Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
CalPro: Prior-Aware Evidential Conformal Prediction with Structure-Aware Sensitivity Bounds for Protein Structures
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add split-conformal calibration (ablation) | CalPro · Protein benchmarks | coverage (%): 78.3 -> 90.1 | Improved |
| add NIG evidential head (ablation) | CalPro · Protein benchmarks | sharpness (Angstrom): 1.98 -> 1.42 | Improved |
| add prior regularizer L_prior (vs priors as features only) (ablation) | CalPro · Protein benchmarks | Spearman correlation with error: 0.76 -> 0.83 | Improved |
| add bio-prior inputs and regularizer (ablation) | CalPro · Protein benchmarks | Spearman correlation with error: 0.74 -> 0.83 | Improved |
| add priors in modality shift (ablation) | CalPro · X-ray to cryo-EM | coverage at 90% nominal (%): 84.7 -> 86.2 | Improved |
| add differentiable surrogate loss L_soft-conf (ablation) | CalPro · Protein benchmarks | Spearman correlation with error: 0.81 -> 0.83 | Improved |
| use GNN head instead of MLP head (ablation) | CalPro · Protein benchmarks | Spearman correlation with error: 0.78 -> 0.83 | Improved |
| add prior regularizer: constant reduction of Ls and Ms (ablation) | CalPro · Shift-sensitivity bound | M_s L_s epsilon (eps=0.1): 1.33 -> 0.68 -> 0.41 | Improved |
| invert the priors (adversarial) (ablation) | CalPro · X-ray to cryo-EM | coverage at 90% nominal (%): 86.2 -> 82.8 | Hurt |
| shuffle the priors (ablation) | CalPro · X-ray to cryo-EM | coverage at 90% nominal (%): 86.2 -> 84.1 | Hurt |
| train CQR on CalPro backbone with adapted prior loss (ablation) | CQR · X-ray to cryo-EM | coverage at 90% nominal (%): 83.7 -> 84.3 | Mixed |
| use CalPro instead of CQR for filtering docking poses | docking filter · PDBbind | docking success (%): 70.1 -> 74.8 | Improved |
Closest papers by meaning
- Inverse problems with experiment-guided AlphaFold (ICML 2025 · similarity 0.87)
- Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time (NeurIPS 2025 · similarity 0.85)
- GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs (NeurIPS 2026 · similarity 0.84)
- Robust Conditional Conformal Prediction via Branched Normalizing Flow (NeurIPS 2026 · similarity 0.84)
- Learning Polyhedral Conformal Sets for Robust Optimization (NeurIPS 2026 · similarity 0.83)
- Learning conformational ensembles of proteins based on backbone geometry (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
