Run demo-0bb3e6d5db on wine-quality: planner=scripted, llm_mode=none (scripted, no LLM)

Data story

1599 rows, 12 columns.

Leakage findings

severitytypecolumns
lowduplicate_rows
lowlabel_noisequality

Leaderboard

Validation rmseflaml0.578rf0.5802hgb0.6069hgb0.6134linear0.653dummy0.8073

Top features (permutation importance, held-out slice)

Score drop when shuffled (rmse)alcohol0.1565sulphates0.08901volatile_acidity0.04546total_sulfur_dioxide0.03341citric_acid0.009773residual_sugar0.009539pH0.008972free_sulfur_dioxide0.007754chlorides0.006756fixed_acidity0.005614

Reviewer: APPROVE

Step latency

Seconds per stepprofile_dataset0.11detect_leakage3.891decide_leakage0train_model0.063train_model0.11train_model0.75train_model3.766tune_model3.047train_model17.02compare_models0.094review0explain_model2.75

Model card

# Model card: rf-708924da5c

- Task: regression, metric rmse, target `quality`
- Family: rf; validation rmse: 0.5802 (seeded holdout of the training file)
- Dropped columns (leakage/ID policy): none
- Unresolved leakage findings: 0
- Planner: scripted; LLM mode: none; seed 0
- Intended use: tabular prediction on data like the training file. Not validated for distribution shift. Holdout scores are optimistic relative to the final test score.