Mindket

CausalArena Leaderboard

Newversion 1 · updated

Overview

A static dashboard of the CausalArena benchmark for learning causal structure, with a leaderboard, real-data checks, case views, a gallery of released graphs and a guide to submitting results.

CausalArena Leaderboard is a kit in the Research category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.

At a glance

You need
  • Python and pip, for the huggingface_hub package that gives you the hf command
  • A web browser
  • Disk space for the repository, which holds 117 files
Runs in
  • A web browser, on the Space's page at Hugging Face
  • Windows, by opening the downloaded index.html in a browser
  • macOS, with the same download
  • Linux, with the same download
Start with
pip install -U huggingface_hub
hf download LAMDA-Tabular/CausalArena-leaderboard --repo-type space --local-dir CausalArena-leaderboard
cd CausalArena-leaderboard

Platform

WindowsOperating system
macOSOperating system
LinuxOperating system

About

What it is

CausalArena Leaderboard is a static dashboard for the public release of CausalArena, a benchmark for learning causal structure from data. It collects the main leaderboard, real-data checks, scaling and runtime views, taxonomy summaries, case inspection, and a gallery of released graphs. You open it in a browser and install nothing.

Who it suits

Researchers who work on learning causal structure and want to compare methods, and contributors who want to add their own results or new causal models.

IndustryWho uses itHow they use itExample
ResearchCausal structure researchersCompare methods on the main leaderboardOpen the leaderboard page and read the rankings
Data sciencePractitionersCheck how methods hold up on real dataRead the real-data checks
EducationStudentsBrowse released causal graphsOpen the SCM Gallery page
Benchmark contributorsMethod authorsSubmit results or propose a new causal modelFollow the Submit page steps

Anyone who is not working on causal structure learning can skip it.

Where to use it

It runs in these places.

  • A web browser, on the Space's page at Hugging Face
  • Windows, by opening the downloaded index.html in a browser
  • macOS, with the same download
  • Linux, with the same download
Use caseWhoWhat they get back
Compare methodsResearchersThe main leaderboard and the scaling and runtime views
Inspect casesResearchersSemantic and Formula case views
Browse released graphsStudents and researchersThe SCM Gallery page of grounded graphs

How to set it up

Using the Space online needs only a browser. Getting its files onto your own computer needs the following.

  • Python and pip, for the huggingface_hub package that gives you the hf command
  • A web browser
  • Disk space for the repository, which holds 117 files
  1. Install the huggingface_hub package.
  2. Download the Space's files into a local folder.
  3. Move into that folder.
  4. Open the file index.html in a web browser.
pip install -U huggingface_hub
hf download LAMDA-Tabular/CausalArena-leaderboard --repo-type space --local-dir CausalArena-leaderboard
cd CausalArena-leaderboard

How to use it

Open the page and move between its views. The table lists what each part shows. To contribute, read the Submit page.

ToolWhat it does
Main leaderboardRanks methods on the benchmark
Real-data checksShows how methods do on real data
Scaling and runtime viewsShow how results change with size and how long runs take
Taxonomy summariesGroup the results by category
Case inspectionLets you look at Semantic and Formula cases
SCM GalleryLets you browse the released grounded graphs
Submit pageDescribes the audited steps for contributing

Example

A researcher with a new causal structure method reads the Submit page. They download the result template from the companion dataset repository, validate their package on their own machine, and submit through the companion GitHub repository. Maintainers refresh the dashboard after checking it.

For newcomers and experts

Learning causal structure means working out which things cause which from data. The first small thing to try is the main leaderboard, then the SCM Gallery to see example graphs.

The page is static, so nothing computes on request and results appear only when maintainers update it. The contribution path is audited, with local validation of packages before submission. Its citation frames it as a benchmark for causal structure learning in the age of foundation models.

  1. You download the result or SCM template
  2. You validate the package locally
  3. You submit through the companion GitHub repository
  4. Maintainers refresh the static dashboard

Good to know

Submissions do not happen on the page itself, and the dashboard only updates after maintainers validate them.

  • License: cc-by-4
  • Cost to run: none named
  • Data it reaches: the page's own files, with no account or service named
  • Citation: the README asks you to cite the CausalArena paper if you use it
  • Not for: submitting directly in the page, since submissions go through the companion GitHub repository

README and files

README

CausalArena Leaderboard

A static dashboard of the CausalArena benchmark for learning causal structure, with a leaderboard, real-data checks, case views, a gallery of released graphs and a guide to submitting results.

Made by LAMDA-Tabular on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: CausalArena Leaderboard is a static dashboard for the public release of CausalArena, a benchmark for learning causal structure from data. It collects the main leaderboard, real-data checks, scaling and runtime views, taxonomy summaries, case inspection, and a gallery of released graphs. You open it in a browser and install nothing.

Who it suits: Researchers who work on learning causal structure and want to compare methods, and contributors who want to add their own results or new causal models.

