[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-when-ml-models-agree-on-answers-but-not-on-why":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},4264,"when-ml-models-agree-on-answers-but-not-on-why","When ML Models Agree on Answers but Not on Why","EvoXplain finds that equally accurate ML models can rely on entirely different internal logic, a problem that is especially serious in genomics.","A new diagnostic tool catches something ML practitioners have quietly sidestepped: two models can post identical accuracy and still explain their predictions through entirely different internal logic.\n\nResearchers introduced EvoXplain, a framework that treats model explanations not as properties of a single trained model but as outputs drawn from an entire training pipeline. Testing on cancer genomics data — a TCGA pan-cancer cohort and a breast-cancer subtype task — they found that logistic regression models hitting 98% accuracy split into several distinct \"explanatory basins,\" each pointing to different gene sets. Gradient-boosted trees, given the same data, converged on a single basin. The split emerged from varying regularization strength alone, with no change to the training data.\n\nThis matters most in genomics, where model explanations get published as biological findings — specific genes flagged as relevant to a cancer subtype. If different training runs point to different genes with equal confidence, the standard practice of averaging explanations across runs is masking a disagreement, not resolving one. EvoXplain also shows that a consensus explanation can correspond to none of the actual trained models.\n\nMost interpretability research focuses on making single models more legible. This work asks a prior question: are the explanations stable across runs at all? For anyone who has published findings derived from ML pipelines, that is a more uncomfortable question than it might sound.","[\"machine-learning\",\"interpretability\",\"genomics\",\"ai\"]","2026-07-07T04:00:00.000Z","2026-07-07T22:28:09.123Z","2026-07-07T22:28:11.937Z","published",null,[],"ai",[26,27,28,24],"machine-learning","interpretability","genomics",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.22240",0,{"sections":35},[36,40,45,50,55,60,65,70,75,79,84,88,93,98],{"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":18},"Dev Tools","dev-tools",59,{"name":80,"slug":81,"count":82,"latest_published_at":83},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":85,"slug":86,"count":82,"latest_published_at":87},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]