Data

Tools

Indexes

Applications

Experiments

Open Source Science

hackathon-leaderboard

Automated Leaderboard System for Hackathon Evaluation Using Large Language Models

https://github.com/skywardai/hackathon-leaderboard

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.0%) to scientific vocabulary

Keywords

ai bedrock hackathon llms text-classification text-clustering
Last synced: 6 months ago · JSON representation ·

Repository

Automated Leaderboard System for Hackathon Evaluation Using Large Language Models

Basic Info
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
ai bedrock hackathon llms text-classification text-clustering
Created over 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme Citation

README.md

Automated Leaderboard System for Hackathon Evaluation Using Large Language Models

The code for the paper Automated Leaderboard System for Hackathon Evaluation Using Large Language Models

Architecture

Architecture Diagram
Overview of the system architecture illustrating the processing pipeline of the Jupyter notebook submissions, from initial raw data intake to the final predicted results.

Results

Bland Altman
Bland-Altman analysis [22] table reveals a mean difference (bias) of 27.5 points—meaning the LLM scores are, on average, 27.5 points higher than the technical scores and representing roughly 6.9% of the maximum technical score. The 95% limits of agreement (–6.83 to 61.83) indicate that most differences fall within a 68.66-point range, which aligns with typical inter-rater variability in manual grading and supports the reliability of our hybrid evaluation approach.

Deployment

How to download the Submissions manually

Preparing Kaggle API credentials.

bash pip install kaggle

Run the file retrieve-competition.py it will download and convert all the submission files to .md file.

How to launch the server

You should have node on your machine. And you are welcome to create a SQLite db file results.db

npm install

node index.js

How to run the marking manually

node mark.js

Citation

bibtex @software{Li_Automated_Leaderboard_System_2025, author = {Li, Bowen and Cheng, Bohan and Talyor, Patrick and Osborne, Dale and Han, Fengling and Shen, Robert and Gondal, Iqbal}, doi = {<>}, month = mar, title = {{Automated Leaderboard System for Hackathon Evaluation Using Large Language Models}}, url = {https://github.com/SkywardAI/hackathon-leaderboard}, version = {1.0.0}, year = {2025} }

Owner

  • Name: SkywardAI
  • Login: SkywardAI
  • Kind: organization

Focus on AI, drive the future forward.

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - family-names: "Li"
    given-names: "Bowen"
    orcid: "https://orcid.org/0009-0007-6470-5607"
  - family-names: "Cheng"
    given-names: "Bohan"
  - family-names: "Talyor"
    given-names: "Patrick"
  - family-names: "Osborne"
    given-names: "Dale"
  - family-names: "Han"
    given-names: "Fengling"
  - family-names: "Shen"
    given-names: "Robert"
  - family-names: "Gondal"
    given-names: "Iqbal"
title: "Automated Leaderboard System for Hackathon Evaluation Using Large Language Models"
version: 1.0.0
doi: <>
date-released: 2025-3-08
url: "https://github.com/SkywardAI/hackathon-leaderboard"

GitHub Events

Total
  • Push event: 2
  • Public event: 1
Last Year
  • Push event: 2
  • Public event: 1

