README.md

metadata

title: Sphragis Leaderboard
emoji: 🥇
colorFrom: green
colorTo: indigo
sdk: static
app_file: index.html
pinned: true
license: apache-2.0
short_description: Leaderboard for Ancient Greek author attribution
fullWidth: true
datasets:
  - Urdatorn/sphragis
tags:
  - leaderboard
  - authorship-attribution
  - ancient-greek

Sphragis Leaderboard

A statically generated SvelteKit + TypeScript leaderboard for the four Sphragis Ancient Greek sentence-based authorship-attribution tasks. The UI uses Svelte 5 runes and runs without Python, CPU, or GPU Space hardware.

Scores and per-author held-out accuracies are typed in src/lib/data.ts. Select a model row to compare its available task accuracies and confusion matrices for every author. The trivial baseline always predicts the most frequent author in the relevant training split; test labels never determine its prediction. The page has separate result tables for human-annotated Sphragis and the Sphragis-Metre track. The initial Sphragis-Metre entry is a text-only GreBERTa baseline intended as the foundation for later metre and syntax ablations.

Install and run locally:

npm ci
npm run dev

The table interaction and visual architecture adapt patterns from the Apache-2.0-licensed embeddings-benchmark/leaderboard-frontend. See NOTICE for attribution.