Micro-Stoppage Mining
Recover short stops that never reach the downtime threshold from PLC state changes and line-speed signals. Higher event recall is better.
Metric
Recall (micro-stops)
Baseline
Idle-Wait Opportunity Model
Submissions
21
Updated
2026-06-22
Leaderboard
| Rank | Submitter | Model | Type | Score | Date |
|---|---|---|---|---|---|
| 1 | p.nakamura | statechange-tab | Research implementation | 0.871 | 2026-06-22 |
| 2 | matereal | idle-wait-opportunity-model | Reference model | 0.840 | 2026-06-16 |
| 3 | a.costa | gap-detector | Baseline model | 0.802 | 2026-06-08 |
| 4 | l.zhang | rule-baseline | Baseline model | 0.731 | 2026-05-30 |
Entries are reference and research submissions on the open split. Scores are illustrative and require plant-specific validation for industrial use.
Task definition
Evaluation metric
Recall (micro-stops)
Submission rules
- 1
Use the official train/test split.
- 2
Report event recall and cluster purity on the test split.
- 3
Include false-positive rate in the submission notes.
Discussion
- s.Question
s.iyer
ML researcher · 2d
Are ensemble submissions allowed, or single-model only? Worth stating explicitly in the rules.
7 - maComment
matereal
Maintainer · 2d
Ensembles are allowed if reproducible from the submitted artifacts. We'll clarify in the next rules revision.
5
Contribute to open industrial AI
Browse open models, datasets, benchmarks, and process maps, or start a discussion. Customer plant data and private deployments stay confidential.