about.html

<!doctype html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"><title>About · CausalVideoGroup</title><link rel="stylesheet" href="styles/main.css"></head><body>
<header class="site-header"><div class="nav-wrap"><a class="brand" href="./">CausalVideoGroup</a><nav class="site-nav" aria-label="Primary navigation"><a href="projects/">Projects</a><a href="discussions/">Discussions</a><a href="people/">People</a><a aria-current="page" href="about.html">About</a></nav></div></header>
<main><header class="page-header"><p class="eyebrow">About</p><h1>How video generators preserve state and respond to intervention.</h1><p class="lede">CausalVideoGroup studies how video generators maintain scene state over long horizons and how their outputs change in response to control signals or edits.</p></header><article class="prose">
<h2>What this site contains</h2><p>The project archive presents public research questions, methods, evidence, and limitations. The discussion archive contains the background material prepared before each meeting and the technical conclusions recorded afterward.</p>
<h2>Why discussions are public</h2><p>Paper summaries are prepared before the meeting so that meeting time can be used to examine assumptions, compare explanations, identify failure cases, and design experiments. Only material approved for public release appears here; unpublished plans and submission-sensitive results remain in private group storage.</p>
<div class="callout"><strong>Core principle:</strong> every discussion should identify a central claim, a hidden assumption, a failure boundary, a connection to our research, and a concrete experiment.</div>
</article></main><footer class="site-footer"><div class="site-footer-inner"><span>© CausalVideoGroup</span><a href="contribute.html">Contribute</a></div></footer></body></html>