add paper

Author: kadubon

llms-full.txt

@@ -48,13 +48,14 @@ The primary machine-readable publication corpus is `works.html`, where each item
 
 ## Corpus Snapshot (works.html / feed.xml)
 
-- Publication entries in Works list: 192.
-- Date span of listed works: 2025-07-25 to 2026-04-01.
-- Latest listed work (2026-04-01): [Constitutional Observable Invention without Meta-Evaluators](https://doi.org/10.5281/zenodo.19363526)
+- Publication entries in Works list: 193.
+- Date span of listed works: 2025-07-25 to 2026-04-03.
+- Latest listed work (2026-04-03): [When Should a Local Agent Act, Assist, Verify, Withdraw, or Exit? A Certified Local Micro-Theory of Open-Task Participation](https://doi.org/10.5281/zenodo.19394600)
 - Earliest listed work (2025-07-25): [Computational Autopoiesis: A New Architecture for Autonomous AI](https://doi.org/10.5281/zenodo.16416998)
 
 ## Most Recent Works
 
+- 2026-04-03: [When Should a Local Agent Act, Assist, Verify, Withdraw, or Exit? A Certified Local Micro-Theory of Open-Task Participation](https://doi.org/10.5281/zenodo.19394600)
 - 2026-04-01: [Constitutional Observable Invention without Meta-Evaluators](https://doi.org/10.5281/zenodo.19363526)
 - 2026-03-31: [Observer-Modifying Contagion on Networks](https://doi.org/10.5281/zenodo.19342966)
 - 2026-03-29: [Classification-Induced Cognitive Drift](https://doi.org/10.5281/zenodo.19306514)

works.html

@@ -71,6 +71,26 @@
         "https://github.com/kadubon"
       ],
       "publication": [
+        {
+          "@type": "ScholarlyArticle",
+          "name": "When Should a Local Agent Act, Assist, Verify, Withdraw, or Exit? A Certified Local Micro-Theory of Open-Task Participation",
+          "genre": "Preprint",
+          "url": "https://doi.org/10.5281/zenodo.19394600",
+          "datePublished": "2026-04-03",
+          "author": [
+            {
+              "@type": "Person",
+              "name": "K Takahashi"
+            }
+          ],
+          "isPartOf": {
+            "@type": "Periodical",
+            "name": "Zenodo"
+          },
+          "citation": "K Takahashi (2026-04-03). When Should a Local Agent Act, Assist, Verify, Withdraw, or Exit? A Certified Local Micro-Theory of Open-Task Participation. Zenodo. https://doi.org/10.5281/zenodo.19394600",
+          "abstract": "This preprint develops a certified local micro-theory of open-task participation in agent societies. It formalizes when an authenticated local agent should act, assist, verify, withdraw, or exit under public evidence, certified uncertainty, attribution, and implementability constraints.",
+          "keywords": "multi-agent systems, local agent participation, open-task participation, decentralized decision making, auditable AI, agent verification, open-world agents, human-AI coordination, verifier portfolios, authenticated snapshots, certified uncertainty, agentic AI, task allocation, decentralized control, local micro-theory, participation governance"
+        },
         {
           "@type": "ScholarlyArticle",
           "name": "Constitutional Observable Invention without Meta-Evaluators",
@@ -3958,6 +3978,27 @@ <h1>
        Machine-readable endpoints: <a href="https://kadubon.github.io/github.io/feed.xml">RSS feed</a>, <a href="https://kadubon.github.io/github.io/CITATION.cff">CITATION.cff</a>, <a href="https://kadubon.github.io/github.io/robots.txt">robots.txt</a>, and <a href="https://kadubon.github.io/github.io/sitemap.xml">sitemap.xml</a>.
       </p>
       <ol class="publication-list">
+       <li>
+        <div class="publication-item">
+         <h3>
+          When Should a Local Agent Act, Assist, Verify, Withdraw, or Exit? A Certified Local Micro-Theory of Open-Task Participation
+         </h3>
+         <p>
+          <span class="publication-meta">
+           Preprint | Published: 2026-04-03
+          </span>
+          <a href="https://doi.org/10.5281/zenodo.19394600" target="_blank">
+           DOI: 10.5281/zenodo.19394600
+          </a>
+         </p>
+         <p class="publication-abstract">
+          Abstract: This preprint develops a certified local micro-theory of open-task participation in agent societies. It formalizes when an authenticated local agent should act, assist, verify, withdraw, or exit under public evidence, certified uncertainty, attribution, and implementability constraints.
+         </p>
+         <p class="publication-keywords">
+          Keywords: multi-agent systems, local agent participation, open-task participation, decentralized decision making, auditable AI, agent verification, open-world agents, human-AI coordination, verifier portfolios, authenticated snapshots, certified uncertainty, agentic AI, task allocation, decentralized control, local micro-theory, participation governance
+         </p>
+        </div>
+       </li>
        <li>
         <div class="publication-item">
          <h3>