Issues and Pull Requests

Last synced: 12 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

leaderboard/package.json npm
  • @eslint/js ^9.13.0 development
  • @types/react ^18.3.11 development
  • @types/react-dom ^18.3.1 development
  • @vitejs/plugin-react ^4.3.3 development
  • eslint ^9.13.0 development
  • eslint-plugin-react ^7.37.1 development
  • eslint-plugin-react-hooks ^5.0.0 development
  • eslint-plugin-react-refresh ^0.4.13 development
  • globals ^15.11.0 development
  • vite ^5.4.9 development
  • react ^18.3.1
  • react-dom ^18.3.1
  • react-router-dom ^6.27.0
leaderboard/pnpm-lock.yaml npm
  • aix-ppc64@0.21.5
  • android-arm64@0.21.5
  • android-arm@0.21.5
  • android-x64@0.21.5
  • babel__core@7.20.5
  • babel__generator@7.6.8
  • babel__template@7.4.4
  • babel__traverse@7.20.6
  • code-frame@7.26.0
  • compat-data@7.26.0
  • config-array@0.18.0
  • core@0.19.1
  • core@0.7.0
  • core@7.26.0
  • darwin-arm64@0.21.5
  • darwin-x64@0.21.5
  • eslint-utils@4.4.1
  • eslintrc@3.1.0
  • estree@1.0.6
  • freebsd-arm64@0.21.5
  • freebsd-x64@0.21.5
  • gen-mapping@0.3.5
  • generator@7.26.0
  • helper-compilation-targets@7.25.9
  • helper-module-imports@7.25.9
  • helper-module-transforms@7.26.0
  • helper-plugin-utils@7.25.9
  • helper-string-parser@7.25.9
  • helper-validator-identifier@7.25.9
  • helper-validator-option@7.25.9
  • helpers@7.26.0
  • js@9.13.0
  • json-schema@7.0.15
  • linux-arm64@0.21.5
  • linux-arm@0.21.5
  • linux-ia32@0.21.5
  • linux-loong64@0.21.5
  • linux-mips64el@0.21.5
  • linux-ppc64@0.21.5
  • linux-riscv64@0.21.5
  • linux-s390x@0.21.5
  • linux-x64@0.21.5
  • module-importer@1.0.1
  • netbsd-x64@0.21.5
  • node@0.16.6
  • object-schema@2.1.4
  • openbsd-x64@0.21.5
  • parser@7.26.1
  • plugin-kit@0.2.2
  • plugin-react@4.3.3
  • plugin-transform-react-jsx-self@7.25.9
  • plugin-transform-react-jsx-source@7.25.9
  • prop-types@15.7.13
  • react-dom@18.3.1
  • react@18.3.12
  • regexpp@4.12.1
  • remapping@2.3.0
  • resolve-uri@3.1.2
  • retry@0.3.1
  • rollup-android-arm-eabi@4.24.2
  • rollup-android-arm64@4.24.2
  • rollup-darwin-arm64@4.24.2
  • rollup-darwin-x64@4.24.2
  • rollup-freebsd-arm64@4.24.2
  • rollup-freebsd-x64@4.24.2
  • rollup-linux-arm-gnueabihf@4.24.2
  • rollup-linux-arm-musleabihf@4.24.2
  • rollup-linux-arm64-gnu@4.24.2
  • rollup-linux-arm64-musl@4.24.2
  • rollup-linux-powerpc64le-gnu@4.24.2
  • rollup-linux-riscv64-gnu@4.24.2
  • rollup-linux-s390x-gnu@4.24.2
  • rollup-linux-x64-gnu@4.24.2
  • rollup-linux-x64-musl@4.24.2
  • rollup-win32-arm64-msvc@4.24.2
  • rollup-win32-ia32-msvc@4.24.2
  • rollup-win32-x64-msvc@4.24.2
  • router@1.20.0
  • set-array@1.2.1
  • sourcemap-codec@1.5.0
  • sunos-x64@0.21.5
  • template@7.25.9
  • trace-mapping@0.3.25
  • traverse@7.25.9
  • types@7.26.0
  • win32-arm64@0.21.5
  • win32-ia32@0.21.5
  • win32-x64@0.21.5
package-lock.json npm
  • 267 dependencies
package.json npm
  • @aws-sdk/client-bedrock-runtime ^3.687.0
  • body-parser ^1.20.3
  • cors ^2.8.5
  • express ^4.21.1
  • sqlite3 ^5.1.7
pnpm-lock.yaml npm
  • abort-controller@3.1.6
  • client-bedrock-runtime@3.687.0
  • client-sso-oidc@3.687.0
  • client-sso@3.687.0
  • client-sts@3.687.0
  • config-resolver@3.0.10
  • core@2.5.1
  • core@3.686.0
  • crc32@5.2.0
  • credential-provider-env@3.686.0
  • credential-provider-http@3.686.0
  • credential-provider-imds@3.2.5
  • credential-provider-ini@3.687.0
  • credential-provider-node@3.687.0
  • credential-provider-process@3.686.0
  • credential-provider-sso@3.687.0
  • credential-provider-web-identity@3.686.0
  • eventstream-codec@3.1.7
  • eventstream-serde-browser@3.0.11
  • eventstream-serde-config-resolver@3.0.8
  • eventstream-serde-node@3.0.10
  • eventstream-serde-universal@3.0.10
  • fetch-http-handler@4.0.0
  • fs@1.1.1
  • hash-node@3.0.8
  • invalid-dependency@3.0.8
  • is-array-buffer@2.2.0
  • is-array-buffer@3.0.0
  • middleware-content-length@3.0.10
  • middleware-endpoint@3.2.1
  • middleware-host-header@3.686.0
  • middleware-logger@3.686.0
  • middleware-recursion-detection@3.686.0
  • middleware-retry@3.0.25
  • middleware-serde@3.0.8
  • middleware-stack@3.0.8
  • middleware-user-agent@3.687.0
  • move-file@1.1.2
  • node-config-provider@3.1.9
  • node-http-handler@3.2.5
  • once@1.1.2
  • promisify@1.1.3
  • property-provider@3.1.8
  • protocol-http@4.1.5
  • querystring-builder@3.0.8
  • querystring-parser@3.0.8
  • region-config-resolver@3.686.0
  • service-error-classification@3.0.8
  • sha256-browser@5.2.0
  • sha256-js@5.2.0
  • shared-ini-file-loader@3.1.9
  • signature-v4@4.2.1
  • smithy-client@3.4.2
  • supports-web-crypto@5.2.0
  • token-providers@3.686.0
  • types@3.6.0
  • types@3.686.0
  • url-parser@3.0.8
  • util-base64@3.0.0
  • util-body-length-browser@3.0.0
  • util-body-length-node@3.0.0
  • util-buffer-from@2.2.0
  • util-buffer-from@3.0.0
  • util-config-provider@3.0.0
  • util-defaults-mode-browser@3.0.25
  • util-defaults-mode-node@3.0.25
  • util-endpoints@2.1.4
  • util-endpoints@3.686.0
  • util-hex-encoding@3.0.0
  • util-locate-window@3.679.0
  • util-middleware@3.0.8
  • util-retry@3.0.8
  • util-stream@3.2.1
  • util-uri-escape@3.0.0
  • util-user-agent-browser@3.686.0
  • util-user-agent-node@3.687.0
  • util-utf8@2.3.0
  • util-utf8@3.0.0
  • util@5.2.0
requirements.txt pypi
  • kaggle *