{
 "@context": "https://schema.org",
 "@type": "Claim",
 "@id": "https://wulfkaal.github.io/positions/2026-09-28-001",
 "identifier": "kaal:position:2026-09-28-001",
 "additionalType": "https://wulfkaal.github.io/positions/schema.json#AffirmedPositionClaim",
 "name": "Completion Requires Independent Specification Authority",
 "text": "Completion is an authority question. The benchmark separates an agent's completion claim from authoritative state. Across seven models, formal completion claims exceeded official evaluator passes by 28.7 to 37.9 percentage points. This evidence extends the requirement for execution-time artifacts that qualified providers can evaluate. It does not establish that every necessary data boundary or attribution rule was enforced. Those findings are limited to the tested software tasks, models, and evaluators.",
 "author": {
  "@type": "Person",
  "name": "Wulf A. Kaal",
  "identifier": "https://orcid.org/0009-0008-7840-1847"
 },
 "datePublished": "2026-09-28",
 "dateModified": "2026-09-28",
 "creativeWorkStatus": "Affirmed",
 "responseType": "extension",
 "keywords": [
  "compliance",
  "disclosure",
  "institutional-design"
 ],
 "scope_conditions": [
  "enterprise and regulatory verification of sovereign runtimes"
 ],
 "currentDebate": {
  "name": "Who Holds the Pen? Let Specifications, Not Agents, Sign Off",
  "url": "https://arxiv.org/abs/2609.29921v1"
 },
 "extends": {
  "identifier": "kaal:claim:7314479-048",
  "url": "https://wulfkaal.github.io/claims/7314479-048",
  "citation": "Wulf A. Kaal, Institutional Requirements for Sovereign Local Agent Runtimes (2026). SSRN: https://ssrn.com/abstract=7314479",
  "paper": "Wulf A. Kaal, Institutional Requirements for Sovereign Local Agent Runtimes (2026). SSRN: https://ssrn.com/abstract=7314479",
  "authors": [
   "Wulf A. Kaal"
  ],
  "year": "2026",
  "ssrn": null,
  "source_pdf_sha256": "debace24a155ae924a155b1fafe98856d98cf83689feff2f87a32f1c06171ce6"
 },
 "isBasedOn": [
  {
   "@id": "https://wulfkaal.github.io/claims/7314479-048"
  },
  {
   "@type": "CreativeWork",
   "name": "Who Holds the Pen? Let Specifications, Not Agents, Sign Off",
   "url": "https://arxiv.org/abs/2609.29921v1"
  }
 ],
 "batch_id": "kaal-weekly-research:2026-09-28:daily-001",
 "review_provenance": "https://wulfkaal.github.io/positions-src/2026-09-28-compound-growth-kaal-weekly-research-2026-09-28-daily-001.json",
 "publicationStatus": "public",
 "recordTypeNote": "Dated commentary position extending a scholarly corpus claim. Not a verbatim claim extracted from the paper.",
 "isPartOf": {
  "@id": "https://wulfkaal.github.io/positions/index.json"
 },
 "version": "1.0",
 "canonical_url": "https://wulfkaal.github.io/positions/2026-09-28-001",
 "canonicalForm": "https://wulfkaal.github.io/positions/2026-09-28-001.md",
 "candidateId": "kaal:candidate:094a7909aedcc3e8b7918d5b7278003caa1995060d3fba12ca1b16e593fb81b0",
 "evidenceLevel": "authoritative_abstract",
 "reviewTier": "independent evidence-first compound-growth review",
 "mappingConfidence": null,
 "mappingAmbiguous": false,
 "mappingMethod": "independent one-to-one proposition and mechanism review",
 "mappingWhyRelevant": "The paper directly measures the gap between agent completion claims and official evaluator passes, then separates agent proposals from specification-governed state established by qualified evidence. This extends the protected requirement for a third-party-evaluable execution artifact without establishing every policy, data-boundary, or attribution property named in the claim.",
 "sourceProvenance": {
  "canonicalUrl": "https://arxiv.org/abs/2609.29921v1",
  "retrievedAt": "2026-09-28T12:38:00.830Z",
  "sourceContentSha256": "8299e602f5131e7e2afc53c5c62d4f2d46fd0e58814a087d047f262f53f0d6e5",
  "sourceProposition": "Across seven tested models, agent completion claims materially exceeded official evaluator passes, supporting a separate specification authority that accepts only qualified evidence before completion becomes authoritative.",
  "sourcePropositionSha256": "7f9b25cb6a7add45f520839e1acedca8e596872725286bdc8e9c0dbf5b3c675f",
  "normalizedWorkId": "arxiv:2609.29921",
  "sourceVersion": "v1",
  "exactEvidenceQuote": "Across seven models, only 79.6%--86.4% are satisfied, while completion-claim rates exceed official evaluator pass rates by 28.7--37.9 percentage points.",
  "exactEvidenceQuoteSha256": "ae42140a0a0bf9e1586a316116c0146438915042b33a179bcd850f5ac4815ee7",
  "claimMappings": [
   {
    "claimId": "kaal:claim:7314479-048",
    "confidence": null,
    "method": "independent one-to-one review",
    "whyRelevant": "The paper directly measures the gap between agent completion claims and official evaluator passes, then separates agent proposals from specification-governed state established by qualified evidence. This extends the protected requirement for a third-party-evaluable execution artifact without establishing every policy, data-boundary, or attribution property named in the claim.",
    "ambiguous": false
   }
  ]
 },
 "userAffirmation": "Standing scholarly-growth preauthorization bound to 160a9893b1aa39c8b4da4e67ab4b60c6dd4a83d31b2fd0d5bac4dee8029133b5; publication remains conditional on successful projection, deployment, and live-byte verification.",
 "publicIdentitySha256": "094a7909aedcc3e8b7918d5b7278003caa1995060d3fba12ca1b16e593fb81b0",
 "sha256": "4035cd50b58ea12b986586e102a699d469f57e1b9633f476f2f44a821004f05a"
}