project-context-v2listed

# Project Context V2 Maintain research memory as a traceable chain from question to evidence to claim. Preserve measurements and provenance before interpretation so a later correction can replace the analysis without destroying the record. ## Non-negotiable rules 1. Treat evidence as more durable than interpretation. When space is limited, remove repetitive prose before removing key tables, sample counts, protocols, baselines, uncertainty, failure cases, or artifact paths. 2. Never silently rewrite history. Mark a result or claim `superseded` or `invalidated`, state why, and link its replacement. 3. Separate four epistemic classes: - **Evidence**: observed values and artifacts. - **Observation**: description directly supported by evidence. - **Interpretation**: causal or mechanistic explanation that may be wrong. - **Decision**: action chosen under stated evidence, constraints, and risk. 4. Never convert missing, incomparable, or failed measurements into conclusions. Use `—`, `not measured`, `failed`, or `incomparable` explicitly. 5. Keep raw or per-sample data in machine-readable artifacts when available. Preserve the decisive subset as Markdown tables so the project remains understandable if outputs are unavailable. 6. Record negative results, bugs, leakage, protocol changes, and counterexamples with the same care as improvements. 7. Do not claim causality from correlation, ablation-free comparisons, changed protocols, or cherry-picked samples. 8. Read before