<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Rubrics on Cognaptus</title>
    <link>https://cognaptus.com/tags/rubrics/</link>
    <description>Recent content in Rubrics on Cognaptus</description>
    <generator>Hugo -- 0.145.0</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 13 Feb 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://cognaptus.com/tags/rubrics/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Thinking About Thinking: When LLMs Start Writing Their Own Report Cards</title>
      <link>https://cognaptus.com/blog/2026-02-13-thinking-about-thinking-when-llms-start-writing-their-own-report-cards/</link>
      <pubDate>Fri, 13 Feb 2026 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2026-02-13-thinking-about-thinking-when-llms-start-writing-their-own-report-cards/</guid>
      <description>RLCER shows how self-evolving rubrics can turn reinforcement learning from answer checking into process-level reasoning supervision.</description>
    </item>
    <item>
      <title>Grading the Doctor: How Health-SCORE Scales Judgment in Medical AI</title>
      <link>https://cognaptus.com/blog/2026-02-02-grading-the-doctor-how-healthscore-scales-judgment-in-medical-ai/</link>
      <pubDate>Mon, 02 Feb 2026 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2026-02-02-grading-the-doctor-how-healthscore-scales-judgment-in-medical-ai/</guid>
      <description>Health-SCORE shows how reusable, adaptive rubrics can turn expert medical judgment into a scalable control layer for healthcare LLMs.</description>
    </item>
  </channel>
</rss>
