Research map / Probabilistic and scientific modeling / Treatment effects
Causal Falsification of Digital Twins
Rob Cornish, Muhammad Faaiz Taufiq, Arnaud Doucet, Chris Holmes
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 |
|---|---|---|---|
| use conditional causal bounds instead of unconditional Manski bounds (ablation) | falsification test · Chloride | hypotheses rejected: 1 -> 24 | Improved |
| use conditional causal bounds instead of Manski bounds (ablation) | falsification test · Sodium | hypotheses rejected: 9 -> 21 | Improved |
| use conditional causal bounds instead of Manski bounds (ablation) | falsification test · Potassium | hypotheses rejected: 0 -> 13 | Improved |
| use conditional causal bounds instead of Manski bounds (ablation) | falsification test · Skin temperature | hypotheses rejected: 9 -> 10 | Improved |
| use conditional causal bounds instead of Manski bounds (ablation) | falsification test · Calcium | hypotheses rejected: 0 -> 5 | Improved |
| use conditional causal bounds instead of Manski bounds (ablation) | falsification test · Glucose | hypotheses rejected: 1 -> 5 | Improved |
| use conditional causal bounds instead of Manski bounds (ablation) | falsification test · Systolic arterial pressure | hypotheses rejected: 0 -> 2 | Improved |
| use conditional causal bounds instead of Manski bounds (ablation) | falsification test · Bicarbonate | hypotheses rejected: 1 -> 2 | No clear effect |
| replace Hoeffding confidence intervals with bootstrap (ablation) | falsification test · MIMIC-III sepsis, Pulse | hypotheses rejected | No clear effect |
| vary the quantile bounds for y low and y high (ablation) | falsification test · MIMIC-III sepsis, Pulse | hypotheses rejected | No clear effect |
Closest papers by meaning
- Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learning (NeurIPS 2024 · similarity 0.86)
- Continuously Updating Digital Twins using Large Language Models (ICML 2025 · similarity 0.83)
- Proximal Causal Inference With Text Data (NeurIPS 2024 · similarity 0.82)
- Improving the Generation and Evaluation of Synthetic Data for Downstream Medical Causal Inference (NeurIPS 2025 · similarity 0.82)
- Causal Identification for Complex Functional Longitudinal Studies (ICLR 2025 · similarity 0.81)
- DoAtlas-1: A Causal Compilation Paradigm for Clinical AI (NeurIPS 2026 · similarity 0.81)
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.
