<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>MNSTRY.org · Provenance at machine scale</title>
    <link>https://mnstry.org/topics/provenance/</link>
    <description>A machine-assembled corpus fails in ways a human-assembled one does not,
quietly and at the joins, and the corrections are all forms of writing
things down before they are needed. These articles run from our own
cleanup ledger through the marking of machine-written material, the
proof of deletion, the reconstruction of a decision, and the one sentence
that keeps a load-bearing choice from being tidied away.</description>
    <item>
      <title>The contaminated corpus</title>
      <link>https://mnstry.org/writing/the-contaminated-corpus/</link>
      <guid isPermaLink="true">https://mnstry.org/writing/the-contaminated-corpus/</guid>
      <description>What a cleanup of our own machine-built research corpus found at the joins, and why the first audit of the damage was wrong in the same way the damage was. The canonical treatment of seam failure in assembled knowledge.</description>
      <pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate>
    </item>
    <item>
      <title>Born marked</title>
      <link>https://mnstry.org/writing/born-marked/</link>
      <guid isPermaLink="true">https://mnstry.org/writing/born-marked/</guid>
      <description>How a machine-assembled corpus quarantines its own output by default, why every promotion is a human act, and why safe to load into a model and safe to show a person are different questions with different gates.</description>
      <pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate>
    </item>
    <item>
      <title>Destroy the key</title>
      <link>https://mnstry.org/writing/destroy-the-key/</link>
      <guid isPermaLink="true">https://mnstry.org/writing/destroy-the-key/</guid>
      <description>How an append-only history and an enforceable right to erasure stop being in conflict, and what the technique costs in honesty. The canonical treatment of cryptographic erasure.</description>
      <pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate>
    </item>
    <item>
      <title>Reconstruction, not explanation</title>
      <link>https://mnstry.org/writing/reconstruction-not-explanation/</link>
      <guid isPermaLink="true">https://mnstry.org/writing/reconstruction-not-explanation/</guid>
      <description>Why accountability for an automated decision means reconstructing the state of the machine at the moment it decided, and why the opacity that actually defeats an audit is operational rather than neural.</description>
      <pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate>
    </item>
    <item>
      <title>Removal conditions</title>
      <link>https://mnstry.org/writing/removal-conditions/</link>
      <guid isPermaLink="true">https://mnstry.org/writing/removal-conditions/</guid>
      <description>Why a rationale does not survive contact with the next maintainer, and what a removal condition adds that the standard architecture decision record leaves out.</description>
      <pubDate>Mon, 03 Aug 2026 00:00:00 GMT</pubDate>
    </item>
  </channel>
</rss>
