domains / families / research / aaai-experiments

aaai-experiments

separate

Use when designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation, AI-for-Social-Impact and alignment/safety evidence, compute and cost reporting, and reproducibility-checklist alignment for Phase-1 survival.

When to use

• designing AAAI experiments
• auditing AAAI experiments
• checking baselines
• checking ablations
• checking statistical significance
• checking robustness
• checking human evaluation
• checking reproducibility-checklist alignment

When not to use

• adding new results during rebuttal
• relying on closed APIs without reproducible substitutes

Skill page

Source