Home / example runs
German credit (OpenML 31)
1000 loan applicants, 20 mixed numeric and categorical columns, predict bad credit.
Pre-computed on 2026-11-09 18:19 UTC on a developer laptop (Windows 11), CPU only. Scripted planner, no LLM, no network
calls during the run. Dataset: OpenML 31.
- Task
- binary, target
bad_credit, metricroc_auc, 1000 rows x 21 columns - Status
- done
- Chosen model
linear- Validation roc_auc
- 0.7913
- Reviewer verdict
- APPROVE
- Columns dropped for leakage
- none
- Steps
- 13
- Wall time
- 46.0 s (process start to report); agent clock 43.0 s. One run on a shared machine that was busy with other jobs: a timing sample, not a benchmark.
- Budgets
- soft wall 55 s (agent stops searching), hard limit 90 s (process killed), FLAML 15 s, 3 tuning trials
Agent steps
| # | tool | server | ok | latency (s) |
|---|---|---|---|---|
| 0 | profile_dataset | data-tools | yes | 0.09 |
| 1 | detect_leakage | data-tools | yes | 18.05 |
| 2 | decide_leakage | agent | yes | 0.00 |
| 3 | train_model | experiments | yes | 0.17 |
| 4 | train_model | experiments | yes | 0.48 |
| 5 | train_model | experiments | yes | 0.92 |
| 6 | train_model | experiments | yes | 3.73 |
| 7 | tune_model | experiments | yes | 2.02 |
| 8 | train_model | experiments | yes | 16.02 |
| 9 | compare_models | experiments | yes | 0.05 |
| 10 | review | agent | yes | 0.00 |
| 11 | explain_model | experiments | yes | 1.24 |
| 12 | report | agent | yes | 0.00 |