.538,0.846,0.118,0.055,0.181
-TiRex-2,Toto-1.0,0.692,0.538,0.846,0.131,0.065,0.2
-TiRex-2,Sundial-Base,0.808,0.654,0.962,0.086,0.006,0.164
-TiRex-2,Seasonal Naive,0.962,0.885,1.0,0.323,0.243,0.395
-TabPFN-TS-3,Chronos-2,0.346,0.154,0.538,-0.022,-0.062,0.013
-TabPFN-TS-3,Toto-2.0-2.5B,0.538,0.346,0.731,0.091,0.003,0.172
-TabPFN-TS-3,Toto-2.0-1B,0.577,0.385,0.769,0.088,-0.001,0.17
-TabPFN-TS-3,Toto-2.0-313m,0.538,0.346,0.731,0.093,0.002,0.175
-TabPFN-TS-3,TiRex-2,0.5,0.308,0.692,0.025,-0.029,0.08
-TabPFN-TS-3,TabPFN-TS-3,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS-3,TiRex,0.538,0.346,0.731,0.119,0.032,0.197
-TabPFN-TS-3,TabPFN-TS,0.731,0.577,0.885,0.058,0.011,0.101
-TabPFN-TS-3,TimesFM-2.5,0.692,0.5,0.846,0.126,0.038,0.206
-TabPFN-TS-3,Toto-2.0-22m,0.615,0.423,0.77,0.117,0.034,0.194
-TabPFN-TS-3,FlowState,0.692,0.5,0.846,0.123,0.036,0.198
-TabPFN-TS-3,Chronos-Bolt,0.654,0.462,0.809,0.122,0.043,0.198
-TabPFN-TS-3,Moirai-2.0,0.654,0.462,0.808,0.14,0.054,0.22
-TabPFN-TS-3,Toto-1.0,0.692,0.5,0.846,0.152,0.072,0.227
-TabPFN-TS-3,Sundial-Base,0.769,0.615,0.923,0.108,0.038,0.185
-TabPFN-TS-3,Seasonal Naive,0.962,0.885,1.0,0.34,0.265,0.41
-TiRex,Chronos-2,0.231,0.077,0.385,-0.159,-0.255,-0.07
-TiRex,Toto-2.0-2.5B,0.308,0.154,0.5,-0.032,-0.059,-0.007
-TiRex,Toto-2.0-1B,0.346,0.192,0.538,-0.035,-0.063,-0.011
-TiRex,Toto-2.0-313m,0.385,0.192,0.577,-0.029,-0.051,-0.011
-TiRex,TiRex-2,0.231,0.077,0.385,-0.107,-0.198,-0.032
-TiRex,TabPFN-TS-3,0.462,0.269,0.654,-0.135,-0.246,-0.034
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,TabPFN-TS,0.5,0.308,0.692,-0.069,-0.171,0.013
-TiRex,TimesFM-2.5,0.519,0.327,0.731,0.008,-0.015,0.033
-TiRex,Toto-2.0-22m,0.577,0.385,0.769,-0.001,-0.024,0.017
-TiRex,FlowState,0.481,0.308,0.654,0.005,-0.022,0.033
-TiRex,Chronos-Bolt,0.558,0.385,0.731,0.004,-0.021,0.032
-TiRex,Moirai-2.0,0.558,0.365,0.731,0.024,-0.003,0.056
-TiRex,Toto-1.0,0.673,0.5,0.846,0.038,0.011,0.068
-TiRex,Sundial-Base,0.75,0.596,0.904,-0.012,-0.103,0.066
-TiRex,Seasonal Naive,0.923,0.808,1.0,0.251,0.191,0.308
-TabPFN-TS,Chronos-2,0.231,0.077,0.385,-0.084,-0.133,-0.039
-TabPFN-TS,Toto-2.0-2.5B,0.346,0.154,0.538,0.035,-0.043,0.117
-TabPFN-TS,Toto-2.0-1B,0.385,0.192,0.577,0.032,-0.05,0.115
-TabPFN-TS,Toto-2.0-313m,0.346,0.154,0.538,0.037,-0.045,0.124
-TabPFN-TS,TiRex-2,0.346,0.154,0.538,-0.035,-0.093,0.02
-TabPFN-TS,TabPFN-TS-3,0.269,0.115,0.423,-0.061,-0.112,-0.012
-TabPFN-TS,TiRex,0.5,0.308,0.692,0.065,-0.014,0.146
-TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS,TimesFM-2.5,0.5,0.308,0.692,0.073,-0.003,0.152
-TabPFN-TS,Toto-2.0-22m,0.5,0.308,0.692,0.063,-0.016,0.142
-TabPFN-TS,FlowState,0.654,0.462,0.846,0.069,-0.011,0.143
-TabPFN-TS,Chronos-Bolt,0.538,0.346,0.731,0.069,0.002,0.143
-TabPFN-TS,Moirai-2.0,0.5,0.308,0.692,0.087,0.008,0.169
-TabPFN-TS,Toto-1.0,0.577,0.385,0.769,0.1,0.022,0.181
-TabPFN-TS,Sundial-Base,0.5,0.308,0.692,0.054,-0.036,0.143
-TabPFN-TS,Seasonal Naive,0.923,0.808,1.0,0.299,0.216,0.373
-TimesFM-2.5,Chronos-2,0.231,0.077,0.423,-0.169,-0.269,-0.077
-TimesFM-2.5,Toto-2.0-2.5B,0.308,0.154,0.5,-0.04,-0.076,-0.01
-TimesFM-2.5,Toto-2.0-1B,0.231,0.077,0.423,-0.044,-0.08,-0.012
-TimesFM-2.5,Toto-2.0-313m,0.308,0.153,0.5,-0.038,-0.066,-0.012
-TimesFM-2.5,TiRex-2,0.346,0.192,0.538,-0.116,-0.214,-0.033
-TimesFM-2.5,TabPFN-TS-3,0.308,0.154,0.5,-0.144,-0.259,-0.04
-TimesFM-2.5,TiRex,0.481,0.269,0.673,-0.009,-0.034,0.014
-TimesFM-2.5,TabPFN-TS,0.5,0.308,0.692,-0.078,-0.179,0.003
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,Toto-2.0-22m,0.462,0.269,0.654,-0.01,-0.044,0.02
-TimesFM-2.5,FlowState,0.538,0.365,0.712,-0.004,-0.035,0.027
-TimesFM-2.5,Chronos-Bolt,0.577,0.404,0.769,-0.004,-0.033,0.024
-TimesFM-2.5,Moirai-2.0,0.615,0.442,0.808,0.016,-0.028,0.057
-TimesFM-2.5,Toto-1.0,0.692,0.519,0.846,0.03,-0.006,0.071
-TimesFM-2.5,Sundial-Base,0.596,0.423,0.788,-0.02,-0.113,0.062
-TimesFM-2.5,Seasonal Naive,0.923,0.808,1.0,0.245,0.182,0.306
-Toto-2.0-22m,Chronos-2,0.115,0.0,0.231,-0.158,-0.252,-0.077
-Toto-2.0-22m,Toto-2.0-2.5B,0.192,0.038,0.346,-0.03,-0.044,-0.016
-Toto-2.0-22m,Toto-2.0-1B,0.154,0.038,0.308,-0.033,-0.048,-0.021
-Toto-2.0-22m,Toto-2.0-313m,0.269,0.115,0.462,-0.028,-0.043,-0.014
-Toto-2.0-22m,TiRex-2,0.423,0.231,0.615,-0.105,-0.195,-0.029
-Toto-2.0-22m,TabPFN-TS-3,0.385,0.23,0.577,-0.133,-0.241,-0.035
-Toto-2.0-22m,TiRex,0.423,0.231,0.615,0.001,-0.018,0.024
-Toto-2.0-22m,TabPFN-TS,0.5,0.308,0.692,-0.067,-0.166,0.016
-Toto-2.0-22m,TimesFM-2.5,0.538,0.346,0.731,0.01,-0.02,0.042
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,FlowState,0.423,0.268,0.615,0.006,-0.028,0.038
-Toto-2.0-22m,Chronos-Bolt,0.538,0.346,0.731,0.006,-0.025,0.036
-Toto-2.0-22m,Moirai-2.0,0.538,0.346,0.731,0.025,0.002,0.052
-Toto-2.0-22m,Toto-1.0,0.731,0.538,0.885,0.039,0.013,0.071
-Toto-2.0-22m,Sundial-Base,0.654,0.462,0.808,-0.01,-0.105,0.074
-Toto-2.0-22m,Seasonal Naive,0.885,0.731,1.0,0.252,0.188,0.315
-FlowState,Chronos-2,0.154,0.038,0.308,-0.165,-0.253,-0.079
-FlowState,Toto-2.0-2.5B,0.192,0.077,0.346,-0.037,-0.071,0.0
-FlowState,Toto-2.0-1B,0.231,0.077,0.385,-0.04,-0.074,-0.004
-FlowState,Toto-2.0-313m,0.231,0.077,0.385,-0.034,-0.066,-0.002
-FlowState,TiRex-2,0.269,0.115,0.423,-0.112,-0.204,-0.031
-FlowState,TabPFN-TS-3,0.308,0.154,0.5,-0.14,-0.246,-0.037
-FlowState,TiRex,0.519,0.346,0.692,-0.005,-0.034,0.022
-FlowState,TabPFN-TS,0.346,0.154,0.538,-0.074,-0.167,0.011
-FlowState,TimesFM-2.5,0.462,0.288,0.635,0.004,-0.027,0.034
-FlowState,Toto-2.0-22m,0.577,0.385,0.732,-0.006,-0.039,0.027
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,Chronos-Bolt,0.538,0.365,0.712,-0.001,-0.029,0.034
-FlowState,Moirai-2.0,0.462,0.307,0.635,0.019,-0.019,0.062
-FlowState,Toto-1.0,0.577,0.404,0.75,0.033,-0.002,0.073
-FlowState,Sundial-Base,0.596,0.423,0.788,-0.017,-0.106,0.06
-FlowState,Seasonal Naive,0.846,0.692,0.962,0.247,0.177,0.309
-Chronos-Bolt,Chronos-2,0.038,0.0,0.115,-0.164,-0.254,-0.085
-Chronos-Bolt,Toto-2.0-2.5B,0.154,0.038,0.308,-0.036,-0.066,-0.005
-Chronos-Bolt,Toto-2.0-1B,0.154,0.038,0.308,-0.039,-0.071,-0.007
-Chronos-Bolt,Toto-2.0-313m,0.269,0.115,0.424,-0.034,-0.064,-0.004
-Chronos-Bolt,TiRex-2,0.346,0.154,0.538,-0.112,-0.213,-0.032
-Chronos-Bolt,TabPFN-TS-3,0.346,0.191,0.538,-0.14,-0.248,-0.045
-Chronos-Bolt,TiRex,0.442,0.269,0.615,-0.004,-0.034,0.02
-Chronos-Bolt,TabPFN-TS,0.462,0.269,0.654,-0.074,-0.167,-0.002
-Chronos-Bolt,TimesFM-2.5,0.423,0.231,0.596,0.004,-0.025,0.032
-Chronos-Bolt,Toto-2.0-22m,0.462,0.269,0.654,-0.006,-0.037,0.025
-Chronos-Bolt,FlowState,0.462,0.288,0.635,0.001,-0.035,0.028
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,Moirai-2.0,0.577,0.423,0.731,0.02,-0.022,0.064
-Chronos-Bolt,Toto-1.0,0.577,0.404,0.75,0.034,-0.001,0.072
-Chronos-Bolt,Sundial-Base,0.558,0.365,0.731,-0.016,-0.106,0.062
-Chronos-Bolt,Seasonal Naive,0.923,0.808,1.0,0.248,0.188,0.306
-Moirai-2.0,Chronos-2,0.077,0.0,0.192,-0.188,-0.285,-0.101
-Moirai-2.0,Toto-2.0-2.5B,0.154,0.038,0.308,-0.057,-0.091,-0.029
-Moirai-2.0,Toto-2.0-1B,0.154,0.038,0.308,-0.06,-0.091,-0.035
-Moirai-2.0,Toto-2.0-313m,0.231,0.077,0.423,-0.055,-0.087,-0.026
-Moirai-2.0,TiRex-2,0.308,0.154,0.462,-0.134,-0.221,-0.058
-Moirai-2.0,TabPFN-TS-3,0.346,0.192,0.538,-0.163,-0.282,-0.057
-Moirai-2.0,TiRex,0.442,0.269,0.635,-0.024,-0.059,0.003
-Moirai-2.0,TabPFN-TS,0.5,0.308,0.692,-0.095,-0.203,-0.008
-Moirai-2.0,TimesFM-2.5,0.385,0.192,0.558,-0.016,-0.061,0.027
-Moirai-2.0,Toto-2.0-22m,0.462,0.269,0.654,-0.026,-0.055,-0.002
-Moirai-2.0,FlowState,0.538,0.365,0.693,-0.019,-0.066,0.018
-Moirai-2.0,Chronos-Bolt,0.423,0.269,0.577,-0.02,-0.068,0.021
-Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
-Moirai-2.0,Toto-1.0,0.615,0.462,0.788,0.014,-0.01,0.043
-Moirai-2.0,Sundial-Base,0.635,0.462,0.789,-0.036,-0.136,0.048
-Moirai-2.0,Seasonal Naive,0.808,0.654,0.924,0.233,0.167,0.293
-Toto-1.0,Chronos-2,0.154,0.038,0.308,-0.205,-0.31,-0.117
-Toto-1.0,Toto-2.0-2.5B,0.192,0.038,0.346,-0.072,-0.112,-0.041
-Toto-1.0,Toto-2.0-1B,0.192,0.077,0.346,-0.076,-0.114,-0.045
