icdm-reproducibility
Use when strengthening reproducibility for an ICDM (IEEE International Conference on Data Mining) paper - seeds, configs, compute and data reporting, and an anonymized reproduction package that survives the Research Track's triple-blind regime while every detail fights for room inside the single 10-page IEEE all-inclusive cap.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill icdm-reproducibility --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 Reproducibility Make the mining result reproducible as *science*, under two ICDM-specific pressures: the Research Track is **triple-blind**, so the reproduction package cannot reveal identity, and the reporting all competes for space inside the **10-page all-inclusive cap**. Reproducibility at ICDM is not a separate checklist form (verify per edition); it is evidence that the discovery is real rather than a lucky configuration. ## What must be reproducible - The mining task setup: exact datasets, versions, preprocessing, splits, and how ground truth or injections were generated. - The method: hyperparameters, model selection procedure, the mechanism's knobs (e.g. sketch size, partition count), and the random seeds. - The evaluation: metrics, thresholds/cutoffs, variance estimation, and the hardware behind any timing claim. ## Reproducibility tiers | Tier | What a reviewer can do | How to reach it | |---|---|---| | Rerunnable | Re-execute your scripts and get your tables | Pinned deps, seeds, config files, entry script | | Rebuildable | Reconstruct the pipeline from description alone | Precise protocol in the paper + appendix | | Attested | Trust numbers that cannot be shared
- What must be reproducible
- Reproducibility tiers
- Configs as artifacts
- Triple-blind the package
- Report inside the page cap
- Vignette: the seed table that answered a review before it was written
- Output format
What does the icdm-reproducibility skill do?
Use when strengthening reproducibility for an ICDM (IEEE International Conference on Data Mining) paper - seeds, configs, compute and data reporting, and an anonymized reproduction package that survives the Research Track's triple-blind regime while every detail fights for room inside the single 10-page IEEE all-inclusive cap.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill icdm-reproducibility --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.