update descriptions and casing

Author: justinchiu-cohere

index.html

@@ -49,8 +49,8 @@ <h1>Refactoring Codebases through Library Design</h1>
 		<nav>
 			<ul>
 				<li><a href="https://arxiv.org/abs/2506.11058" target="_blank" class="nav-button"><i class="ai ai-arxiv"></i> arXiv</a></li>
-				<li><a href="https://github.com/code-refactor/minicode" target="_blank" class="nav-button"><i class="fa-brands fa-github"></i> MINiCODE</a></li>
-				<li><a href="https://github.com/code-refactor/Librarian" target="_blank" class="nav-button"><i class="fa-brands fa-github"></i> LIBRARIAN</a></li>
+				<li><a href="https://github.com/code-refactor/minicode" target="_blank" class="nav-button"><i class="fa-brands fa-github"></i> Minicode</a></li>
+				<li><a href="https://github.com/code-refactor/Librarian" target="_blank" class="nav-button"><i class="fa-brands fa-github"></i> Librarian</a></li>
 				<li><a href="#citation" class="nav-button"><i class="fa-solid fa-quote-right"></i> Citation</a></li>
 			</ul>
 		</nav>
@@ -73,10 +73,10 @@ <h2 id="abstract">Abstract</h2>
 		<h2 id="contributions">Key Contributions</h2>
 		<div class="contributions-grid">
 			<a href="https://github.com/code-refactor/Librarian" target="_blank" class="contribution-box">
-				<p><strong>LIBRARIAN</strong> is a novel sample-and-rerank method that refactors codebases into reusable libraries. It clusters code to find shared structures, samples refactorings, and ranks them by simplicity and correctness. It achieves 1.6-2x better compression than top code agents while boosting accuracy.</p>
+				<p><strong>Librarian</strong> is a novel sample-and-rerank method that refactors codebases into reusable libraries. It clusters code to find shared structures, samples refactorings, and ranks them by simplicity and correctness. It achieves 1.6-2x better compression than top code agents while boosting accuracy.</p>
 			</a>
 			<a href="https://github.com/code-refactor/minicode" target="_blank" class="contribution-box">
-				<p><strong>MINiCODE</strong> is a new benchmark for testing code agents' ability to create unified libraries from multiple code sources. It emphasizes open-ended design, verifiable correctness via unit tests, and large-context synthesis. It spans competition coding and synthesized repositories, filling gaps in existing benchmarks.</p>
+				<p><strong>Minicode</strong> is a benchmark for testing code agents' ability to create unified libraries from multiple code sources, such as competition coding programs and Python repositories. It requires open-ended design and large-context understanding in order to craft simple libraries.</p>
 			</a>
 		</div>
 	</section>