-Toto-1.0,Toto-2.0-313m,0.269,0.115,0.462,-0.07,-0.106,-0.039
-Toto-1.0,TiRex-2,0.308,0.154,0.462,-0.15,-0.25,-0.07
-Toto-1.0,TabPFN-TS-3,0.308,0.154,0.5,-0.179,-0.293,-0.078
-Toto-1.0,TiRex,0.327,0.154,0.5,-0.039,-0.073,-0.011
-Toto-1.0,TabPFN-TS,0.423,0.231,0.615,-0.111,-0.221,-0.022
-Toto-1.0,TimesFM-2.5,0.308,0.154,0.481,-0.03,-0.076,0.006
-Toto-1.0,Toto-2.0-22m,0.269,0.115,0.462,-0.041,-0.077,-0.014
-Toto-1.0,FlowState,0.423,0.25,0.596,-0.034,-0.078,0.002
-Toto-1.0,Chronos-Bolt,0.423,0.25,0.596,-0.035,-0.078,0.001
-Toto-1.0,Moirai-2.0,0.385,0.212,0.538,-0.014,-0.045,0.01
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,Sundial-Base,0.519,0.346,0.692,-0.051,-0.149,0.03
-Toto-1.0,Seasonal Naive,0.885,0.731,1.0,0.222,0.159,0.278
-Sundial-Base,Chronos-2,0.154,0.038,0.308,-0.146,-0.242,-0.074
-Sundial-Base,Toto-2.0-2.5B,0.231,0.077,0.385,-0.02,-0.121,0.066
-Sundial-Base,Toto-2.0-1B,0.269,0.115,0.423,-0.023,-0.124,0.063
-Sundial-Base,Toto-2.0-313m,0.192,0.038,0.346,-0.018,-0.11,0.067
-Sundial-Base,TiRex-2,0.192,0.038,0.346,-0.094,-0.196,-0.006
-Sundial-Base,TabPFN-TS-3,0.231,0.077,0.385,-0.122,-0.227,-0.04
-Sundial-Base,TiRex,0.25,0.096,0.404,0.012,-0.071,0.093
-Sundial-Base,TabPFN-TS,0.5,0.308,0.692,-0.057,-0.166,0.035
-Sundial-Base,TimesFM-2.5,0.404,0.212,0.577,0.02,-0.066,0.101
-Sundial-Base,Toto-2.0-22m,0.346,0.192,0.538,0.01,-0.08,0.095
-Sundial-Base,FlowState,0.404,0.212,0.577,0.016,-0.064,0.096
-Sundial-Base,Chronos-Bolt,0.442,0.269,0.635,0.016,-0.066,0.096
-Sundial-Base,Moirai-2.0,0.365,0.211,0.538,0.035,-0.051,0.119
-Sundial-Base,Toto-1.0,0.481,0.308,0.654,0.049,-0.031,0.129
-Sundial-Base,Sundial-Base,0.5,0.5,0.5,0.0,0.0,0.0
-Sundial-Base,Seasonal Naive,0.885,0.731,1.0,0.26,0.177,0.334
-Seasonal Naive,Chronos-2,0.038,0.0,0.115,-0.548,-0.729,-0.384
-Seasonal Naive,Toto-2.0-2.5B,0.038,0.0,0.115,-0.377,-0.504,-0.267
-Seasonal Naive,Toto-2.0-1B,0.077,0.0,0.192,-0.382,-0.514,-0.266
-Seasonal Naive,Toto-2.0-313m,0.077,0.0,0.192,-0.375,-0.505,-0.259
-Seasonal Naive,TiRex-2,0.038,0.0,0.115,-0.478,-0.652,-0.321
-Seasonal Naive,TabPFN-TS-3,0.038,0.0,0.115,-0.515,-0.695,-0.36
-Seasonal Naive,TiRex,0.077,0.0,0.192,-0.335,-0.445,-0.237
-Seasonal Naive,TabPFN-TS,0.077,0.0,0.192,-0.428,-0.596,-0.276
-Seasonal Naive,TimesFM-2.5,0.077,0.0,0.192,-0.324,-0.441,-0.223
-Seasonal Naive,Toto-2.0-22m,0.115,0.0,0.269,-0.337,-0.46,-0.231
-Seasonal Naive,FlowState,0.154,0.038,0.308,-0.329,-0.447,-0.215
-Seasonal Naive,Chronos-Bolt,0.077,0.0,0.192,-0.33,-0.44,-0.232
-Seasonal Naive,Moirai-2.0,0.192,0.076,0.346,-0.303,-0.415,-0.201
-Seasonal Naive,Toto-1.0,0.115,0.0,0.269,-0.285,-0.386,-0.189
-Seasonal Naive,Sundial-Base,0.115,0.0,0.269,-0.351,-0.501,-0.215
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_energy/pairwise_SQL.csv

@@ -1,257 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,Toto-2.0-1B,0.615,0.423,0.808,0.104,0.037,0.17
-Chronos-2,Toto-2.0-2.5B,0.654,0.462,0.808,0.107,0.041,0.173
-Chronos-2,TiRex-2,0.462,0.269,0.654,0.046,0.003,0.094
-Chronos-2,Toto-2.0-313m,0.615,0.423,0.808,0.111,0.041,0.178
-Chronos-2,TabPFN-TS-3,0.654,0.462,0.846,0.027,-0.009,0.067
-Chronos-2,TiRex,0.731,0.538,0.885,0.141,0.072,0.204
-Chronos-2,Toto-2.0-22m,0.808,0.654,0.923,0.137,0.072,0.202
-Chronos-2,TabPFN-TS,0.808,0.654,0.923,0.082,0.044,0.12
-Chronos-2,TimesFM-2.5,0.769,0.577,0.923,0.159,0.083,0.225
-Chronos-2,FlowState,0.885,0.731,1.0,0.167,0.099,0.227
-Chronos-2,Moirai-2.0,0.923,0.808,1.0,0.178,0.111,0.242
-Chronos-2,Chronos-Bolt,0.923,0.808,1.0,0.161,0.096,0.219
-Chronos-2,Toto-1.0,0.846,0.692,0.962,0.183,0.115,0.249
-Chronos-2,Toto-2.0-4m,0.885,0.768,1.0,0.178,0.104,0.248
-Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.437,0.368,0.497
-Toto-2.0-1B,Chronos-2,0.385,0.192,0.577,-0.116,-0.204,-0.038
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-2.5B,0.538,0.346,0.692,0.004,-0.003,0.012
-Toto-2.0-1B,TiRex-2,0.5,0.308,0.692,-0.064,-0.157,0.009
-Toto-2.0-1B,Toto-2.0-313m,0.577,0.385,0.769,0.008,-0.003,0.02
-Toto-2.0-1B,TabPFN-TS-3,0.462,0.269,0.654,-0.085,-0.194,0.015
-Toto-2.0-1B,TiRex,0.692,0.5,0.846,0.042,0.016,0.07
-Toto-2.0-1B,Toto-2.0-22m,0.885,0.731,1.0,0.038,0.025,0.054
-Toto-2.0-1B,TabPFN-TS,0.654,0.462,0.846,-0.024,-0.12,0.056
-Toto-2.0-1B,TimesFM-2.5,0.808,0.654,0.962,0.062,0.029,0.096
-Toto-2.0-1B,FlowState,0.846,0.692,0.962,0.071,0.039,0.104
-Toto-2.0-1B,Moirai-2.0,0.846,0.692,0.962,0.083,0.055,0.111
-Toto-2.0-1B,Chronos-Bolt,0.846,0.692,0.962,0.064,0.029,0.097
-Toto-2.0-1B,Toto-1.0,0.923,0.808,1.0,0.088,0.059,0.12
-Toto-2.0-1B,Toto-2.0-4m,0.885,0.731,1.0,0.083,0.051,0.117
-Toto-2.0-1B,Seasonal Naive,1.0,1.0,1.0,0.372,0.312,0.433
-Toto-2.0-2.5B,Chronos-2,0.346,0.192,0.538,-0.12,-0.209,-0.043
-Toto-2.0-2.5B,Toto-2.0-1B,0.462,0.308,0.654,-0.004,-0.012,0.003
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,TiRex-2,0.5,0.308,0.692,-0.068,-0.162,0.007
-Toto-2.0-2.5B,Toto-2.0-313m,0.692,0.538,0.846,0.004,-0.008,0.015
-Toto-2.0-2.5B,TabPFN-TS-3,0.423,0.231,0.615,-0.09,-0.198,0.008
-Toto-2.0-2.5B,TiRex,0.731,0.538,0.885,0.038,0.013,0.065
-Toto-2.0-2.5B,Toto-2.0-22m,0.808,0.654,0.962,0.034,0.021,0.048
-Toto-2.0-2.5B,TabPFN-TS,0.654,0.462,0.846,-0.028,-0.125,0.049
-Toto-2.0-2.5B,TimesFM-2.5,0.692,0.5,0.846,0.058,0.025,0.092
-Toto-2.0-2.5B,FlowState,0.846,0.692,0.962,0.067,0.035,0.101
-Toto-2.0-2.5B,Moirai-2.0,0.885,0.768,1.0,0.079,0.051,0.108
-Toto-2.0-2.5B,Chronos-Bolt,0.885,0.768,1.0,0.061,0.028,0.091
-Toto-2.0-2.5B,Toto-1.0,0.885,0.769,1.0,0.085,0.057,0.115
-Toto-2.0-2.5B,Toto-2.0-4m,0.846,0.692,0.962,0.08,0.048,0.112
-Toto-2.0-2.5B,Seasonal Naive,1.0,1.0,1.0,0.369,0.312,0.43
-TiRex-2,Chronos-2,0.538,0.346,0.731,-0.049,-0.104,-0.003
-TiRex-2,Toto-2.0-1B,0.5,0.308,0.692,0.06,-0.009,0.136
-TiRex-2,Toto-2.0-2.5B,0.5,0.308,0.692,0.064,-0.007,0.139
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,Toto-2.0-313m,0.5,0.308,0.692,0.067,-0.004,0.147
-TiRex-2,TabPFN-TS-3,0.577,0.385,0.769,-0.02,-0.087,0.038
-TiRex-2,TiRex,0.692,0.538,0.846,0.099,0.033,0.169
-TiRex-2,Toto-2.0-22m,0.577,0.385,0.769,0.095,0.027,0.165
-TiRex-2,TabPFN-TS,0.654,0.462,0.846,0.038,-0.015,0.087
-TiRex-2,TimesFM-2.5,0.731,0.538,0.885,0.118,0.044,0.193
-TiRex-2,FlowState,0.731,0.577,0.885,0.126,0.058,0.197
-TiRex-2,Moirai-2.0,0.808,0.654,0.923,0.138,0.076,0.204
-TiRex-2,Chronos-Bolt,0.846,0.692,0.962,0.12,0.05,0.194
-TiRex-2,Toto-1.0,0.769,0.615,0.923,0.143,0.077,0.212
-TiRex-2,Toto-2.0-4m,0.885,0.769,1.0,0.138,0.066,0.209
-TiRex-2,Seasonal Naive,1.0,1.0,1.0,0.41,0.334,0.479
-Toto-2.0-313m,Chronos-2,0.385,0.192,0.577,-0.124,-0.216,-0.043
-Toto-2.0-313m,Toto-2.0-1B,0.423,0.231,0.615,-0.008,-0.02,0.003
-Toto-2.0-313m,Toto-2.0-2.5B,0.308,0.154,0.462,-0.004,-0.015,0.008
-Toto-2.0-313m,TiRex-2,0.5,0.308,0.692,-0.072,-0.172,0.004
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,TabPFN-TS-3,0.462,0.269,0.654,-0.094,-0.204,0.006
-Toto-2.0-313m,TiRex,0.654,0.462,0.846,0.034,0.013,0.057
-Toto-2.0-313m,Toto-2.0-22m,0.769,0.614,0.923,0.03,0.017,0.045
-Toto-2.0-313m,TabPFN-TS,0.615,0.423,0.808,-0.032,-0.133,0.048
-Toto-2.0-313m,TimesFM-2.5,0.731,0.538,0.885,0.055,0.025,0.084
-Toto-2.0-313m,FlowState,0.808,0.654,0.962,0.063,0.034,0.094
-Toto-2.0-313m,Moirai-2.0,0.769,0.577,0.923,0.075,0.046,0.105
-Toto-2.0-313m,Chronos-Bolt,0.808,0.654,0.962,0.057,0.023,0.089
-Toto-2.0-313m,Toto-1.0,0.846,0.692,0.962,0.081,0.051,0.111
-Toto-2.0-313m,Toto-2.0-4m,0.846,0.692,0.962,0.076,0.046,0.105
-Toto-2.0-313m,Seasonal Naive,1.0,1.0,1.0,0.367,0.309,0.428
-TabPFN-TS-3,Chronos-2,0.346,0.154,0.538,-0.028,-0.072,0.009
-TabPFN-TS-3,Toto-2.0-1B,0.538,0.346,0.731,0.079,-0.015,0.163
-TabPFN-TS-3,Toto-2.0-2.5B,0.577,0.385,0.769,0.082,-0.008,0.165
-TabPFN-TS-3,TiRex-2,0.423,0.231,0.615,0.02,-0.04,0.08
-TabPFN-TS-3,Toto-2.0-313m,0.538,0.346,0.731,0.086,-0.006,0.169
-TabPFN-TS-3,TabPFN-TS-3,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS-3,TiRex,0.577,0.385,0.769,0.117,0.03,0.195
-TabPFN-TS-3,Toto-2.0-22m,0.615,0.423,0.808,0.113,0.029,0.192
