[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-public-dataset-teaches-ai-to-read-crime-reports":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},4525,"a-public-dataset-teaches-ai-to-read-crime-reports","A Public Dataset Teaches AI to Read Crime Reports","Researchers released CrimeNER, a labeled dataset of 1,500+ crime documents meant to help NLP models extract structured facts from police and DOJ records.","A research team has released a labeled dataset designed to train AI models to extract structured information from crime-related text.\n\nThe dataset, called CrimeNER-db, contains more than 1,500 annotated documents drawn from public reports on terrorist attacks and press notes from the US Department of Justice. The researchers defined 4 broad entity categories and 21 fine-grained types — think locations, weapons, perpetrators, and victims — to cover the range of facts buried in these documents. They tested the dataset against both fully supervised models and zero- and few-shot approaches to gauge how well trained models generalize. The dataset is publicly available on GitHub.\n\nNamed-entity recognition — the task of pulling structured facts like names, places, and dates from raw text — is well-studied in general domains but thin on labeled data for law enforcement contexts. A dataset purpose-built for crime documents could give agencies, journalists, and researchers a foundation for building tools that surface relevant facts faster than manual review allows.\n\nThe DOJ publishes thousands of press releases a year; getting a model to reliably parse them is useful, though whether real agencies adopt academic NER tools in operational workflows is a different question entirely.","[\"nlp\",\"datasets\",\"ai\",\"law-enforcement\"]","2026-07-09T04:00:00.000Z","2026-07-09T06:37:50.253Z","2026-07-09T06:37:53.191Z","published",null,[],"ai",[26,27,24,28],"nlp","datasets","law-enforcement",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.02150",0,{"sections":35},[36,40,45,50,55,60,65,70,75,80,84,88,93,98],{"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":79},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":18},"Gaming","gaming",41,{"name":85,"slug":86,"count":83,"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"]