• User's experiment is not working or producing unexpected results
• User needs help diagnosing why a method fails on certain data
• User wants to organize their experiment process with structured logging
• User asks about debugging research code or iterating on approaches
• User mentions "experiment debugging", "why doesn't this work", "experiment log", "results are wrong"

This skill is typically loaded from within

experiment-pipeline

when a stage attempt fails. After debugging, return to the pipeline's stage-gate structure to continue. Can also be used standalone for any experiment debugging.

1. Slow progress: Running random experiments without understanding failure causes
2. Wasted time: Abandoning good approaches because activation tricks were missed

• Simplify the task: Reduce data complexity, relax the task setting, add more supervision, use easier inputs
• Remove your changes: Start from the baseline method and remove your algorithmic improvements one by one

• Add ONE factor at a time (more complex data, one algorithmic change, one constraint)
• Find the single factor that causes failure
• The more atomic the identified cause, the more useful the diagnosis

1. List possible explanations for why this factor causes failure
2. Rank by likelihood (based on your understanding and literature)
3. Design targeted experiments to verify or eliminate each hypothesis
4. Confirm the actual cause experimentally — don't rely on intuition alone

• Search for techniques that address this specific cause (use your literature tree from the

  research-ideation

  skill)
• Design a fix that targets the confirmed cause, not the surface symptom
• Verify the fix works on the original failure cases
• Check that the fix doesn't break previously working cases

1. Change only one variable at a time: If you change two things and it works, you don't know which one fixed it. If you change two things and it doesn't work, you don't know which one is wrong. Single-variable changes are slower per experiment but faster overall.
2. Fast iteration requires effective experiments, not more experiments: Blind experimentation makes things worse. One well-designed diagnostic experiment is worth ten random trials.
3. Some great techniques don't work alone: They need specific activation tricks — learning rate schedules, initialization schemes, data preprocessing steps. Don't discard a technique after one failed attempt. Check related papers for their undisclosed tricks.
4. Check related papers for their tricks: Papers solving similar technical challenges often have critical implementation details buried in supplementary material or code. These tricks can make the difference between a technique working or failing.
5. "Once you've ruled out the impossible, whatever remains must be true": Systematic elimination beats intuition. When debugging, explicitly list ALL possible causes, then eliminate them one by one with targeted experiments.

Cross-cycle learning: If using

experiment-pipeline

, your experiment logs feed into

evo-memory

's ESE (Experiment Strategy Evolution) mechanism. Tag reusable strategies with

[Reusable]

so ESE can extract them for future cycles.

experiment-pipeline

• Confirmed cause of failure (from Step 4)
• Proposed fix and its verification status (from Step 5)
• Updated experiment log entry