-TabPFN-TS-3,TabPFN-TS,0.769,0.615,0.923,0.057,0.008,0.098
-TabPFN-TS-3,TimesFM-2.5,0.654,0.462,0.809,0.136,0.046,0.217
-TabPFN-TS-3,FlowState,0.731,0.538,0.885,0.144,0.053,0.217
-TabPFN-TS-3,Moirai-2.0,0.692,0.5,0.846,0.155,0.07,0.235
-TabPFN-TS-3,Chronos-Bolt,0.769,0.615,0.923,0.138,0.059,0.21
-TabPFN-TS-3,Toto-1.0,0.731,0.538,0.885,0.16,0.078,0.237
-TabPFN-TS-3,Toto-2.0-4m,0.692,0.5,0.846,0.155,0.067,0.235
-TabPFN-TS-3,Seasonal Naive,1.0,1.0,1.0,0.421,0.35,0.49
-TiRex,Chronos-2,0.269,0.115,0.462,-0.164,-0.257,-0.078
-TiRex,Toto-2.0-1B,0.308,0.154,0.5,-0.044,-0.075,-0.016
-TiRex,Toto-2.0-2.5B,0.269,0.115,0.462,-0.04,-0.069,-0.013
-TiRex,TiRex-2,0.308,0.154,0.462,-0.11,-0.204,-0.034
-TiRex,Toto-2.0-313m,0.346,0.154,0.538,-0.035,-0.061,-0.013
-TiRex,TabPFN-TS-3,0.423,0.231,0.615,-0.133,-0.242,-0.031
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,Toto-2.0-22m,0.538,0.346,0.731,-0.004,-0.029,0.02
-TiRex,TabPFN-TS,0.5,0.308,0.692,-0.068,-0.171,0.014
-TiRex,TimesFM-2.5,0.673,0.481,0.846,0.021,-0.002,0.045
-TiRex,FlowState,0.635,0.461,0.808,0.03,0.003,0.06
-TiRex,Moirai-2.0,0.788,0.615,0.923,0.043,0.014,0.075
-TiRex,Chronos-Bolt,0.75,0.577,0.885,0.023,-0.005,0.052
-TiRex,Toto-1.0,0.788,0.615,0.923,0.048,0.024,0.076
-TiRex,Toto-2.0-4m,0.769,0.614,0.923,0.043,0.012,0.072
-TiRex,Seasonal Naive,1.0,1.0,1.0,0.344,0.286,0.404
-Toto-2.0-22m,Chronos-2,0.192,0.077,0.346,-0.159,-0.254,-0.077
-Toto-2.0-22m,Toto-2.0-1B,0.115,0.0,0.269,-0.039,-0.057,-0.025
-Toto-2.0-22m,Toto-2.0-2.5B,0.192,0.038,0.346,-0.035,-0.05,-0.021
-Toto-2.0-22m,TiRex-2,0.423,0.231,0.615,-0.106,-0.198,-0.028
-Toto-2.0-22m,Toto-2.0-313m,0.231,0.077,0.386,-0.031,-0.047,-0.018
-Toto-2.0-22m,TabPFN-TS-3,0.385,0.192,0.577,-0.128,-0.238,-0.029
-Toto-2.0-22m,TiRex,0.462,0.269,0.654,0.004,-0.02,0.028
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,TabPFN-TS,0.5,0.308,0.692,-0.064,-0.17,0.021
-Toto-2.0-22m,TimesFM-2.5,0.615,0.423,0.808,0.025,-0.009,0.059
-Toto-2.0-22m,FlowState,0.615,0.423,0.808,0.034,-0.001,0.07
-Toto-2.0-22m,Moirai-2.0,0.654,0.462,0.846,0.047,0.018,0.075
-Toto-2.0-22m,Chronos-Bolt,0.692,0.5,0.885,0.027,-0.009,0.062
-Toto-2.0-22m,Toto-1.0,0.769,0.615,0.923,0.052,0.03,0.079
-Toto-2.0-22m,Toto-2.0-4m,0.731,0.577,0.885,0.047,0.022,0.073
-Toto-2.0-22m,Seasonal Naive,1.0,1.0,1.0,0.347,0.288,0.407
-TabPFN-TS,Chronos-2,0.192,0.077,0.346,-0.09,-0.136,-0.046
-TabPFN-TS,Toto-2.0-1B,0.346,0.154,0.538,0.023,-0.059,0.107
-TabPFN-TS,Toto-2.0-2.5B,0.346,0.154,0.538,0.027,-0.051,0.111
-TabPFN-TS,TiRex-2,0.346,0.154,0.538,-0.039,-0.095,0.015
-TabPFN-TS,Toto-2.0-313m,0.385,0.192,0.577,0.031,-0.05,0.117
-TabPFN-TS,TabPFN-TS-3,0.231,0.077,0.385,-0.06,-0.109,-0.008
-TabPFN-TS,TiRex,0.5,0.308,0.692,0.064,-0.014,0.146
-TabPFN-TS,Toto-2.0-22m,0.5,0.308,0.692,0.06,-0.022,0.145
-TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS,TimesFM-2.5,0.5,0.308,0.692,0.084,0.006,0.167
-TabPFN-TS,FlowState,0.615,0.423,0.808,0.092,0.015,0.166
-TabPFN-TS,Moirai-2.0,0.577,0.385,0.769,0.104,0.024,0.189
-TabPFN-TS,Chronos-Bolt,0.654,0.462,0.846,0.086,0.022,0.16
-TabPFN-TS,Toto-1.0,0.577,0.385,0.769,0.109,0.026,0.194
-TabPFN-TS,Toto-2.0-4m,0.615,0.423,0.808,0.105,0.018,0.189
-TabPFN-TS,Seasonal Naive,1.0,1.0,1.0,0.386,0.308,0.462
-TimesFM-2.5,Chronos-2,0.231,0.077,0.423,-0.189,-0.291,-0.09
-TimesFM-2.5,Toto-2.0-1B,0.192,0.038,0.346,-0.066,-0.106,-0.029
-TimesFM-2.5,Toto-2.0-2.5B,0.308,0.154,0.5,-0.062,-0.102,-0.025
-TimesFM-2.5,TiRex-2,0.269,0.115,0.462,-0.134,-0.24,-0.046
-TimesFM-2.5,Toto-2.0-313m,0.269,0.115,0.462,-0.058,-0.092,-0.026
-TimesFM-2.5,TabPFN-TS-3,0.346,0.191,0.538,-0.157,-0.277,-0.048
-TimesFM-2.5,TiRex,0.327,0.154,0.519,-0.021,-0.047,0.002
-TimesFM-2.5,Toto-2.0-22m,0.385,0.192,0.577,-0.026,-0.062,0.009
-TimesFM-2.5,TabPFN-TS,0.5,0.308,0.692,-0.091,-0.2,-0.006
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,FlowState,0.577,0.404,0.75,0.009,-0.023,0.04
-TimesFM-2.5,Moirai-2.0,0.615,0.442,0.808,0.022,-0.023,0.067
-TimesFM-2.5,Chronos-Bolt,0.538,0.365,0.712,0.002,-0.028,0.029
-TimesFM-2.5,Toto-1.0,0.654,0.462,0.808,0.028,-0.012,0.068
-TimesFM-2.5,Toto-2.0-4m,0.615,0.423,0.808,0.023,-0.015,0.057
-TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.33,0.269,0.394
-FlowState,Chronos-2,0.115,0.0,0.269,-0.2,-0.294,-0.11
-FlowState,Toto-2.0-1B,0.154,0.038,0.308,-0.076,-0.116,-0.04
-FlowState,Toto-2.0-2.5B,0.154,0.038,0.308,-0.072,-0.113,-0.036
-FlowState,TiRex-2,0.269,0.115,0.423,-0.145,-0.245,-0.061
-FlowState,Toto-2.0-313m,0.192,0.038,0.346,-0.068,-0.104,-0.035
-FlowState,TabPFN-TS-3,0.269,0.115,0.462,-0.168,-0.277,-0.057
-FlowState,TiRex,0.365,0.192,0.539,-0.031,-0.064,-0.003
-FlowState,Toto-2.0-22m,0.385,0.192,0.577,-0.035,-0.075,0.001
-FlowState,TabPFN-TS,0.385,0.192,0.577,-0.102,-0.199,-0.015
-FlowState,TimesFM-2.5,0.423,0.25,0.596,-0.009,-0.042,0.022
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,Moirai-2.0,0.538,0.384,0.712,0.013,-0.029,0.059
-FlowState,Chronos-Bolt,0.538,0.365,0.712,-0.007,-0.041,0.029
-FlowState,Toto-1.0,0.423,0.269,0.596,0.019,-0.019,0.059
-FlowState,Toto-2.0-4m,0.654,0.462,0.809,0.014,-0.03,0.052
-FlowState,Seasonal Naive,0.962,0.885,1.0,0.324,0.259,0.389
-Moirai-2.0,Chronos-2,0.077,0.0,0.192,-0.216,-0.319,-0.125
-Moirai-2.0,Toto-2.0-1B,0.154,0.038,0.308,-0.09,-0.125,-0.058
-Moirai-2.0,Toto-2.0-2.5B,0.115,0.0,0.232,-0.086,-0.122,-0.054
-Moirai-2.0,TiRex-2,0.192,0.077,0.346,-0.16,-0.257,-0.082
-Moirai-2.0,Toto-2.0-313m,0.231,0.077,0.423,-0.082,-0.117,-0.048
-Moirai-2.0,TabPFN-TS-3,0.308,0.154,0.5,-0.183,-0.308,-0.075
-Moirai-2.0,TiRex,0.212,0.077,0.385,-0.045,-0.081,-0.014
-Moirai-2.0,Toto-2.0-22m,0.346,0.154,0.538,-0.049,-0.081,-0.018
-Moirai-2.0,TabPFN-TS,0.423,0.231,0.615,-0.116,-0.233,-0.025
-Moirai-2.0,TimesFM-2.5,0.385,0.192,0.558,-0.023,-0.071,0.023
-Moirai-2.0,FlowState,0.462,0.288,0.616,-0.013,-0.062,0.029
-Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
-Moirai-2.0,Chronos-Bolt,0.5,0.346,0.673,-0.02,-0.075,0.025
-Moirai-2.0,Toto-1.0,0.577,0.423,0.75,0.006,-0.016,0.034
-Moirai-2.0,Toto-2.0-4m,0.5,0.308,0.692,0.001,-0.036,0.039
-Moirai-2.0,Seasonal Naive,0.923,0.808,1.0,0.315,0.249,0.385
-Chronos-Bolt,Chronos-2,0.077,0.0,0.192,-0.192,-0.28,-0.106
-Chronos-Bolt,Toto-2.0-1B,0.154,0.038,0.308,-0.069,-0.108,-0.029
-Chronos-Bolt,Toto-2.0-2.5B,0.115,0.0,0.232,-0.064,-0.101,-0.028
-Chronos-Bolt,TiRex-2,0.154,0.038,0.308,-0.137,-0.24,-0.053
-Chronos-Bolt,Toto-2.0-313m,0.192,0.038,0.346,-0.06,-0.097,-0.024
-Chronos-Bolt,TabPFN-TS-3,0.231,0.077,0.385,-0.16,-0.266,-0.063
-Chronos-Bolt,TiRex,0.25,0.115,0.423,-0.024,-0.055,0.005
-Chronos-Bolt,Toto-2.0-22m,0.308,0.115,0.5,-0.028,-0.066,0.009
-Chronos-Bolt,TabPFN-TS,0.346,0.154,0.538,-0.094,-0.19,-0.023
-Chronos-Bolt,TimesFM-2.5,0.462,0.288,0.635,-0.002,-0.03,0.027
-Chronos-Bolt,FlowState,0.462,0.288,0.635,0.007,-0.03,0.039
-Chronos-Bolt,Moirai-2.0,0.5,0.327,0.654,0.02,-0.025,0.07
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,Toto-1.0,0.538,0.365,0.712,0.026,-0.013,0.068
-Chronos-Bolt,Toto-2.0-4m,0.5,0.308,0.692,0.021,-0.023,0.063
-Chronos-Bolt,Seasonal Naive,1.0,1.0,1.0,0.329,0.273,0.388
-Toto-1.0,Chronos-2,0.154,0.038,0.308,-0.224,-0.332,-0.13
-Toto-1.0,Toto-2.0-1B,0.077,0.0,0.192,-0.097,-0.136,-0.063
-Toto-1.0,Toto-2.0-2.5B,0.115,0.0,0.231,-0.092,-0.13,-0.06
-Toto-1.0,TiRex-2,0.231,0.077,0.385,-0.167,-0.27,-0.084
-Toto-1.0,Toto-2.0-313m,0.154,0.038,0.308,-0.088,-0.125,-0.054
-Toto-1.0,TabPFN-TS-3,0.269,0.115,0.462,-0.19,-0.311,-0.085
-Toto-1.0,TiRex,0.212,0.077,0.385,-0.051,-0.082,-0.024
-Toto-1.0,Toto-2.0-22m,0.231,0.077,0.385,-0.055,-0.085,-0.031
-Toto-1.0,TabPFN-TS,0.423,0.231,0.615,-0.123,-0.241,-0.027
-Toto-1.0,TimesFM-2.5,0.346,0.192,0.538,-0.029,-0.073,0.011
-Toto-1.0,FlowState,0.577,0.404,0.731,-0.019,-0.063,0.019
-Toto-1.0,Moirai-2.0,0.423,0.25,0.577,-0.006,-0.035,0.016
-Toto-1.0,Chronos-Bolt,0.462,0.288,0.635,-0.026,-0.072,0.013
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,Toto-2.0-4m,0.5,0.308,0.692,-0.005,-0.037,0.02
