[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-model-predicts-nuclear-sizes-with-textbook-level-accuracy":10,"sections":35},{"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":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},6582,"ai-model-predicts-nuclear-sizes-with-textbook-level-accuracy","AI Model Predicts Nuclear Sizes With Textbook-Level Accuracy","A neural network called NuCLR predicts nuclear sizes and quadrupole transition strengths as accurately as specialized physics models.","A machine-learning model just matched decades of specialized nuclear-physics calculations at predicting how big atomic nuclei are.\n\nResearchers trained NuCLR (Nuclear Co-Learned Representations), a multi-task model, on experimental data spanning the chart of nuclides. They tested it on charge radii and electric-quadrupole transition strengths, a measure of how non-spherical a nucleus is, for hundreds of nuclei held out of training. The model's charge-radius predictions were off by an average of 0.0147 femtometers, and its transition-strength predictions were off by 0.192 e^2b^2. Training the model to handle both properties at once, rather than building separate single-task models, made both sets of predictions more accurate.\n\nNuclear physicists lean on expensive, hand-tuned theoretical models to fill gaps in measured data, especially for the unstable, hard-to-produce nuclei studied at rare-isotope facilities. NuCLR does not just spit out numbers - it also produces error bars that flag which regions of the nuclear chart it is least confident about, effectively mapping where new experiments would teach it, and physicists, something new.\n\nThat is the unglamorous but genuinely useful kind of AI news: not a chatbot breakthrough, just a slightly better ruler for the physics stockroom.","[\"ai\",\"nuclear-physics\",\"machine-learning\",\"physics\"]","2026-09-17T04:00:00.000Z","2026-09-18T01:11:17.382Z","2026-09-18T01:11:29.295Z","published",null,[],"science",[26,27,28,29],"ai","nuclear-physics","machine-learning","physics",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.17838",0,{"sections":36},[37,41,45,50,55,59,62,67,72,76,81,86,91,96],{"name":38,"slug":26,"count":39,"latest_published_at":40},"AI",3852,"2026-09-17T08:27:09.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":18},"Security","security",648,{"name":46,"slug":47,"count":48,"latest_published_at":49},"Policy","policy",338,"2026-09-11T04:00:00.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":18},"Hardware","hardware",154,{"name":60,"slug":24,"count":61,"latest_published_at":18},"Science",114,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",99,"2026-09-09T17:27:33.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Software","software",75,"2026-09-10T20:41:21.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":18},"Dev Tools","dev-tools",73,{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",55,"2026-09-09T23:14:29.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",43,"2026-09-10T12:18:06.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",41,"2026-09-08T01:57:23.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]