<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <id>urn:uuid:a20ea89f-3e25-5d6e-a6ab-2958989cb3b0</id>
  <title>SocioLens — RO-LD06-06: How many published AI evaluations outside medicine can no longer be repeated?</title>
  <subtitle>New versions of this research opportunity and changes to the claims it rests on.</subtitle>
  <link rel="self" type="application/atom+xml" href="https://sociolens-web.pages.dev/opportunities/ro-ld06-06/feed.xml"/>
  <link rel="alternate" type="text/html" href="https://sociolens-web.pages.dev/opportunities/ro-ld06-06/"/>
  <updated>2026-10-15T00:00:00Z</updated>
  <author><name>SocioLens</name></author>
  <entry>
    <id>urn:uuid:e071e332-1598-553f-b0d0-93d5186e5ed9</id>
    <title type="text">New research opportunity: RO-LD06-06 — How many published AI evaluations outside medicine can no longer be repeated?</title>
    <link rel="alternate" type="text/html" href="https://sociolens-web.pages.dev/opportunities/ro-ld06-06/v1/"/>
    <updated>2026-10-15T00:00:00Z</updated>
    <summary type="text">Among published studies in NLP, the social sciences and education research that evaluate closed language models through an API, what share used a model version that has since been retired or is due to retire, and how many of a sample can still be re-run to reproduce their main result?</summary>
  </entry>
</feed>