-Toto-1.0,Seasonal Naive,0.962,0.885,1.0,0.311,0.248,0.377
-Toto-2.0-4m,Chronos-2,0.115,0.0,0.232,-0.217,-0.33,-0.116
-Toto-2.0-4m,Toto-2.0-1B,0.115,0.0,0.269,-0.091,-0.132,-0.054
-Toto-2.0-4m,Toto-2.0-2.5B,0.154,0.038,0.308,-0.087,-0.126,-0.05
-Toto-2.0-4m,TiRex-2,0.115,0.0,0.231,-0.161,-0.264,-0.071
-Toto-2.0-4m,Toto-2.0-313m,0.154,0.038,0.308,-0.082,-0.117,-0.049
-Toto-2.0-4m,TabPFN-TS-3,0.308,0.154,0.5,-0.184,-0.307,-0.072
-Toto-2.0-4m,TiRex,0.231,0.077,0.386,-0.045,-0.078,-0.012
-Toto-2.0-4m,Toto-2.0-22m,0.269,0.115,0.423,-0.05,-0.079,-0.023
-Toto-2.0-4m,TabPFN-TS,0.385,0.192,0.577,-0.117,-0.234,-0.018
-Toto-2.0-4m,TimesFM-2.5,0.385,0.192,0.577,-0.023,-0.061,0.015
-Toto-2.0-4m,FlowState,0.346,0.191,0.538,-0.014,-0.054,0.029
-Toto-2.0-4m,Moirai-2.0,0.5,0.308,0.692,-0.001,-0.041,0.035
-Toto-2.0-4m,Chronos-Bolt,0.5,0.308,0.692,-0.021,-0.067,0.023
-Toto-2.0-4m,Toto-1.0,0.5,0.308,0.692,0.005,-0.02,0.036
-Toto-2.0-4m,Toto-2.0-4m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-4m,Seasonal Naive,1.0,1.0,1.0,0.315,0.256,0.378
-Seasonal Naive,Chronos-2,0.0,0.0,0.0,-0.776,-0.987,-0.581
-Seasonal Naive,Toto-2.0-1B,0.0,0.0,0.0,-0.592,-0.765,-0.454
-Seasonal Naive,Toto-2.0-2.5B,0.0,0.0,0.0,-0.586,-0.754,-0.453
-Seasonal Naive,TiRex-2,0.0,0.0,0.0,-0.694,-0.92,-0.5
-Seasonal Naive,Toto-2.0-313m,0.0,0.0,0.0,-0.58,-0.749,-0.446
-Seasonal Naive,TabPFN-TS-3,0.0,0.0,0.0,-0.728,-0.962,-0.539
-Seasonal Naive,TiRex,0.0,0.0,0.0,-0.526,-0.679,-0.401
-Seasonal Naive,Toto-2.0-22m,0.0,0.0,0.0,-0.532,-0.686,-0.404
-Seasonal Naive,TabPFN-TS,0.0,0.0,0.0,-0.63,-0.858,-0.445
-Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-0.493,-0.65,-0.368
-Seasonal Naive,FlowState,0.038,0.0,0.115,-0.48,-0.638,-0.35
-Seasonal Naive,Moirai-2.0,0.077,0.0,0.192,-0.46,-0.627,-0.331
-Seasonal Naive,Chronos-Bolt,0.0,0.0,0.0,-0.49,-0.633,-0.376
-Seasonal Naive,Toto-1.0,0.038,0.0,0.115,-0.452,-0.604,-0.33
-Seasonal Naive,Toto-2.0-4m,0.0,0.0,0.0,-0.459,-0.608,-0.344
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_energy/pairwise_WAPE.csv

@@ -1,257 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,Toto-2.0-313m,0.615,0.423,0.808,0.099,0.028,0.168
-Chronos-2,Toto-2.0-1B,0.615,0.423,0.808,0.095,0.019,0.17
-Chronos-2,Toto-2.0-2.5B,0.615,0.423,0.808,0.104,0.03,0.173
-Chronos-2,TiRex-2,0.615,0.423,0.808,0.048,0.002,0.096
-Chronos-2,TabPFN-TS-3,0.731,0.538,0.885,0.045,-0.012,0.099
-Chronos-2,Toto-2.0-22m,0.692,0.5,0.846,0.122,0.054,0.188
-Chronos-2,TabPFN-TS,0.808,0.654,0.923,0.103,0.035,0.178
-Chronos-2,TiRex,0.846,0.692,0.962,0.141,0.074,0.204
-Chronos-2,TimesFM-2.5,0.731,0.538,0.885,0.149,0.075,0.214
-Chronos-2,Moirai-2.0,0.885,0.731,1.0,0.156,0.089,0.221
-Chronos-2,Chronos-Bolt,0.923,0.808,1.0,0.149,0.081,0.219
-Chronos-2,FlowState,0.808,0.654,0.923,0.146,0.079,0.202
-Chronos-2,Sundial-Base,0.846,0.692,0.962,0.13,0.071,0.194
-Chronos-2,Toto-1.0,0.885,0.769,1.0,0.176,0.109,0.244
-Chronos-2,Seasonal Naive,0.923,0.808,1.0,0.376,0.282,0.449
-Toto-2.0-313m,Chronos-2,0.385,0.192,0.577,-0.11,-0.202,-0.029
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,Toto-2.0-1B,0.538,0.346,0.731,-0.005,-0.026,0.012
-Toto-2.0-313m,Toto-2.0-2.5B,0.423,0.231,0.615,0.006,-0.007,0.018
-Toto-2.0-313m,TiRex-2,0.538,0.346,0.731,-0.057,-0.158,0.028
-Toto-2.0-313m,TabPFN-TS-3,0.577,0.385,0.769,-0.06,-0.174,0.05
-Toto-2.0-313m,Toto-2.0-22m,0.731,0.538,0.885,0.026,0.005,0.044
-Toto-2.0-313m,TabPFN-TS,0.692,0.5,0.846,0.005,-0.109,0.1
-Toto-2.0-313m,TiRex,0.654,0.462,0.846,0.047,0.019,0.079
-Toto-2.0-313m,TimesFM-2.5,0.769,0.615,0.923,0.055,0.019,0.099
-Toto-2.0-313m,Moirai-2.0,0.769,0.577,0.923,0.064,0.026,0.103
-Toto-2.0-313m,Chronos-Bolt,0.846,0.692,0.962,0.056,0.014,0.105
-Toto-2.0-313m,FlowState,0.808,0.654,0.962,0.052,0.012,0.09
-Toto-2.0-313m,Sundial-Base,0.769,0.615,0.923,0.034,-0.073,0.132
-Toto-2.0-313m,Toto-1.0,0.846,0.692,0.962,0.086,0.056,0.12
-Toto-2.0-313m,Seasonal Naive,0.923,0.808,1.0,0.307,0.221,0.386
-Toto-2.0-1B,Chronos-2,0.385,0.192,0.577,-0.104,-0.204,-0.02
-Toto-2.0-1B,Toto-2.0-313m,0.462,0.269,0.654,0.005,-0.012,0.025
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-2.5B,0.5,0.308,0.692,0.01,-0.003,0.026
-Toto-2.0-1B,TiRex-2,0.577,0.385,0.769,-0.052,-0.153,0.034
-Toto-2.0-1B,TabPFN-TS-3,0.462,0.269,0.654,-0.055,-0.17,0.057
-Toto-2.0-1B,Toto-2.0-22m,0.769,0.577,0.923,0.03,0.006,0.053
-Toto-2.0-1B,TabPFN-TS,0.577,0.385,0.769,0.01,-0.1,0.109
-Toto-2.0-1B,TiRex,0.769,0.615,0.923,0.051,0.016,0.094
-Toto-2.0-1B,TimesFM-2.5,0.808,0.654,0.962,0.06,0.02,0.109
-Toto-2.0-1B,Moirai-2.0,0.769,0.577,0.923,0.068,0.029,0.113
-Toto-2.0-1B,Chronos-Bolt,0.808,0.654,0.962,0.06,0.011,0.118
-Toto-2.0-1B,FlowState,0.769,0.615,0.923,0.057,0.015,0.097
-Toto-2.0-1B,Sundial-Base,0.808,0.654,0.962,0.039,-0.069,0.14
-Toto-2.0-1B,Toto-1.0,0.808,0.654,0.962,0.09,0.054,0.13
-Toto-2.0-1B,Seasonal Naive,0.962,0.885,1.0,0.31,0.223,0.392
-Toto-2.0-2.5B,Chronos-2,0.385,0.192,0.577,-0.116,-0.209,-0.031
-Toto-2.0-2.5B,Toto-2.0-313m,0.577,0.385,0.769,-0.006,-0.018,0.007
-Toto-2.0-2.5B,Toto-2.0-1B,0.5,0.308,0.692,-0.011,-0.027,0.003
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,TiRex-2,0.577,0.385,0.769,-0.063,-0.16,0.02
-Toto-2.0-2.5B,TabPFN-TS-3,0.5,0.346,0.692,-0.066,-0.174,0.041
-Toto-2.0-2.5B,Toto-2.0-22m,0.731,0.538,0.885,0.02,0.002,0.037
-Toto-2.0-2.5B,TabPFN-TS,0.615,0.423,0.808,-0.001,-0.108,0.094
-Toto-2.0-2.5B,TiRex,0.692,0.5,0.885,0.041,0.011,0.077
-Toto-2.0-2.5B,TimesFM-2.5,0.692,0.5,0.885,0.05,0.012,0.097
-Toto-2.0-2.5B,Moirai-2.0,0.731,0.538,0.885,0.058,0.019,0.099
-Toto-2.0-2.5B,Chronos-Bolt,0.808,0.654,0.962,0.05,0.005,0.099
-Toto-2.0-2.5B,FlowState,0.769,0.615,0.923,0.047,0.006,0.086
-Toto-2.0-2.5B,Sundial-Base,0.731,0.577,0.885,0.028,-0.075,0.128
-Toto-2.0-2.5B,Toto-1.0,0.769,0.577,0.923,0.08,0.048,0.119
-Toto-2.0-2.5B,Seasonal Naive,0.923,0.808,1.0,0.303,0.219,0.384
-TiRex-2,Chronos-2,0.385,0.192,0.577,-0.05,-0.106,-0.002
-TiRex-2,Toto-2.0-313m,0.462,0.269,0.654,0.054,-0.029,0.137
-TiRex-2,Toto-2.0-1B,0.423,0.231,0.615,0.049,-0.035,0.133
-TiRex-2,Toto-2.0-2.5B,0.423,0.231,0.615,0.059,-0.02,0.138
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,TabPFN-TS-3,0.538,0.346,0.731,-0.003,-0.078,0.069
-TiRex-2,Toto-2.0-22m,0.538,0.346,0.731,0.078,0.004,0.154
-TiRex-2,TabPFN-TS,0.692,0.5,0.846,0.058,-0.019,0.139
-TiRex-2,TiRex,0.577,0.385,0.769,0.098,0.027,0.167
-TiRex-2,TimesFM-2.5,0.615,0.423,0.769,0.106,0.033,0.182
-TiRex-2,Moirai-2.0,0.731,0.538,0.885,0.114,0.041,0.183
-TiRex-2,Chronos-Bolt,0.654,0.462,0.846,0.107,0.025,0.193
-TiRex-2,FlowState,0.731,0.538,0.885,0.103,0.027,0.175
-TiRex-2,Sundial-Base,0.769,0.615,0.923,0.086,0.001,0.169
-TiRex-2,Toto-1.0,0.577,0.385,0.769,0.135,0.059,0.211
-TiRex-2,Seasonal Naive,0.962,0.885,1.0,0.344,0.247,0.425
-TabPFN-TS-3,Chronos-2,0.269,0.115,0.462,-0.047,-0.11,0.012
-TabPFN-TS-3,Toto-2.0-313m,0.423,0.231,0.615,0.056,-0.053,0.148
-TabPFN-TS-3,Toto-2.0-1B,0.538,0.346,0.731,0.052,-0.061,0.145
-TabPFN-TS-3,Toto-2.0-2.5B,0.5,0.308,0.654,0.062,-0.043,0.148
-TabPFN-TS-3,TiRex-2,0.462,0.269,0.654,0.003,-0.074,0.072
-TabPFN-TS-3,TabPFN-TS-3,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS-3,Toto-2.0-22m,0.577,0.385,0.769,0.081,-0.016,0.164
-TabPFN-TS-3,TabPFN-TS,0.692,0.5,0.846,0.061,-0.003,0.119
-TabPFN-TS-3,TiRex,0.538,0.346,0.731,0.1,0.002,0.189
-TabPFN-TS-3,TimesFM-2.5,0.577,0.385,0.769,0.109,0.018,0.192
-TabPFN-TS-3,Moirai-2.0,0.654,0.462,0.809,0.116,0.015,0.206
-TabPFN-TS-3,Chronos-Bolt,0.654,0.462,0.846,0.109,0.021,0.191
-TabPFN-TS-3,FlowState,0.654,0.462,0.846,0.106,0.011,0.188
-TabPFN-TS-3,Sundial-Base,0.654,0.462,0.846,0.089,0.008,0.164
-TabPFN-TS-3,Toto-1.0,0.654,0.462,0.808,0.137,0.046,0.221
-TabPFN-TS-3,Seasonal Naive,0.962,0.885,1.0,0.346,0.261,0.422
-Toto-2.0-22m,Chronos-2,0.308,0.154,0.5,-0.139,-0.232,-0.057
-Toto-2.0-22m,Toto-2.0-313m,0.269,0.115,0.462,-0.027,-0.046,-0.005
-Toto-2.0-22m,Toto-2.0-1B,0.231,0.077,0.423,-0.031,-0.055,-0.006
-Toto-2.0-22m,Toto-2.0-2.5B,0.269,0.115,0.462,-0.021,-0.039,-0.002
