{"id":"M-1","type":"method","title":"Evidence tier definitions: the working constitution","created":"2026-07-13","status":"under active development","authors":["Upstream Zero"],"edges":[],"founderDecision":"FD-1","pubState":"published","body":"M-1 is the most important document we will publish: the\nworking definitions of the six evidence tiers. What qualifies a claim as\n**Narrated**, **Observed**, **Replicated**, **Causally Supported**,\n**Cross Evaluator**, or **Real World Corroborated**. How many runs\nconstitute replication. Which evaluators count as independent. What counts\nas real-world corroboration.\n\nThe tier *names* and their order are settled. The thresholds are not. They\nare a founder decision, under active development, and this page will hold\nthe versioned definitions when they exist. Until then, every claim on this\nsite is presented at Narrated, which requires no definition beyond honesty.","url":"/methods/M-1","machineUrl":"/objects/M-1","referencedBy":[{"from":"evidence-tier","rel":"depends-on"},{"from":"first-light","rel":"cites"}],"_meta":{"site":"Upstream Zero · Commercial Intelligence for AI-Mediated Commercial Evaluation","version":"0.1","note":"Claims are presented at their evidence tier; Narrated is the lowest. Verify by walking edges, not by trusting us."}}