<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Structured Extraction on 67AI Lab</title>
    <link>https://67ailab.com/tags/structured-extraction/</link>
    <description>Recent content in Structured Extraction on 67AI Lab</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 12 Nov 2026 14:10:00 +0000</lastBuildDate>
    <atom:link href="https://67ailab.com/tags/structured-extraction/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Turning Scan Reports into JSON Is Solved. Spotting Contradictions Isn&#39;t</title>
      <link>https://67ailab.com/posts/spark-eval-05-l2-report-structuring/</link>
      <pubDate>Thu, 12 Nov 2026 14:10:00 +0000</pubDate>
      <guid>https://67ailab.com/posts/spark-eval-05-l2-report-structuring/</guid>
      <description>&lt;p&gt;Imaging departments hold years of free-text scan reports. Registries, audits&#xA;and research projects need the same reports as structured fields: which&#xA;tracer, how much activity, how long after injection, and for each lesion its&#xA;site, side, size and uptake.&lt;/p&gt;&#xA;&lt;p&gt;Doing that by hand is slow, and the reports often can&amp;rsquo;t leave the hospital&#xA;network. Task L2 asks whether a model on a desk-side box can do the conversion&#xA;unattended, and whether it notices when a report contradicts itself.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