-Toto-2.0-22m,TiRex-2,0.462,0.269,0.654,-0.085,-0.181,-0.004
-Toto-2.0-22m,TabPFN-TS-3,0.423,0.231,0.615,-0.088,-0.197,0.015
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,TabPFN-TS,0.5,0.308,0.692,-0.022,-0.126,0.071
-Toto-2.0-22m,TiRex,0.5,0.308,0.692,0.021,-0.012,0.058
-Toto-2.0-22m,TimesFM-2.5,0.5,0.308,0.692,0.03,-0.011,0.078
-Toto-2.0-22m,Moirai-2.0,0.577,0.385,0.769,0.039,-0.002,0.079
-Toto-2.0-22m,Chronos-Bolt,0.692,0.5,0.846,0.031,-0.011,0.077
-Toto-2.0-22m,FlowState,0.654,0.5,0.808,0.027,-0.018,0.066
-Toto-2.0-22m,Sundial-Base,0.615,0.423,0.808,0.008,-0.099,0.104
-Toto-2.0-22m,Toto-1.0,0.692,0.5,0.846,0.061,0.032,0.094
-Toto-2.0-22m,Seasonal Naive,0.962,0.885,1.0,0.289,0.209,0.365
-TabPFN-TS,Chronos-2,0.192,0.077,0.346,-0.115,-0.216,-0.036
-TabPFN-TS,Toto-2.0-313m,0.308,0.154,0.5,-0.005,-0.112,0.098
-TabPFN-TS,Toto-2.0-1B,0.423,0.231,0.615,-0.01,-0.123,0.091
-TabPFN-TS,Toto-2.0-2.5B,0.385,0.192,0.577,0.001,-0.103,0.098
-TabPFN-TS,TiRex-2,0.308,0.154,0.5,-0.062,-0.161,0.018
-TabPFN-TS,TabPFN-TS-3,0.308,0.154,0.5,-0.065,-0.135,0.003
-TabPFN-TS,Toto-2.0-22m,0.5,0.308,0.692,0.021,-0.076,0.112
-TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS,TiRex,0.462,0.269,0.654,0.042,-0.07,0.138
-TabPFN-TS,TimesFM-2.5,0.538,0.346,0.731,0.051,-0.047,0.137
-TabPFN-TS,Moirai-2.0,0.538,0.346,0.731,0.059,-0.056,0.163
-TabPFN-TS,Chronos-Bolt,0.538,0.346,0.731,0.051,-0.035,0.132
-TabPFN-TS,FlowState,0.577,0.385,0.769,0.047,-0.06,0.132
-TabPFN-TS,Sundial-Base,0.615,0.423,0.808,0.029,-0.086,0.132
-TabPFN-TS,Toto-1.0,0.577,0.385,0.769,0.081,-0.022,0.177
-TabPFN-TS,Seasonal Naive,0.962,0.885,1.0,0.304,0.213,0.381
-TiRex,Chronos-2,0.154,0.038,0.308,-0.164,-0.256,-0.08
-TiRex,Toto-2.0-313m,0.346,0.154,0.538,-0.049,-0.085,-0.019
-TiRex,Toto-2.0-1B,0.231,0.077,0.385,-0.054,-0.104,-0.017
-TiRex,Toto-2.0-2.5B,0.308,0.115,0.5,-0.043,-0.084,-0.011
-TiRex,TiRex-2,0.423,0.231,0.615,-0.108,-0.201,-0.027
-TiRex,TabPFN-TS-3,0.462,0.269,0.654,-0.112,-0.233,-0.002
-TiRex,Toto-2.0-22m,0.5,0.308,0.692,-0.022,-0.061,0.012
-TiRex,TabPFN-TS,0.538,0.346,0.731,-0.044,-0.161,0.065
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,TimesFM-2.5,0.558,0.365,0.75,0.009,-0.023,0.041
-TiRex,Moirai-2.0,0.442,0.269,0.615,0.018,-0.013,0.051
-TiRex,Chronos-Bolt,0.481,0.308,0.673,0.01,-0.028,0.06
-TiRex,FlowState,0.519,0.346,0.692,0.006,-0.029,0.041
-TiRex,Sundial-Base,0.635,0.462,0.808,-0.013,-0.12,0.076
-TiRex,Toto-1.0,0.712,0.538,0.885,0.041,0.009,0.076
-TiRex,Seasonal Naive,0.885,0.731,1.0,0.273,0.184,0.352
-TimesFM-2.5,Chronos-2,0.269,0.115,0.462,-0.175,-0.273,-0.081
-TimesFM-2.5,Toto-2.0-313m,0.231,0.077,0.385,-0.058,-0.11,-0.019
-TimesFM-2.5,Toto-2.0-1B,0.192,0.038,0.346,-0.063,-0.122,-0.021
-TimesFM-2.5,Toto-2.0-2.5B,0.308,0.115,0.5,-0.052,-0.107,-0.012
-TimesFM-2.5,TiRex-2,0.385,0.231,0.577,-0.119,-0.222,-0.034
-TimesFM-2.5,TabPFN-TS-3,0.423,0.231,0.615,-0.122,-0.238,-0.019
-TimesFM-2.5,Toto-2.0-22m,0.5,0.308,0.692,-0.031,-0.085,0.011
-TimesFM-2.5,TabPFN-TS,0.462,0.269,0.654,-0.053,-0.159,0.045
-TimesFM-2.5,TiRex,0.442,0.25,0.635,-0.009,-0.043,0.023
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,Moirai-2.0,0.577,0.404,0.75,0.009,-0.046,0.062
-TimesFM-2.5,Chronos-Bolt,0.5,0.327,0.674,0.001,-0.039,0.042
-TimesFM-2.5,FlowState,0.538,0.365,0.712,-0.003,-0.048,0.038
-TimesFM-2.5,Sundial-Base,0.596,0.423,0.788,-0.022,-0.12,0.067
-TimesFM-2.5,Toto-1.0,0.654,0.481,0.808,0.032,-0.012,0.081
-TimesFM-2.5,Seasonal Naive,0.923,0.808,1.0,0.267,0.184,0.338
-Moirai-2.0,Chronos-2,0.115,0.0,0.269,-0.185,-0.284,-0.098
-Moirai-2.0,Toto-2.0-313m,0.231,0.077,0.423,-0.068,-0.114,-0.027
-Moirai-2.0,Toto-2.0-1B,0.231,0.077,0.423,-0.073,-0.128,-0.029
-Moirai-2.0,Toto-2.0-2.5B,0.269,0.115,0.462,-0.062,-0.11,-0.02
-Moirai-2.0,TiRex-2,0.269,0.115,0.462,-0.129,-0.223,-0.043
-Moirai-2.0,TabPFN-TS-3,0.346,0.191,0.538,-0.132,-0.26,-0.016
-Moirai-2.0,Toto-2.0-22m,0.423,0.231,0.615,-0.04,-0.086,0.002
-Moirai-2.0,TabPFN-TS,0.462,0.269,0.654,-0.063,-0.195,0.053
-Moirai-2.0,TiRex,0.558,0.385,0.731,-0.018,-0.054,0.013
-Moirai-2.0,TimesFM-2.5,0.423,0.25,0.596,-0.009,-0.067,0.044
-Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
-Moirai-2.0,Chronos-Bolt,0.423,0.269,0.596,-0.008,-0.073,0.062
-Moirai-2.0,FlowState,0.538,0.365,0.712,-0.012,-0.065,0.03
-Moirai-2.0,Sundial-Base,0.596,0.423,0.769,-0.032,-0.143,0.065
-Moirai-2.0,Toto-1.0,0.577,0.404,0.75,0.024,-0.008,0.056
-Moirai-2.0,Seasonal Naive,0.808,0.654,0.924,0.26,0.164,0.341
-Chronos-Bolt,Chronos-2,0.077,0.0,0.192,-0.175,-0.28,-0.089
-Chronos-Bolt,Toto-2.0-313m,0.154,0.038,0.308,-0.059,-0.118,-0.014
-Chronos-Bolt,Toto-2.0-1B,0.192,0.038,0.346,-0.064,-0.133,-0.011
-Chronos-Bolt,Toto-2.0-2.5B,0.192,0.038,0.346,-0.053,-0.109,-0.005
-Chronos-Bolt,TiRex-2,0.346,0.154,0.538,-0.119,-0.24,-0.026
-Chronos-Bolt,TabPFN-TS-3,0.346,0.154,0.538,-0.123,-0.236,-0.021
-Chronos-Bolt,Toto-2.0-22m,0.308,0.154,0.5,-0.032,-0.083,0.011
-Chronos-Bolt,TabPFN-TS,0.462,0.269,0.654,-0.054,-0.152,0.034
-Chronos-Bolt,TiRex,0.519,0.327,0.692,-0.01,-0.064,0.027
-Chronos-Bolt,TimesFM-2.5,0.5,0.326,0.673,-0.001,-0.044,0.038
-Chronos-Bolt,Moirai-2.0,0.577,0.404,0.731,0.008,-0.066,0.068
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,FlowState,0.5,0.327,0.673,-0.004,-0.072,0.041
-Chronos-Bolt,Sundial-Base,0.519,0.327,0.692,-0.023,-0.128,0.067
-Chronos-Bolt,Toto-1.0,0.615,0.442,0.788,0.032,-0.022,0.08
-Chronos-Bolt,Seasonal Naive,0.923,0.808,1.0,0.266,0.183,0.339
-FlowState,Chronos-2,0.192,0.077,0.346,-0.171,-0.253,-0.086
-FlowState,Toto-2.0-313m,0.192,0.038,0.346,-0.055,-0.098,-0.012
-FlowState,Toto-2.0-1B,0.231,0.077,0.385,-0.06,-0.108,-0.016
-FlowState,Toto-2.0-2.5B,0.231,0.077,0.385,-0.049,-0.094,-0.006
-FlowState,TiRex-2,0.269,0.115,0.462,-0.115,-0.212,-0.027
-FlowState,TabPFN-TS-3,0.346,0.154,0.538,-0.118,-0.231,-0.011
-FlowState,Toto-2.0-22m,0.346,0.192,0.5,-0.028,-0.07,0.018
-FlowState,TabPFN-TS,0.423,0.231,0.615,-0.05,-0.152,0.056
-FlowState,TiRex,0.481,0.308,0.654,-0.006,-0.043,0.028
-FlowState,TimesFM-2.5,0.462,0.288,0.635,0.003,-0.04,0.046
-FlowState,Moirai-2.0,0.462,0.288,0.635,0.012,-0.031,0.061
-FlowState,Chronos-Bolt,0.5,0.327,0.673,0.004,-0.043,0.067
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,Sundial-Base,0.558,0.385,0.75,-0.019,-0.118,0.069
-FlowState,Toto-1.0,0.5,0.327,0.692,0.035,-0.006,0.084
-FlowState,Seasonal Naive,0.769,0.577,0.923,0.269,0.178,0.347
-Sundial-Base,Chronos-2,0.154,0.038,0.308,-0.149,-0.241,-0.077
-Sundial-Base,Toto-2.0-313m,0.231,0.077,0.385,-0.035,-0.153,0.068
-Sundial-Base,Toto-2.0-1B,0.192,0.038,0.346,-0.04,-0.162,0.064
-Sundial-Base,Toto-2.0-2.5B,0.269,0.115,0.423,-0.029,-0.146,0.07
-Sundial-Base,TiRex-2,0.231,0.077,0.385,-0.094,-0.203,-0.001
-Sundial-Base,TabPFN-TS-3,0.346,0.154,0.538,-0.097,-0.196,-0.008
-Sundial-Base,Toto-2.0-22m,0.385,0.192,0.577,-0.008,-0.116,0.09
-Sundial-Base,TabPFN-TS,0.385,0.192,0.577,-0.03,-0.153,0.08
-Sundial-Base,TiRex,0.365,0.192,0.538,0.013,-0.083,0.107
-Sundial-Base,TimesFM-2.5,0.404,0.212,0.577,0.022,-0.072,0.107
-Sundial-Base,Moirai-2.0,0.404,0.231,0.577,0.031,-0.069,0.125
-Sundial-Base,Chronos-Bolt,0.481,0.308,0.673,0.023,-0.072,0.113
-Sundial-Base,FlowState,0.442,0.25,0.615,0.019,-0.074,0.106
-Sundial-Base,Sundial-Base,0.5,0.5,0.5,0.0,0.0,0.0
-Sundial-Base,Toto-1.0,0.519,0.327,0.712,0.054,-0.039,0.14
-Sundial-Base,Seasonal Naive,0.846,0.692,0.962,0.283,0.183,0.364
-Toto-1.0,Chronos-2,0.115,0.0,0.231,-0.214,-0.323,-0.123
-Toto-1.0,Toto-2.0-313m,0.154,0.038,0.308,-0.094,-0.136,-0.059
-Toto-1.0,Toto-2.0-1B,0.192,0.038,0.346,-0.099,-0.15,-0.058
-Toto-1.0,Toto-2.0-2.5B,0.231,0.077,0.423,-0.088,-0.135,-0.051
-Toto-1.0,TiRex-2,0.423,0.231,0.615,-0.156,-0.268,-0.062
-Toto-1.0,TabPFN-TS-3,0.346,0.192,0.538,-0.159,-0.284,-0.048
-Toto-1.0,Toto-2.0-22m,0.308,0.154,0.5,-0.065,-0.104,-0.033
-Toto-1.0,TabPFN-TS,0.423,0.231,0.615,-0.088,-0.215,0.022
-Toto-1.0,TiRex,0.288,0.115,0.462,-0.043,-0.083,-0.009
-Toto-1.0,TimesFM-2.5,0.346,0.192,0.519,-0.033,-0.088,0.012