Industry | Who uses it | How they use it | Example
Research | Causal structure researchers | Compare methods on the main leaderboard | Open the leaderboard page and read the rankings
Data science | Practitioners | Check how methods hold up on real data | Read the real-data checks
Education | Students | Browse released causal graphs | Open the SCM Gallery page
Benchmark contributors | Method authors | Submit results or propose a new causal model | Follow the Submit page steps

Anyone who is not working on causal structure learning can skip it.

Where to use it: It runs in these places.

  • A web browser, on the Space's page at Hugging Face
  • Windows, by opening the downloaded index.html in a browser
  • macOS, with the same download
  • Linux, with the same download
Use case | Who | What they get back
Compare methods | Researchers | The main leaderboard and the scaling and runtime views
Inspect cases | Researchers | Semantic and Formula case views
Browse released graphs | Students and researchers | The SCM Gallery page of grounded graphs

How to set it up: Using the Space online needs only a browser. Getting its files onto your own computer needs the following.

  • Python and pip, for the huggingface_hub package that gives you the hf command
  • A web browser
  • Disk space for the repository, which holds 117 files
  1. Install the huggingface_hub package.
  2. Download the Space's files into a local folder.
  3. Move into that folder.
  4. Open the file index.html in a web browser.
pip install -U huggingface_hub
hf download LAMDA-Tabular/CausalArena-leaderboard --repo-type space --local-dir CausalArena-leaderboard
cd CausalArena-leaderboard

How to use it: Open the page and move between its views. The table lists what each part shows. To contribute, read the Submit page.

Tool | What it does
Main leaderboard | Ranks methods on the benchmark
Real-data checks | Shows how methods do on real data
Scaling and runtime views | Show how results change with size and how long runs take
Taxonomy summaries | Group the results by category
Case inspection | Lets you look at Semantic and Formula cases
SCM Gallery | Lets you browse the released grounded graphs
Submit page | Describes the audited steps for contributing

Example: A researcher with a new causal structure method reads the Submit page. They download the result template from the companion dataset repository, validate their package on their own machine, and submit through the companion GitHub repository. Maintainers refresh the dashboard after checking it.

For newcomers and experts: Learning causal structure means working out which things cause which from data. The first small thing to try is the main leaderboard, then the SCM Gallery to see example graphs.

The page is static, so nothing computes on request and results appear only when maintainers update it. The contribution path is audited, with local validation of packages before submission. Its citation frames it as a benchmark for causal structure learning in the age of foundation models.

You download the result or SCM template
You validate the package locally
You submit through the companion GitHub repository
Maintainers refresh the static dashboard

Good to know: Submissions do not happen on the page itself, and the dashboard only updates after maintainers validate them.

  • License: cc-by-4
  • Cost to run: none named
  • Data it reaches: the page's own files, with no account or service named
  • Citation: the README asks you to cite the CausalArena paper if you use it
  • Not for: submitting directly in the page, since submissions go through the companion GitHub repository

On Hugging Face, 13 November 2026

  • Likes: 2
  • Built with: static
  • License: cc-by-4.0

Links

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.

Files
README.md  5 KB

1 file, 5 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-12

Compare with similar

Listed Hugging Face Spaces in the same category that share the most tags with this one.

ProductLikesBuilt withLicenseLast change
CausalArena Leaderboard This page2staticcc-by-4.0
Arena LeaderboardShares static5,039staticapache-2.0
BrowserShares static533staticcc0-1.0
Model PulseShares static214staticapache-2.0
MTEB-BR LeaderboardShares static126staticapache-2.0
Hub StatsShares static65staticapache-2.0
Numbers as Mindket last read them, on 2026-11-12.

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

Bonsai-27B-GGUF

lmstudio-community · Kit

A GGUF conversion of the 27B Bonsai model for LM Studio, with a 3.80 GB Q1_0 language file and a 0.93 GB BF16 vision projector. Tested for text, vision and par…

New

Runs DeepSeek-V4.1-Flash-1017 as a 2.9 bits-per-weight EXL3 quantization, a 196 GiB copy for people serving large models on their own hardware. Perplexity stay…

New

MusicGen Small

facebook · Kit

Generates short music clips from a text description or an audio prompt, in the small checkpoint of facebook's MusicGen. It suits developers and music hobbyists…

New

Similar in Research

See all in Research

Merlin-Cancer-Super

AbdomenAtlas · Kit

Detects and outlines tumors in 9 organs on CT scans, trained with the R-Super method that learns from radiology reports. A research model for medical imaging g…

New

EarthJev

dBenf · Kit

Answers typed questions about satellite image patches from all 12 Sentinel-2 bands, returning a probability for each option without writing text. A Qwen3.5-0.8…

New

getting-over-it-rl-jax

zimmerk4 · Kit

Plays the full game Getting Over It from the bottom to the end with a small trained policy network that learned inside a JAX physics simulator. For reinforceme…

New