{"id":"D-1","type":"deliverable","title":"Evaluation Observation Report (specification draft)","created":"2026-07-13","status":"specification draft, no example exists yet","authors":["Upstream Zero"],"edges":[],"pubState":"published","body":"The artifact a diagnostic engagement produces. Contents specification:\n\n- **Observation log:** what evaluators said and recommended, verbatim,\n  instrument-stamped (evaluator, version, access mode, date)\n- **Sampling conditions:** N, prompt variants, repeats, variance; printed\n  in the report body, not an appendix\n- **Requirement coverage read:** which category requirements your\n  representations substantiate, fail to substantiate, or leave invisible\n- **Confidence breakdown map:** where evaluator narration about you\n  hedges, contradicts itself, or requests evidence\n- **Declared limits:** what this report cannot tell you (mechanism;\n  persistence across model updates)\n\n**What it does not contain:** rankings promises, optimization tricks,\ncompetitor disparagement, or any number we haven't earned the digits of.\n\n**Example status:** none yet. When a real (consented, redacted) example\nexists it will be linked here; an illustrative mock would be rendered in\nthe SPECIMEN register, never in the visual language of real findings.","url":"/deliverables/D-1","machineUrl":"/objects/D-1","referencedBy":[{"from":"ENG-1","rel":"produces"},{"from":"ENG-2","rel":"produces"}],"_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."}}