-Toto-1.0,Moirai-2.0,0.423,0.25,0.596,-0.024,-0.06,0.008
-Toto-1.0,Chronos-Bolt,0.385,0.212,0.558,-0.033,-0.087,0.021
-Toto-1.0,FlowState,0.5,0.308,0.673,-0.037,-0.092,0.006
-Toto-1.0,Sundial-Base,0.481,0.288,0.673,-0.057,-0.163,0.038
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,Seasonal Naive,0.846,0.654,0.962,0.242,0.151,0.321
-Seasonal Naive,Chronos-2,0.077,0.0,0.192,-0.601,-0.814,-0.393
-Seasonal Naive,Toto-2.0-313m,0.077,0.0,0.192,-0.443,-0.63,-0.284
-Seasonal Naive,Toto-2.0-1B,0.038,0.0,0.115,-0.45,-0.645,-0.288
-Seasonal Naive,Toto-2.0-2.5B,0.077,0.0,0.192,-0.435,-0.623,-0.28
-Seasonal Naive,TiRex-2,0.038,0.0,0.115,-0.525,-0.739,-0.328
-Seasonal Naive,TabPFN-TS-3,0.038,0.0,0.115,-0.529,-0.73,-0.353
-Seasonal Naive,Toto-2.0-22m,0.038,0.0,0.115,-0.406,-0.574,-0.264
-Seasonal Naive,TabPFN-TS,0.038,0.0,0.115,-0.436,-0.616,-0.27
-Seasonal Naive,TiRex,0.115,0.0,0.269,-0.376,-0.544,-0.225
-Seasonal Naive,TimesFM-2.5,0.077,0.0,0.192,-0.363,-0.511,-0.225
-Seasonal Naive,Moirai-2.0,0.192,0.076,0.346,-0.351,-0.517,-0.196
-Seasonal Naive,Chronos-Bolt,0.077,0.0,0.192,-0.363,-0.513,-0.225
-Seasonal Naive,FlowState,0.231,0.077,0.423,-0.368,-0.532,-0.217
-Seasonal Naive,Sundial-Base,0.154,0.038,0.308,-0.394,-0.572,-0.225
-Seasonal Naive,Toto-1.0,0.154,0.038,0.346,-0.319,-0.473,-0.178
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_energy/pairwise_WQL.csv

@@ -1,257 +0,0 @@
-model_1,model_2,win_rate,win_rate_lower,win_rate_upper,skill_score,skill_score_lower,skill_score_upper
-Chronos-2,Chronos-2,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-2,Toto-2.0-1B,0.5,0.308,0.692,0.085,0.012,0.16
-Chronos-2,Toto-2.0-2.5B,0.577,0.385,0.769,0.096,0.024,0.164
-Chronos-2,Toto-2.0-313m,0.538,0.346,0.731,0.093,0.022,0.164
-Chronos-2,TiRex-2,0.577,0.385,0.769,0.045,-0.001,0.094
-Chronos-2,TabPFN-TS-3,0.692,0.5,0.846,0.051,-0.003,0.106
-Chronos-2,Toto-2.0-22m,0.692,0.5,0.846,0.122,0.052,0.188
-Chronos-2,TiRex,0.808,0.654,0.962,0.143,0.076,0.204
-Chronos-2,TabPFN-TS,0.846,0.692,0.962,0.105,0.046,0.172
-Chronos-2,TimesFM-2.5,0.808,0.654,0.962,0.159,0.086,0.224
-Chronos-2,FlowState,0.846,0.692,0.962,0.166,0.098,0.224
-Chronos-2,Chronos-Bolt,0.962,0.885,1.0,0.165,0.099,0.23
-Chronos-2,Moirai-2.0,0.923,0.808,1.0,0.175,0.108,0.243
-Chronos-2,Toto-1.0,0.885,0.769,1.0,0.186,0.119,0.252
-Chronos-2,Toto-2.0-4m,0.962,0.885,1.0,0.183,0.114,0.247
-Chronos-2,Seasonal Naive,1.0,1.0,1.0,0.46,0.384,0.522
-Toto-2.0-1B,Chronos-2,0.5,0.308,0.692,-0.093,-0.19,-0.012
-Toto-2.0-1B,Toto-2.0-1B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-1B,Toto-2.0-2.5B,0.654,0.462,0.808,0.012,-0.002,0.029
-Toto-2.0-1B,Toto-2.0-313m,0.5,0.308,0.692,0.009,-0.011,0.036
-Toto-2.0-1B,TiRex-2,0.577,0.385,0.769,-0.044,-0.148,0.041
-Toto-2.0-1B,TabPFN-TS-3,0.5,0.308,0.692,-0.038,-0.155,0.074
-Toto-2.0-1B,Toto-2.0-22m,0.885,0.731,1.0,0.04,0.019,0.065
-Toto-2.0-1B,TiRex,0.731,0.577,0.885,0.063,0.022,0.115
-Toto-2.0-1B,TabPFN-TS,0.654,0.462,0.808,0.022,-0.085,0.112
-Toto-2.0-1B,TimesFM-2.5,0.846,0.692,0.962,0.081,0.037,0.131
-Toto-2.0-1B,FlowState,0.808,0.654,0.962,0.088,0.047,0.131
-Toto-2.0-1B,Chronos-Bolt,0.923,0.808,1.0,0.087,0.036,0.138
-Toto-2.0-1B,Moirai-2.0,0.846,0.692,0.962,0.098,0.054,0.147
-Toto-2.0-1B,Toto-1.0,0.962,0.885,1.0,0.11,0.074,0.153
-Toto-2.0-1B,Toto-2.0-4m,0.962,0.885,1.0,0.107,0.065,0.155
-Toto-2.0-1B,Seasonal Naive,1.0,1.0,1.0,0.41,0.333,0.481
-Toto-2.0-2.5B,Chronos-2,0.423,0.231,0.615,-0.106,-0.196,-0.025
-Toto-2.0-2.5B,Toto-2.0-1B,0.346,0.192,0.538,-0.012,-0.03,0.002
-Toto-2.0-2.5B,Toto-2.0-2.5B,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-2.5B,Toto-2.0-313m,0.615,0.423,0.769,-0.003,-0.018,0.012
-Toto-2.0-2.5B,TiRex-2,0.538,0.346,0.731,-0.056,-0.158,0.027
-Toto-2.0-2.5B,TabPFN-TS-3,0.5,0.308,0.692,-0.05,-0.161,0.059
-Toto-2.0-2.5B,Toto-2.0-22m,0.769,0.615,0.923,0.028,0.011,0.045
-Toto-2.0-2.5B,TiRex,0.769,0.615,0.923,0.051,0.016,0.092
-Toto-2.0-2.5B,TabPFN-TS,0.692,0.538,0.846,0.01,-0.093,0.098
-Toto-2.0-2.5B,TimesFM-2.5,0.769,0.615,0.923,0.07,0.031,0.118
-Toto-2.0-2.5B,FlowState,0.846,0.692,0.962,0.077,0.036,0.12
-Toto-2.0-2.5B,Chronos-Bolt,0.846,0.692,0.962,0.076,0.031,0.122
-Toto-2.0-2.5B,Moirai-2.0,0.808,0.654,0.923,0.087,0.046,0.133
-Toto-2.0-2.5B,Toto-1.0,0.923,0.808,1.0,0.099,0.067,0.137
-Toto-2.0-2.5B,Toto-2.0-4m,0.846,0.692,0.962,0.096,0.057,0.137
-Toto-2.0-2.5B,Seasonal Naive,1.0,1.0,1.0,0.403,0.329,0.473
-Toto-2.0-313m,Chronos-2,0.462,0.269,0.654,-0.103,-0.196,-0.022
-Toto-2.0-313m,Toto-2.0-1B,0.5,0.308,0.692,-0.009,-0.037,0.011
-Toto-2.0-313m,Toto-2.0-2.5B,0.385,0.231,0.577,0.003,-0.012,0.018
-Toto-2.0-313m,Toto-2.0-313m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-313m,TiRex-2,0.538,0.346,0.731,-0.053,-0.156,0.03
-Toto-2.0-313m,TabPFN-TS-3,0.5,0.308,0.692,-0.047,-0.16,0.066
-Toto-2.0-313m,Toto-2.0-22m,0.846,0.692,0.962,0.031,0.014,0.049
-Toto-2.0-313m,TiRex,0.769,0.615,0.923,0.054,0.021,0.09
-Toto-2.0-313m,TabPFN-TS,0.654,0.462,0.846,0.013,-0.097,0.104
-Toto-2.0-313m,TimesFM-2.5,0.769,0.615,0.923,0.073,0.032,0.121
-Toto-2.0-313m,FlowState,0.808,0.654,0.962,0.08,0.042,0.122
-Toto-2.0-313m,Chronos-Bolt,0.846,0.692,0.962,0.079,0.033,0.131
-Toto-2.0-313m,Moirai-2.0,0.808,0.654,0.924,0.09,0.047,0.134
-Toto-2.0-313m,Toto-1.0,0.885,0.769,1.0,0.102,0.071,0.134
-Toto-2.0-313m,Toto-2.0-4m,0.923,0.808,1.0,0.099,0.061,0.139
-Toto-2.0-313m,Seasonal Naive,1.0,1.0,1.0,0.404,0.333,0.471
-TiRex-2,Chronos-2,0.423,0.231,0.615,-0.047,-0.104,0.001
-TiRex-2,Toto-2.0-1B,0.423,0.231,0.615,0.042,-0.043,0.129
-TiRex-2,Toto-2.0-2.5B,0.462,0.269,0.654,0.053,-0.028,0.137
-TiRex-2,Toto-2.0-313m,0.462,0.269,0.654,0.05,-0.031,0.135
-TiRex-2,TiRex-2,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex-2,TabPFN-TS-3,0.5,0.308,0.692,0.006,-0.078,0.082
-TiRex-2,Toto-2.0-22m,0.5,0.308,0.692,0.08,0.002,0.161
-TiRex-2,TiRex,0.615,0.423,0.808,0.102,0.031,0.173
-TiRex-2,TabPFN-TS,0.615,0.423,0.808,0.063,-0.006,0.135
-TiRex-2,TimesFM-2.5,0.731,0.538,0.885,0.12,0.044,0.196
-TiRex-2,FlowState,0.808,0.654,0.923,0.126,0.052,0.194
-TiRex-2,Chronos-Bolt,0.808,0.654,0.962,0.125,0.045,0.209
-TiRex-2,Moirai-2.0,0.808,0.654,0.962,0.136,0.067,0.203
-TiRex-2,Toto-1.0,0.769,0.615,0.923,0.147,0.069,0.224
-TiRex-2,Toto-2.0-4m,0.846,0.692,0.962,0.144,0.068,0.221
-TiRex-2,Seasonal Naive,1.0,1.0,1.0,0.434,0.355,0.506
-TabPFN-TS-3,Chronos-2,0.308,0.154,0.5,-0.053,-0.119,0.003
-TabPFN-TS-3,Toto-2.0-1B,0.5,0.308,0.692,0.036,-0.08,0.134
-TabPFN-TS-3,Toto-2.0-2.5B,0.5,0.308,0.692,0.048,-0.063,0.139
-TabPFN-TS-3,Toto-2.0-313m,0.5,0.308,0.692,0.045,-0.071,0.138
-TabPFN-TS-3,TiRex-2,0.5,0.308,0.692,-0.006,-0.089,0.073
-TabPFN-TS-3,TabPFN-TS-3,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS-3,Toto-2.0-22m,0.577,0.385,0.769,0.075,-0.031,0.163
-TabPFN-TS-3,TiRex,0.538,0.346,0.731,0.097,-0.002,0.184
-TabPFN-TS-3,TabPFN-TS,0.769,0.615,0.923,0.057,-0.009,0.113
-TabPFN-TS-3,TimesFM-2.5,0.615,0.423,0.808,0.114,0.023,0.198
-TabPFN-TS-3,FlowState,0.731,0.538,0.885,0.121,0.019,0.206
-TabPFN-TS-3,Chronos-Bolt,0.731,0.577,0.885,0.12,0.034,0.196
-TabPFN-TS-3,Moirai-2.0,0.654,0.462,0.846,0.131,0.027,0.222
-TabPFN-TS-3,Toto-1.0,0.654,0.462,0.808,0.142,0.045,0.231
-TabPFN-TS-3,Toto-2.0-4m,0.692,0.5,0.846,0.139,0.049,0.221
-TabPFN-TS-3,Seasonal Naive,1.0,1.0,1.0,0.431,0.357,0.498
-Toto-2.0-22m,Chronos-2,0.308,0.154,0.5,-0.139,-0.231,-0.055
-Toto-2.0-22m,Toto-2.0-1B,0.115,0.0,0.269,-0.042,-0.07,-0.019
-Toto-2.0-22m,Toto-2.0-2.5B,0.231,0.077,0.385,-0.029,-0.047,-0.011
-Toto-2.0-22m,Toto-2.0-313m,0.154,0.038,0.308,-0.032,-0.052,-0.014
-Toto-2.0-22m,TiRex-2,0.5,0.308,0.692,-0.087,-0.192,-0.002
-Toto-2.0-22m,TabPFN-TS-3,0.423,0.231,0.615,-0.081,-0.195,0.03
-Toto-2.0-22m,Toto-2.0-22m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-22m,TiRex,0.5,0.308,0.692,0.024,-0.012,0.064
-Toto-2.0-22m,TabPFN-TS,0.5,0.308,0.692,-0.019,-0.126,0.073
-Toto-2.0-22m,TimesFM-2.5,0.654,0.462,0.846,0.043,0.0,0.09
-Toto-2.0-22m,FlowState,0.769,0.615,0.923,0.05,0.007,0.089
-Toto-2.0-22m,Chronos-Bolt,0.769,0.615,0.923,0.049,0.002,0.098
