{"id":32997,"date":"2026-01-21T17:03:02","date_gmt":"2026-01-21T17:03:02","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/check-mate-a-sanity-check-for-trustworthy-ai\/"},"modified":"2026-06-08T13:22:38","modified_gmt":"2026-06-08T13:22:38","slug":"check-mate-a-sanity-check-for-trustworthy-ai","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/check-mate-a-sanity-check-for-trustworthy-ai\/","title":{"rendered":"Check Mate: A Sanity Check for Trustworthy AI"},"content":{"rendered":"<p>Methods of Explainable AI (XAI) try to illuminate the decision making process of complex Machine Learning models by generating explanations. However, for most real-world data there is no \u201cgroundtruth\u201d explanation, which makes evaluating the correctness of XAI methods and model decisions difficult. Often visual assessment or anecdotal evidence is the only type of evaluation. In this work we propose to<\/p>\n<p>use the game of chess as a source of \u201cnear ground-truth\u201d (NGT) explanations, which XAI methods can be compared against using various metrics, serving as a \u201csanity check\u201d. We demonstrate this process in an experiment with a deep convolutional neural network, to which we apply a range of commonly used XAI methods. As our main contribution, we publish our data set of 30 million chess positions along with<\/p>\n<p>their NGT explanations for free use in XAI research.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Methods of Explainable AI (XAI) try to illuminate the decision making process of complex Machine Learning models by generating explanations. However, for most real-world data there is no \u201cgroundtruth\u201d explanation, which makes evaluating the correctness of XAI methods and model decisions difficult. Often visual assessment or anecdotal evidence is the only type of evaluation. In this work we propose to use the game of chess as a source of \u201cnear [&hellip;]<\/p>\n","protected":false},"author":12,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"class_list":["post-32997","publication","type-publication","status-publish","hentry","publication-type-inproceedings"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32997","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/12"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32997\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=32997"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=32997"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}