AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs

Clément Yvernes, Emilie Devijver, Marianne Clausel, Eric Gaussier

ICML 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Differentiable and score-based DAG learning · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
choose backdoor-based equivalent formula over frontdoor formula for E(Y | do(z))linear Gaussian model on Figure 1 graph · simulation, 1000 runsestimator varianceImproved
estimate null effect of X on Y via frontdoor-type formula instead of simpler equivalentlinear Gaussian model on Figure 1 graph · simulation, 1000 runsestimator varianceHurt
replace P(P38 | do(Mek)) with equivalent query P(P38 | do(Akt, Erk, Jnk))adjustment estimators on Sachs dataset · Sachs protein signalingbootstrap variance: 0.000572 -> 0.000016Improved
replace P(P38 | do(Mek)) with equivalent query P(P38 | do(Erk, Jnk))adjustment estimators on Sachs dataset · Sachs protein signalingbootstrap variance: 0.000572 -> 0.000017Improved
replace P(P38 | do(Mek)) with equivalent observational query P(P38)adjustment estimators on Sachs dataset · Sachs protein signalingbootstrap variance: 0.000572 -> 0.001029Hurt
use any equivalent formula for the null effectadjustment estimators on Sachs dataset · Sachs protein signalingpredicted effect: -0.00154 to 0.02272No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy