AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

On Measuring Influence in Avoiding Undesired Future

Lue Tao, Tian-Zuo Wang, Yuan Jiang, Zhi-Hua Zhou

ICLR 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Latent-variable causal estimation

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
select variables by influence power instead of ACEalteration selection · TRADERsuccess rate (%): 51.13 -> 60.94Improved
select variables by influence power instead of MAX-ALLalteration selection · DOCTORsuccess rate (%): 51.08 -> 65.32Improved
select variables by influence power instead of CORRalteration selection · DOCTORsuccess rate (%): 51.33 -> 65.32Improved
select variables by influence power instead of MAX-ALLalteration selection · FARMERsuccess rate (%): 63.18 -> 63.86No clear effect
alter variables instead of only observingalteration selection · FARMERsuccess rate (%): 10.05 -> 63.86Improved
select variables by influence power instead of MAX-ALLalteration selection · BERMUDAsuccess rate (%): 72.71 -> 75.16Improved
select variables by influence power instead of CORRalteration selection · BERMUDAsuccess rate (%): 19.09 -> 75.16Improved
increase sample size from 10 to 5000 (ablation)OURS · TRADERsuccess rate (%): 42.97 -> 60.34Improved
increase sample size from 10 to 5000 (ablation)OURS · FARMERsuccess rate (%): 19.23 -> 63.62Improved
increase sample size from 10 to 5000 (ablation)OURS · DOCTORsuccess rate (%): 44.20 -> 65.72Improved
increase sample size from 1000 to 5000 (ablation)OURS · DOCTORsuccess rate (%): 65.20 -> 65.72No clear effect
increase MCTS iterations (ablation)MCTS influence power estimate · TRADER, FARMER, DOCTORmistake rateImproved

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