index.html

<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Chronologic</title>
<style>
  body { max-width: 42rem; margin: 2rem auto; padding: 0 1rem; font: 16px/1.55 Georgia, serif; color: #222; background: #fdfcf8; }
  a { color: #6b4e16; }
  @media (prefers-color-scheme: dark) { body { color: #ddd; background: #1b1a17; } a { color: #d9b36c; } }
</style>
</head>
<body>
<h1>Chronologic</h1>
<p><strong>Chronologic-EN</strong> measures whether language models can respond like
English-language writers placed in specific social and historical contexts between 1831
and 1930: 866 questions drawn from 187 period sources, each with a metadata frame naming
the context.</p>
<ul>
  <li><a href="https://github.com/Historical-AI-Lab/Chronologic-EN">Code on GitHub</a></li>
  <li><a href="https://huggingface.co/chronologic/chronologic-date-deberta">chronologic-date-deberta</a></li>
  <li><a href="https://huggingface.co/chronologic/chronologic-authenticity-deberta">chronologic-authenticity-deberta</a></li>
  <li><a href="https://huggingface.co/datasets/chronologic/Chronologic-EN-1.0">Chronologic-EN-1.0</a> (controlled access)</li>
</ul>
<p>Contact: Ted Underwood, University of Illinois Urbana-Champaign, tunder@illinois.edu.</p>
</body>
</html>