The reporting rule we hold ourselves to
Every experiment report must preserve its question, controls, correctness checks, negative results, limitations and the decision that followed.
A research log is useful only when an awkward result cannot be polished out of it. ShiftWing therefore uses a fixed reporting rule for every experiment.
The required record
- The hypothesis or research question.
- The controls and frozen comparison.
- The method and reproduction path.
- The correctness checks.
- The results, including negative results.
- The limitations.
- The decision and next step.
Why the decision belongs in the report
Measurements without a decision invite later reinterpretation. Recording what changed—and what did not—connects evidence to engineering while leaving a trail that can be challenged.
Cite this page: Dingal AI Research. “The reporting rule we hold ourselves to”. 24 August 2026.
Related
LocalForge: code review that never leaves your machine
LocalForge is a private local reviewer designed to keep repository context, inference and disagreement on the computer where the code lives.
A negative result worth publishing
A larger target missed the threshold written down before the run, so the release decision stayed negative even though parts of the result looked promising.
Why frontier AI has to run on the hardware people own
Frontier capability matters most when regular people can use it without surrendering their work, context or control to a remote service.