AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Multiverse Mechanica: A Testbed for Learning Game Mechanics via Counterfactual Worlds

Robert Ness, Ricardo Cannizzaro, Yunshu Wu, Lars Kunze

ICLR 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Counterfactual identification and bounds · 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
add seed-consistency loss L1 (ablation)Multiverse alignment fine-tuning · Shield mechanicExo MSE: 0.795 -> 0.087Improved
add seed-consistency loss L1 (ablation)Multiverse alignment fine-tuning · Shield mechanic reconstructionPSNR: 19.42 -> 13.35Hurt
add structure-alignment loss L2 on top of L1 (ablation)Multiverse alignment fine-tuning · Shield mechanic reconstructionSSIM: 0.275 -> 0.429Improved
add structure-alignment loss L2 on top of L1 (ablation)Multiverse alignment fine-tuning · Shield mechanic counterfactualSSIM: 0.129 -> 0.196Improved
add structure-alignment loss L2 without L1 (ablation)Multiverse alignment fine-tuning · Shield mechanicExo MSE: 0.793 -> 0.795No clear effect
use full multiverse alignment instead of standard diffusion fine-tuningOpenJourney-v4 · Shield mechanic counterfactualPSNR: 13.58 -> 11.04Hurt

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