icdm-experiments
Use when designing or auditing the empirical evaluation for an ICDM (IEEE International Conference on Data Mining) paper - mining-task definition, strong and fairly-tuned baselines, ablations that isolate the named mechanism, scalability curves that test scale claims, and discovery-validity checks that separate real findings from evaluation artifacts.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill icdm-experiments --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# ICDM Experiments Design the evaluation an ICDM reviewer will trust: a defined mining task, baselines tuned as carefully as your method, ablations that isolate the mechanism, a measured scale story, and a discovery-validity argument. ICDM's data-centric reviewers punish leaderboard-only wins and un-checkable discovery claims, and the whole evaluation must fit inside the 10-page all-inclusive cap. ## Define the mining task before the metric - State the task operationally: inputs, outputs, and what a correct answer is. "Anomaly detection" is a genre; "rank edges by anomalousness in a one-pass stream, evaluated against injected ground truth" is a task. - Fix the evaluation protocol — splits, negatives, thresholds, ranking cutoffs — before running anything, and describe it precisely enough to reproduce inside the page cap. ## The four evidence axes | Axis | Question it answers | Typical evidence | |---|---|---| | Quality | Is the mining result good on the task? | Ranking/accuracy vs baselines with variance | | Scale | Does the scale claim hold? | Latency/memory curves across data sizes | | Mechanism | Is the *named mechanism* the reason? | Ablations toggling exactly that component | |
- Define the mining task before the metric
- The four evidence axes
- Baselines and tuning symmetry
- Ablations that isolate the mechanism
- Test the scale claim, do not assert it
- Discovery validity: the ICDM instinct
- Vignette: an ablation that saved the claim
- Output format
What does the icdm-experiments skill do?
Use when designing or auditing the empirical evaluation for an ICDM (IEEE International Conference on Data Mining) paper - mining-task definition, strong and fairly-tuned baselines, ablations that isolate the named mechanism, scalability curves that test scale claims, and discovery-validity checks that separate real findings from evaluation artifacts.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill icdm-experiments --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Awesome-Journal-Skills, a repository with 909 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.