domains / families / research / kdd-experiments

kdd-experiments

separate

Use when designing or auditing the empirical section of a KDD paper, where evidence combines quality deltas with scalability and efficiency measurements, temporal-leakage-safe splits, mechanism-isolating ablations, tuning-symmetric baselines, and, for the ADS track, post-launch measurement design that survives the desk check.

When to use

• designing empirical sections for KDD papers
• auditing KDD paper evidence
• designing temporal-leakage-safe splits
• creating mechanism-isolating ablations
• ensuring tuning-symmetric baselines
• designing post-launch measurement for ADS track
• auditing data hygiene and leakage
• planning four-axis evidence (quality, scale, efficiency, mechanism)

When not to use

• writing theoretical proofs
• designing non-KDD conference experiments
• general machine learning model training
• software engineering code review

Skill page

Source