[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-real-world-data-beats-synthetic-for-time-series-ai-models":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},4303,"real-world-data-beats-synthetic-for-time-series-ai-models","Real-world data beats synthetic for time series AI models","A new 142-billion-point open corpus shows that training forecasting models on real data consistently outperforms synthetic pretraining across benchmarks.","Researchers have released RMISC, a large open archive of real-world time series data designed to settle a standing debate in forecasting AI.\n\nThe corpus pulls together around 200 datasets spanning multiple domains and roughly 142 billion time points. The team used it to pretrain four time series foundation models under three conditions — univariate real data, synthetic multivariate data, and real-world multivariate data — then tested zero-shot generalization on standard in-distribution and out-of-distribution benchmarks. Real-world multivariate pretraining won across the board. The dataset is openly accessible, which matters given how much of this research stays locked inside labs.\n\nThe result chips away at a convenient assumption the field has leaned on: that synthetic data, which is cheaper and easier to scale, is good enough. It turns out the complex cross-variable relationships in real sensor readings, financial streams, and other messy data are not well-approximated by generated proxies. That gap compounds when models are asked to generalize outside their training distribution — exactly the scenario where foundation models are supposed to shine.\n\nThe finding mirrors a pattern already seen in large language models, where synthetic data helped at the margins but real, diverse corpora remained the stronger foundation — and suggests the time series community may be overdue for a similar reckoning with its pretraining defaults.","[\"ai\",\"machine learning\",\"time series\",\"datasets\"]","2026-07-08T04:00:00.000Z","2026-07-08T05:12:47.483Z","2026-07-08T05:12:50.445Z","published",null,[],"ai",[24,26,27,28],"machine learning","time series","datasets",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.06504",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"]