Lessons

1Ablations need controls that answer the explanation35 min read

Use a two-factor comparison to identify an interaction.

  • →Design ablations that distinguish mechanisms from confounds
  • →Use factorial comparisons to detect interactions
Read lesson
2Equal steps may not mean a fair resource comparison35 min read

Select and report a resource comparison that matches the claim.

  • →Compare methods under explicit resource constraints
Read lesson
3Keep the evaluation separate from the method's memory35 min read

Identify contamination paths and design a cleaner benchmark.

  • →Construct an evaluation resistant to contamination and leakage
Read lesson
4A negative result can sharpen the next question35 min read

Distinguish absence of evidence, practical equivalence, and a failed mechanism.

  • →Interpret a negative result and choose a next study
  • →Document limitations and excluded runs transparently
Read lesson

Skills in this course

  1. 01Design ablations that distinguish mechanisms from confoundsDesign ablations that distinguish mechanisms from confounds.
  2. 02Compare methods under explicit resource constraintsCompare methods under explicit resource constraints.
  3. 03Construct an evaluation resistant to contamination and leakageConstruct an evaluation resistant to contamination and leakage.
  4. 04Interpret a negative result and choose a next studyInterpret a negative result and choose a next study.
  5. 05Use factorial comparisons to detect interactionsUse factorial comparisons to detect interactions.
  6. 06Document limitations and excluded runs transparentlyDocument limitations and excluded runs transparently.