analiza aiqbench
This paper proposes a way to score candidate causal graphs when the true structure is unknown, using a learned probabilistic judgment model fed with association, conditional dependence, and directionality evidence. Its reported results are on synthetic data only: a correlation with structural error across 20 algorithm-and-size settings, and a 54.4% best-candidate hit rate versus 48.4% for the Self-Compatibility baseline. Readers should weigh whether the gains hold on real observational data, where the true graph is unavailable to validate against.
CausalGrade: Evidence-Guided Causal Graph Scoring with Jev
arXiv:2610.40692v1 Announce Type: cross Abstract: Evaluating the structural quality of candidate causal graphs when the true causal structure is unknown is an important problem in applying causal discovery results. This paper proposes CausalGrade, a causal graph scoring method based on the probabilistic judgment model Jev. The method jointly provides Jev with evidence of association, conditional dependence, and directionality from observational data and edge probabilities produced by the causal discovery foundation model CDFM. Jev produces probabilistic judgments about direct causal edges, and a graph-level score is obtained by measuring the agreement between the adjacency structure of the graph under evaluation and these edge-level judgments. Across 300 synthetic datasets, the score exhibits a relatively strong negative correlation with structural error in all 20 combinations of four causal discovery algorithms and five variable counts, indicating that higher scores generally correspond to smaller structural errors. In 500 synthetic graph selection tasks, CausalGrade achieves a best-candidate hit rate of 54.4\%, exceeding the 48.4\% achieved by the Self-Compatibility metric \(\kappa_G\), further supporting its ability to discriminate the structural quality of graphs under evaluation.
Abstract:Evaluating the structural quality of candidate causal graphs when the true causal structure is unknown is an important problem in applying causal discovery results. This paper proposes CausalGrade, a causal graph scoring method based on the probabilistic judgment model Jev. The method jointly provides Jev with evidence of association, conditional dependence, and directionality from observational data and edge probabilities produced by the causal discovery foundation model CDFM. Jev produces probabilistic judgments about direct causal edges, and a graph-level score is obtained by measuring the agreement between the adjacency structure of the graph under evaluation and these edge-level judgments. Across 300 synthetic datasets, the score exhibits a relatively strong negative correlation with structural error in all 20 combinations of four causal discovery algorithms and five variable counts, indicating that higher scores generally correspond to smaller structural errors. In 500 synthetic graph selection tasks, CausalGrade achieves a best-candidate hit rate of 54.4\%, exceeding the 48.4\% achieved by the Self-Compatibility metric \(\kappa_G\), further supporting its ability to discriminate the structural quality of graphs under evaluation.
Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2610.40692 [stat.ML]
(or arXiv:2610.40692v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2610.40692 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 272 cuvinte