Self-Sensing Concrete Assistant
An integrated intelligence suite for the Inframat-X Lab. Use the Predictor to estimate piezoresistive stress sensitivity based on 224 experimental records, or consult the Research Assistant to synthesize findings from our 130-paper technical corpus. All synthesized answers include bidirectional citations (e.g., [18], [71]) mapped directly to the laboratory’s verified source index.
2-probe includes contact resistance; 4-probe isolates material resistivity.
🟢 Loaded model: stress_gf_xgb.joblib
- Pipeline: ColumnTransformer → (RobustScaler + OneHot) → XGBoost
- Target: Stress GF (MPa-1) on original scale (model may train on log1p; saved flag used at inference).
- Missing values are safely imputed per-feature.
- Trained columns:
Filler 1 Type, Filler 1 Diameter (µm), Filler 1 Length (mm), Conductive Filler Conc. (wt%), Filler 1 Dimensionality, Filler 2 Type, Filler 2 Diameter (µm), Filler 2 Length (mm), Filler 2 Dimensionality, Specimen Volume (mm3), Probe Count, Probe Material, W/B, S/B, Gauge Length (mm), Curing Condition, Number of Fillers, Drying Temperature (°C), Drying Duration (hr), Loading Rate (MPa/s), Modulus of Elasticity (GPa), Current Type, Applied Voltage (V)
Using local folder papers/ — 100 PDF(s) indexed. Upload more PDFs and reload the Space to expand coverage. Answers cite short document codes such as S71, S92.
Literature Q&A
Hybrid retrieval with diversity. Answers carry inline short-code citations (e.g., (S92), (S71)).
Upload your gold.csv and compute metrics against the app logs.
🧪 Run Full 300‑Question Audit
Click the button below to start the audit. It will take several minutes.