-Toto-2.0-22m,Moirai-2.0,0.731,0.538,0.885,0.061,0.018,0.104
-Toto-2.0-22m,Toto-1.0,0.846,0.692,0.962,0.073,0.047,0.104
-Toto-2.0-22m,Toto-2.0-4m,0.808,0.654,0.962,0.069,0.038,0.103
-Toto-2.0-22m,Seasonal Naive,1.0,1.0,1.0,0.385,0.315,0.453
-TiRex,Chronos-2,0.192,0.038,0.346,-0.166,-0.256,-0.083
-TiRex,Toto-2.0-1B,0.269,0.115,0.423,-0.067,-0.129,-0.023
-TiRex,Toto-2.0-2.5B,0.231,0.077,0.385,-0.054,-0.102,-0.016
-TiRex,Toto-2.0-313m,0.231,0.077,0.385,-0.057,-0.099,-0.021
-TiRex,TiRex-2,0.385,0.192,0.577,-0.113,-0.209,-0.032
-TiRex,TabPFN-TS-3,0.462,0.269,0.654,-0.107,-0.225,0.002
-TiRex,Toto-2.0-22m,0.5,0.308,0.692,-0.024,-0.068,0.012
-TiRex,TiRex,0.5,0.5,0.5,0.0,0.0,0.0
-TiRex,TabPFN-TS,0.5,0.308,0.692,-0.043,-0.153,0.057
-TiRex,TimesFM-2.5,0.673,0.5,0.846,0.02,-0.015,0.053
-TiRex,FlowState,0.596,0.404,0.769,0.027,-0.013,0.066
-TiRex,Chronos-Bolt,0.712,0.538,0.865,0.026,-0.018,0.077
-TiRex,Moirai-2.0,0.75,0.577,0.904,0.038,0.007,0.071
-TiRex,Toto-1.0,0.788,0.635,0.942,0.05,0.022,0.081
-TiRex,Toto-2.0-4m,0.769,0.614,0.923,0.047,0.012,0.079
-TiRex,Seasonal Naive,1.0,1.0,1.0,0.37,0.299,0.439
-TabPFN-TS,Chronos-2,0.154,0.038,0.308,-0.118,-0.207,-0.048
-TabPFN-TS,Toto-2.0-1B,0.346,0.192,0.538,-0.022,-0.126,0.078
-TabPFN-TS,Toto-2.0-2.5B,0.308,0.154,0.462,-0.01,-0.109,0.085
-TabPFN-TS,Toto-2.0-313m,0.346,0.154,0.538,-0.013,-0.116,0.088
-TabPFN-TS,TiRex-2,0.385,0.192,0.577,-0.067,-0.156,0.006
-TabPFN-TS,TabPFN-TS-3,0.231,0.077,0.385,-0.061,-0.128,0.009
-TabPFN-TS,Toto-2.0-22m,0.5,0.308,0.692,0.018,-0.078,0.112
-TabPFN-TS,TiRex,0.5,0.308,0.692,0.042,-0.06,0.132
-TabPFN-TS,TabPFN-TS,0.5,0.5,0.5,0.0,0.0,0.0
-TabPFN-TS,TimesFM-2.5,0.538,0.346,0.731,0.061,-0.032,0.147
-TabPFN-TS,FlowState,0.577,0.385,0.769,0.068,-0.037,0.15
-TabPFN-TS,Chronos-Bolt,0.577,0.385,0.769,0.066,-0.013,0.144
-TabPFN-TS,Moirai-2.0,0.615,0.423,0.808,0.078,-0.027,0.177
-TabPFN-TS,Toto-1.0,0.577,0.385,0.769,0.09,-0.012,0.186
-TabPFN-TS,Toto-2.0-4m,0.615,0.423,0.808,0.087,-0.017,0.179
-TabPFN-TS,Seasonal Naive,1.0,1.0,1.0,0.396,0.322,0.469
-TimesFM-2.5,Chronos-2,0.192,0.038,0.346,-0.19,-0.289,-0.094
-TimesFM-2.5,Toto-2.0-1B,0.154,0.038,0.308,-0.088,-0.15,-0.039
-TimesFM-2.5,Toto-2.0-2.5B,0.231,0.077,0.385,-0.075,-0.134,-0.032
-TimesFM-2.5,Toto-2.0-313m,0.231,0.077,0.385,-0.079,-0.137,-0.033
-TimesFM-2.5,TiRex-2,0.269,0.115,0.462,-0.136,-0.244,-0.046
-TimesFM-2.5,TabPFN-TS-3,0.385,0.192,0.577,-0.129,-0.247,-0.023
-TimesFM-2.5,Toto-2.0-22m,0.346,0.154,0.538,-0.045,-0.098,-0.0
-TimesFM-2.5,TiRex,0.327,0.154,0.5,-0.02,-0.056,0.015
-TimesFM-2.5,TabPFN-TS,0.462,0.269,0.654,-0.064,-0.172,0.031
-TimesFM-2.5,TimesFM-2.5,0.5,0.5,0.5,0.0,0.0,0.0
-TimesFM-2.5,FlowState,0.538,0.365,0.712,0.008,-0.042,0.052
-TimesFM-2.5,Chronos-Bolt,0.577,0.404,0.75,0.006,-0.031,0.046
-TimesFM-2.5,Moirai-2.0,0.615,0.442,0.788,0.018,-0.038,0.072
-TimesFM-2.5,Toto-1.0,0.654,0.481,0.808,0.031,-0.017,0.08
-TimesFM-2.5,Toto-2.0-4m,0.615,0.423,0.808,0.028,-0.014,0.068
-TimesFM-2.5,Seasonal Naive,1.0,1.0,1.0,0.357,0.288,0.423
-FlowState,Chronos-2,0.154,0.038,0.308,-0.199,-0.288,-0.109
-FlowState,Toto-2.0-1B,0.192,0.038,0.346,-0.097,-0.151,-0.049
-FlowState,Toto-2.0-2.5B,0.154,0.038,0.308,-0.084,-0.136,-0.038
-FlowState,Toto-2.0-313m,0.192,0.038,0.346,-0.087,-0.139,-0.043
-FlowState,TiRex-2,0.192,0.077,0.346,-0.145,-0.241,-0.055
-FlowState,TabPFN-TS-3,0.269,0.115,0.462,-0.138,-0.259,-0.02
-FlowState,Toto-2.0-22m,0.231,0.077,0.385,-0.053,-0.098,-0.007
-FlowState,TiRex,0.404,0.231,0.596,-0.028,-0.071,0.013
-FlowState,TabPFN-TS,0.423,0.231,0.615,-0.073,-0.177,0.036
-FlowState,TimesFM-2.5,0.462,0.288,0.635,-0.008,-0.055,0.04
-FlowState,FlowState,0.5,0.5,0.5,0.0,0.0,0.0
-FlowState,Chronos-Bolt,0.5,0.326,0.674,-0.002,-0.052,0.067
-FlowState,Moirai-2.0,0.538,0.365,0.712,0.011,-0.039,0.061
-FlowState,Toto-1.0,0.462,0.288,0.635,0.023,-0.024,0.072
-FlowState,Toto-2.0-4m,0.538,0.346,0.731,0.02,-0.033,0.065
-FlowState,Seasonal Naive,0.923,0.808,1.0,0.352,0.275,0.427
-Chronos-Bolt,Chronos-2,0.038,0.0,0.115,-0.197,-0.299,-0.11
-Chronos-Bolt,Toto-2.0-1B,0.077,0.0,0.192,-0.095,-0.16,-0.038
-Chronos-Bolt,Toto-2.0-2.5B,0.154,0.038,0.308,-0.082,-0.139,-0.032
-Chronos-Bolt,Toto-2.0-313m,0.154,0.038,0.308,-0.085,-0.15,-0.035
-Chronos-Bolt,TiRex-2,0.192,0.038,0.346,-0.143,-0.264,-0.047
-Chronos-Bolt,TabPFN-TS-3,0.269,0.115,0.423,-0.136,-0.244,-0.035
-Chronos-Bolt,Toto-2.0-22m,0.231,0.077,0.385,-0.051,-0.108,-0.002
-Chronos-Bolt,TiRex,0.288,0.135,0.462,-0.027,-0.084,0.018
-Chronos-Bolt,TabPFN-TS,0.423,0.231,0.615,-0.071,-0.168,0.013
-Chronos-Bolt,TimesFM-2.5,0.423,0.25,0.596,-0.006,-0.048,0.03
-Chronos-Bolt,FlowState,0.5,0.326,0.674,0.002,-0.072,0.05
-Chronos-Bolt,Chronos-Bolt,0.5,0.5,0.5,0.0,0.0,0.0
-Chronos-Bolt,Moirai-2.0,0.462,0.308,0.635,0.012,-0.062,0.076
-Chronos-Bolt,Toto-1.0,0.615,0.442,0.769,0.025,-0.03,0.078
-Chronos-Bolt,Toto-2.0-4m,0.615,0.423,0.77,0.022,-0.038,0.07
-Chronos-Bolt,Seasonal Naive,1.0,1.0,1.0,0.353,0.287,0.417
-Moirai-2.0,Chronos-2,0.077,0.0,0.192,-0.212,-0.32,-0.122
-Moirai-2.0,Toto-2.0-1B,0.154,0.038,0.308,-0.109,-0.173,-0.057
-Moirai-2.0,Toto-2.0-2.5B,0.192,0.077,0.346,-0.096,-0.154,-0.048
-Moirai-2.0,Toto-2.0-313m,0.192,0.076,0.346,-0.099,-0.154,-0.05
-Moirai-2.0,TiRex-2,0.192,0.038,0.346,-0.157,-0.255,-0.072
-Moirai-2.0,TabPFN-TS-3,0.346,0.154,0.538,-0.151,-0.285,-0.028
-Moirai-2.0,Toto-2.0-22m,0.269,0.115,0.462,-0.064,-0.116,-0.018
-Moirai-2.0,TiRex,0.25,0.096,0.423,-0.039,-0.077,-0.007
-Moirai-2.0,TabPFN-TS,0.385,0.192,0.577,-0.084,-0.216,0.026
-Moirai-2.0,TimesFM-2.5,0.385,0.212,0.558,-0.019,-0.077,0.037
-Moirai-2.0,FlowState,0.462,0.288,0.635,-0.011,-0.066,0.037
-Moirai-2.0,Chronos-Bolt,0.538,0.365,0.692,-0.012,-0.082,0.058
-Moirai-2.0,Moirai-2.0,0.5,0.5,0.5,0.0,0.0,0.0
-Moirai-2.0,Toto-1.0,0.538,0.365,0.712,0.013,-0.016,0.045
-Moirai-2.0,Toto-2.0-4m,0.538,0.346,0.731,0.009,-0.03,0.051
-Moirai-2.0,Seasonal Naive,0.923,0.808,1.0,0.345,0.266,0.421
-Toto-1.0,Chronos-2,0.115,0.0,0.231,-0.228,-0.337,-0.135
-Toto-1.0,Toto-2.0-1B,0.038,0.0,0.115,-0.123,-0.18,-0.08
-Toto-1.0,Toto-2.0-2.5B,0.077,0.0,0.192,-0.11,-0.158,-0.072
-Toto-1.0,Toto-2.0-313m,0.115,0.0,0.231,-0.113,-0.155,-0.077
-Toto-1.0,TiRex-2,0.231,0.077,0.385,-0.172,-0.289,-0.074
-Toto-1.0,TabPFN-TS-3,0.346,0.192,0.538,-0.166,-0.3,-0.047
-Toto-1.0,Toto-2.0-22m,0.154,0.038,0.308,-0.078,-0.117,-0.049
-Toto-1.0,TiRex,0.212,0.058,0.365,-0.053,-0.088,-0.023
-Toto-1.0,TabPFN-TS,0.423,0.231,0.615,-0.099,-0.228,0.012
-Toto-1.0,TimesFM-2.5,0.346,0.192,0.519,-0.032,-0.087,0.017
-Toto-1.0,FlowState,0.538,0.365,0.712,-0.024,-0.078,0.023
-Toto-1.0,Chronos-Bolt,0.385,0.231,0.558,-0.026,-0.085,0.029
-Toto-1.0,Moirai-2.0,0.462,0.288,0.635,-0.013,-0.047,0.016
-Toto-1.0,Toto-1.0,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-1.0,Toto-2.0-4m,0.577,0.385,0.731,-0.004,-0.04,0.026
-Toto-1.0,Seasonal Naive,0.962,0.885,1.0,0.337,0.259,0.412
-Toto-2.0-4m,Chronos-2,0.038,0.0,0.115,-0.224,-0.327,-0.128
-Toto-2.0-4m,Toto-2.0-1B,0.038,0.0,0.115,-0.119,-0.184,-0.069
-Toto-2.0-4m,Toto-2.0-2.5B,0.154,0.038,0.308,-0.106,-0.159,-0.06
-Toto-2.0-4m,Toto-2.0-313m,0.077,0.0,0.192,-0.109,-0.161,-0.065
-Toto-2.0-4m,TiRex-2,0.154,0.038,0.308,-0.168,-0.283,-0.072
-Toto-2.0-4m,TabPFN-TS-3,0.308,0.154,0.5,-0.161,-0.283,-0.052
-Toto-2.0-4m,Toto-2.0-22m,0.192,0.038,0.346,-0.075,-0.115,-0.039
-Toto-2.0-4m,TiRex,0.231,0.077,0.386,-0.049,-0.086,-0.012
-Toto-2.0-4m,TabPFN-TS,0.385,0.192,0.577,-0.095,-0.218,0.017
-Toto-2.0-4m,TimesFM-2.5,0.385,0.192,0.577,-0.028,-0.073,0.014
-Toto-2.0-4m,FlowState,0.462,0.269,0.654,-0.02,-0.07,0.032
-Toto-2.0-4m,Chronos-Bolt,0.385,0.23,0.577,-0.022,-0.075,0.036
-Toto-2.0-4m,Moirai-2.0,0.462,0.269,0.654,-0.01,-0.053,0.029
-Toto-2.0-4m,Toto-1.0,0.423,0.269,0.615,0.004,-0.027,0.038
-Toto-2.0-4m,Toto-2.0-4m,0.5,0.5,0.5,0.0,0.0,0.0
-Toto-2.0-4m,Seasonal Naive,1.0,1.0,1.0,0.339,0.27,0.408
-Seasonal Naive,Chronos-2,0.0,0.0,0.0,-0.852,-1.093,-0.622
-Seasonal Naive,Toto-2.0-1B,0.0,0.0,0.0,-0.694,-0.927,-0.5
