Research map / Probabilistic and scientific modeling / Molecules and proteins
X-CAL: Explicit Calibration for Survival Analysis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 X-CAL to Log-Norm maximum likelihood training (λ=1000) | Log-Norm survival model · Gamma simulation, censored | D-cal: 0.029 -> 7e-5 | Helped |
| Add X-CAL to Log-Norm maximum likelihood training (λ=1000) | Log-Norm survival model · Gamma simulation, censored | concordance: 0.981 -> 0.897 | Hurt |
| Add X-CAL to Log-Norm maximum likelihood training (λ=1000) | Log-Norm survival model · Survival-MNIST, censored | D-cal: 0.392 -> 0.007 | Helped |
| Add X-CAL to Log-Norm S-CRPS training (λ=1000) | Log-Norm survival model · Survival-MNIST, censored | D-cal: 0.215 -> 9e-4 | Helped |
| Add X-CAL to Log-Norm S-CRPS training (λ=1000) | Log-Norm survival model · MIMIC-III length of stay | D-cal: 0.859 -> 0.005 | Helped |
| Add X-CAL to Cat-ni maximum likelihood training (λ=1000) | Cat-ni survival model · MIMIC-III length of stay | D-cal: 0.002 -> 1e-4 | Helped |
| Use interpolated rather than non-interpolated CDF (ablation) | Categorical survival model · MIMIC-III length of stay | D-cal: 0.002 -> 4e-4 | Helped |
| Add X-CAL to Log-Norm maximum likelihood training (λ=1000) | Log-Norm survival model · Glioma (TCGA) | D-cal: 0.059 -> 0.004 | Helped |
| Add X-CAL to MTLR maximum likelihood training (λ=1000) | MTLR-ni survival model · Glioma (TCGA) | D-cal: 0.009 -> 0.002 | Helped |
| Set soft-membership temperature to γ=10 instead of γ=10^4 (ablation) | X-CAL · Gamma simulation, training data | Exact D-Cal: 0.0039 -> 0.2337 | Hurt |
| Set soft-membership temperature to γ=10^5 instead of γ=10^4 (ablation) | X-CAL · Gamma simulation, training data | Exact D-Cal: 0.0039 -> 0.0025 | Helped |
| Set soft-membership temperature to γ=5 × 10^7 instead of γ=10^4 (ablation) | X-CAL · Gamma simulation, training data | Exact D-Cal: 0.0039 -> 0.0048 | Hurt |
Closest papers by meaning
- Toward Conditional Distribution Calibration in Survival Prediction (NeurIPS 2024 · similarity 0.86)
- Conformalized Survival Distributions: A Generic Post-Process to Increase Calibration (ICML 2024 · similarity 0.86)
- Deep Copula-Based Survival Analysis for Dependent Censoring with Identifiability Guarantees (AAAI 2024 · similarity 0.83)
- Testing Calibration in Nearly-Linear Time (NeurIPS 2024 · similarity 0.83)
- SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference (NeurIPS 2026 · similarity 0.83)
- Uncertainty-Calibrated Prediction of Randomly-Timed Biomarker Trajectories with Conformal Bands (NeurIPS 2025 · similarity 0.82)
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.