[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-query-language-to-make-ml-models-explain-themselves":10,"sections":34},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},4297,"a-query-language-to-make-ml-models-explain-themselves","A Query Language to Make ML Models Explain Themselves","Researchers propose ExplAIner, a declarative framework that lets analysts interrogate black-box classification models with a structured, unified query language.","A new query language wants to bring order to the chaotic world of AI explainability.\n\nResearchers have introduced ExplAIner, a formal query language designed to unify how analysts ask \"why did the model decide that?\" questions about classification models. The work builds on an earlier language called FOIL but addresses two concrete failures: FOIL cannot express optimality-based explanations, and evaluating it against decision trees is computationally hard at every level of the polynomial hierarchy. ExplAIner extends FOIL's vocabulary with a layered structure that can express abductive, contrastive, feature-based, and distance-based queries under one roof. The researchers also introduce Opt-FOIL, a fragment tuned for finding minimal explanations ordered by strict partial orders, and prove its evaluation sits in FP-to-the-NP — a meaningful tractability result.\n\nThe complexity proofs carry a practical payoff: any fixed ExplAIner query can be evaluated with a fixed number of SAT solver calls, while Opt-FOIL explanations need only a polynomial number of such calls. That matters because the explainability field currently resembles a junk drawer — dozens of competing scores and methods, no common grammar, no easy way to compare them. A declarative layer above the solvers is the kind of boring infrastructure that actually ages well.\n\nThe XAI field has accumulated explanation methods faster than anyone can audit them; SHAP, LIME, and their relatives each make different assumptions and produce incompatible outputs. Whether ExplAIner achieves the standardization it promises depends entirely on adoption — and academic query languages have a long history of being theoretically elegant and practically ignored.","[\"ai\",\"machine-learning\",\"explainability\",\"research\"]","2026-07-08T04:00:00.000Z","2026-07-08T05:05:06.253Z","2026-07-08T05:05:09.211Z","published",null,[],"ai",[24,26,27,28],"machine-learning","explainability","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.06407",0,{"sections":35},[36,40,45,50,55,60,65,70,75,80,85,89,94,99],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":86,"slug":87,"count":83,"latest_published_at":88},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]