-Seasonal Naive,Toto-2.0-2.5B,0.0,0.0,0.0,-0.674,-0.899,-0.491
-Seasonal Naive,Toto-2.0-313m,0.0,0.0,0.0,-0.679,-0.891,-0.5
-Seasonal Naive,TiRex-2,0.0,0.0,0.0,-0.768,-1.023,-0.55
-Seasonal Naive,TabPFN-TS-3,0.0,0.0,0.0,-0.758,-0.992,-0.556
-Seasonal Naive,Toto-2.0-22m,0.0,0.0,0.0,-0.626,-0.83,-0.46
-Seasonal Naive,TiRex,0.0,0.0,0.0,-0.588,-0.782,-0.427
-Seasonal Naive,TabPFN-TS,0.0,0.0,0.0,-0.657,-0.882,-0.476
-Seasonal Naive,TimesFM-2.5,0.0,0.0,0.0,-0.556,-0.734,-0.404
-Seasonal Naive,FlowState,0.077,0.0,0.192,-0.544,-0.745,-0.38
-Seasonal Naive,Chronos-Bolt,0.0,0.0,0.0,-0.547,-0.716,-0.403
-Seasonal Naive,Moirai-2.0,0.077,0.0,0.192,-0.528,-0.727,-0.362
-Seasonal Naive,Toto-1.0,0.038,0.0,0.115,-0.508,-0.7,-0.35
-Seasonal Naive,Toto-2.0-4m,0.0,0.0,0.0,-0.513,-0.688,-0.369
-Seasonal Naive,Seasonal Naive,0.5,0.5,0.5,0.0,0.0,0.0

tables/domain_health/leaderboard_MASE.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-TiRex-2,80.37037037037038,34.9166343514373,0.0,0.3575023838736039,0.0,0.0
-TimesFM-2.5,70.37037037037038,32.87474894024488,0.0,1.1256479395833334,0.0,0.0
-Chronos-2,68.88888888888891,31.78597649489514,0.0,0.3492251116666667,0.0,0.0
-TabPFN-TS-3,68.51851851851852,28.963255047296542,0.0,199.6776895770319,0.0,0.0
-TabPFN-TS,66.66666666666666,34.55373879766452,0.0,53.951610824166664,0.0,0.0
-TiRex,65.18518518518519,32.47588770643868,0.0,0.330588668125,0.0,0.0
-FlowState,63.33333333333334,27.93729353213241,0.0,1.679734656979167,0.0,0.0
-LightGBM,62.96296296296296,33.38915880315173,1.2161332720833333,0.19742606979166666,0.0,0.0
-CatBoost,62.22222222222222,33.16623383500657,13.210264008932292,0.19426541770833333,0.0,0.0
-Moirai-2.0,62.03703703703704,33.79488506711863,0.0,0.3505868739583333,0.1,0.0
-Toto-2.0-313m,60.74074074074075,27.130941962281884,0.0,1.1242909435416668,0.0,0.0
-Toto-2.0-2.5B,60.74074074074075,27.02155839964281,0.0,5.925324101666666,0.0,0.0
-Toto-2.0-1B,56.666666666666664,26.055688762834595,0.0,2.728815209166667,0.0,0.0
-Toto-2.0-22m,56.2962962962963,27.354995059689568,0.0,0.4238227016666667,0.0,0.0
-Toto-1.0,55.18518518518518,31.700573837170467,0.0,9.804296426666667,0.0,0.0
-Chronos-Bolt,54.629629629629626,30.041136052707273,0.0,0.41178704374999997,0.0,0.0
-Toto-2.0-4m,54.07407407407408,28.997499277709025,0.0,0.36290417583333334,0.0,0.0
-AutoETS,48.14814814814816,28.071655328734924,0.0,2.5273205354166666,0.0,0.0
-Stat. Ensemble,48.148148148148145,29.22979017092695,0.0,191.30953815208332,0.0,0.0
-Sundial-Base,44.81481481481482,22.70787609837541,0.0,8.29280267,0.0,0.0
-AutoARIMA,32.59259259259259,5.881738752268506,0.0,7.6933014760416665,0.0,0.0
-TFT,28.888888888888886,8.056299346355855,577.3621929408333,0.91290832015625,0.0,0.0
-AutoTheta,26.666666666666668,15.20916710141943,0.0,2.3246237520833333,0.0,0.0
-DeepAR,23.333333333333336,8.848833829469338,1252.3585836206248,0.9790481578125001,0.0,0.0
-PatchTST,22.592592592592585,12.927869318522445,812.3820815818749,0.4485787422916667,0.0,0.0
-Seasonal Naive,20.185185185185187,0.0,0.0,1.2681127877083334,0.0,0.0
-Naive,17.962962962962962,0.30982947391161586,0.0,1.2969351423177082,0.0,0.0
-Drift,17.77777777777778,7.491051482058886,0.0,1.3917920932291667,0.0,0.0

tables/domain_health/leaderboard_SQL.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-TiRex-2,84.44444444444444,39.425727939082535,0.0,0.3575023838736039,0.0,0.0
-Chronos-2,78.51851851851852,38.08875531260849,0.0,0.3492251116666667,0.0,0.0
-TimesFM-2.5,73.33333333333336,38.03594071146331,0.0,1.1256479395833334,0.0,0.0
-Toto-2.0-313m,68.51851851851852,33.76977925435224,0.0,1.1242909435416668,0.0,0.0
-Moirai-2.0,67.5925925925926,38.69101646514035,0.0,0.3505868739583333,0.1,0.0
-TabPFN-TS,66.66666666666666,37.79500412291329,0.0,53.951610824166664,0.0,0.0
-Toto-2.0-2.5B,65.92592592592594,33.54660585794915,0.0,5.925324101666666,0.0,0.0
-TiRex,65.55555555555556,36.908809542631595,0.0,0.330588668125,0.0,0.0
-TabPFN-TS-3,64.81481481481482,33.86938070997042,0.0,199.6776895770319,0.0,0.0
-Toto-1.0,63.703703703703695,37.78506660666954,0.0,9.804296426666667,0.0,0.0
-Toto-2.0-1B,62.5925925925926,32.77732666419397,0.0,2.728815209166667,0.0,0.0
-Toto-2.0-22m,62.22222222222222,33.710262442699914,0.0,0.4238227016666667,0.0,0.0
-Chronos-Bolt,61.66666666666666,36.49963478571547,0.0,0.41178704374999997,0.0,0.0
-FlowState,57.03703703703704,32.77403706037661,0.0,1.679734656979167,0.0,0.0
-Toto-2.0-4m,55.18518518518518,34.41096517434523,0.0,0.36290417583333334,0.0,0.0
-AutoETS,52.22222222222223,31.12404358258436,0.0,2.5273205354166666,0.0,0.0
-Stat. Ensemble,46.666666666666664,31.666899122864876,0.0,191.30953815208332,0.0,0.0
-LightGBM,41.851851851851855,24.996902028028057,1.2161332720833333,0.19742606979166666,0.0,0.0
-CatBoost,37.77777777777778,24.745890887412404,13.210264008932292,0.19426541770833333,0.0,0.0
-Sundial-Base,36.29629629629629,23.555776042271713,0.0,8.29280267,0.0,0.0
-AutoARIMA,33.33333333333333,8.15543220497067,0.0,7.6933014760416665,0.0,0.0
-TFT,32.59259259259259,13.487049535026774,577.3621929408333,0.91290832015625,0.0,0.0
-PatchTST,25.925925925925924,17.70708962424181,812.3820815818749,0.4485787422916667,0.0,0.0
-AutoTheta,25.185185185185183,17.733419411019135,0.0,2.3246237520833333,0.0,0.0
-DeepAR,22.962962962962962,13.730380882991922,1252.3585836206248,0.9790481578125001,0.0,0.0
-Seasonal Naive,19.444444444444446,0.0,0.0,1.2681127877083334,0.0,0.0
-Naive,14.629629629629632,-7.297793646802875,0.0,1.2969351423177082,0.0,0.0
-Drift,13.333333333333334,0.404190086867684,0.0,1.3917920932291667,0.0,0.0

tables/domain_health/leaderboard_WAPE.csv

@@ -1,29 +0,0 @@
-model_name,win_rate,skill_score,median_training_time_s_per100,median_inference_time_s_per100,training_corpus_overlap,num_failures
-TimesFM-2.5,69.62962962962965,30.236433011588616,0.0,1.1256479395833334,0.0,0.0
-TiRex-2,68.14814814814817,26.601930748682324,0.0,0.3575023838736039,0.0,0.0
-TabPFN-TS-3,67.77777777777779,27.06736057976333,0.0,199.6776895770319,0.0,0.0
-Chronos-2,66.2962962962963,29.12048347898083,0.0,0.3492251116666667,0.0,0.0
-Toto-2.0-2.5B,64.07407407407408,23.803402469752132,0.0,5.925324101666666,0.0,0.0
-TiRex,63.70370370370372,29.759653720585042,0.0,0.330588668125,0.0,0.0
-FlowState,62.22222222222222,25.714346434991153,0.0,1.679734656979167,0.0,0.0
-Moirai-2.0,60.92592592592593,31.595921669939887,0.0,0.3505868739583333,0.1,0.0
-Toto-1.0,60.370370370370374,28.753205083598854,0.0,9.804296426666667,0.0,0.0
-Toto-2.0-313m,59.25925925925927,23.159110215973843,0.0,1.1242909435416668,0.0,0.0
-Toto-2.0-22m,58.51851851851851,23.737937635347716,0.0,0.4238227016666667,0.0,0.0
-Toto-2.0-1B,58.14814814814815,22.479955103457115,0.0,2.728815209166667,0.0,0.0
-TabPFN-TS,57.407407407407405,29.1761523445201,0.0,53.951610824166664,0.0,0.0
-AutoETS,56.666666666666664,29.45241897965094,0.0,2.5273205354166666,0.0,0.0
-Toto-2.0-4m,55.92592592592594,24.961571876693643,0.0,0.36290417583333334,0.0,0.0
-Stat. Ensemble,55.925925925925924,29.6956210738891,0.0,191.30953815208332,0.0,0.0
-LightGBM,54.81481481481482,28.23998648969035,1.2161332720833333,0.19742606979166666,0.0,0.0
-Chronos-Bolt,52.77777777777778,25.883263022341175,0.0,0.41178704374999997,0.0,0.0
-CatBoost,47.77777777777777,24.80079887494443,13.210264008932292,0.19426541770833333,0.0,0.0
-Sundial-Base,41.85185185185184,16.462366143379946,0.0,8.29280267,0.0,0.0
-AutoARIMA,36.66666666666667,15.90999185953288,0.0,7.6933014760416665,0.0,0.0
-AutoTheta,30.740740740740733,14.265515876146328,0.0,2.3246237520833333,0.0,0.0
-DeepAR,28.148148148148156,4.835755105983619,1252.3585836206248,0.9790481578125001,0.0,0.0
-Drift,26.296296296296294,6.995102476216641,0.0,1.3917920932291667,0.0,0.0
-TFT,24.814814814814813,-0.6246028567987283,577.3621929408333,0.91290832015625,0.0,0.0
-Seasonal Naive,24.629629629629633,0.0,0.0,1.2681127877083334,0.0,0.0
-Naive,24.629629629629626,0.09410405602899852,0.0,1.2969351423177082,0.0,0.0
-PatchTST,21.851851851851848,2.754946880183251,812.3820815818749,0.4485787422916667,0.0,0.0