| name | sci-evidence-discussion |
| description | Use when converting experiment tables, logs, figures, measurements, HIL outputs, simulations, or appendix data into results, discussion, limitations, or contribution text |
SCI Evidence To Discussion
Overview
Turn measured evidence into manuscript discussion without overclaiming.
Core principle: separate observation, interpretation, and claim strength.
Evidence Table
Use or update the project's experiment evidence table when present. Otherwise record the fields below in the response.
Record:
- metric name and unit
- source file/log/table
- sample count or run scope
- baseline/reference definition
- measurement environment
- evidence level
- caveats and exclusions
Discussion Pattern
- Observation: what the data show.
- Mechanism: why this may happen, only if supported.
- Scope: where the result applies.
- Boundary: what the result does not prove.
- Next evidence: what would strengthen the claim.
Output
- results paragraph
- discussion paragraph
- limitation sentence if needed
- claim-evidence mapping row
Common Mistakes
- Confusing detector-only latency with end-to-end agent latency.
- Treating manual power-meter screen readings as calibrated power traces.
- Moving Paper 2/downlink results into Paper 1 without scope separation.
- Reporting steady-state results as all-phase behavior.
