{"slug": "kira-a-full-stack-reading-screening-system-with-dual-pathway-analysis-for", "title": "KIRA: A Full-Stack Reading Screening System with Dual-Pathway Analysis for Children", "summary": "Researchers behind the arXiv paper 2610.28840v1 released KIRA, a dual-pathway reading screening system that adapts pretrained word and phoneme recognizers to children's speech, cutting word error rate from 13.88% to 8.84% and phoneme error rate from 41.66% to 23.00%. KIRA pairs word-level fluency scoring with phoneme-level error detection to support Word Reading (WRE) and Oral Reading Fluency (ORF), two foundational K-2 screening tasks, and delivers results through a web-based teacher-facing interface that shows fluency scores alongside phoneme feedback for targeted intervention. The system is presented as a full-stack, deployable, classroom-ready screener, addressing the limited scope and opaque evaluation of existing proprietary AI screeners.", "body_md": "arXiv:2610.28840v1 Announce Type: new \nAbstract: Early-grade reading screening is critical for identifying children at risk of reading difficulty. Existing AI-based screeners are often limited in the scope of their analyses and evaluation metrics, or are proprietary systems that lack transparent model specifications and evaluation. We present KIRA, a dual-pathway screening system that pairs word-level fluency scoring with detailed phoneme-level error detection. We adapt pretrained word and phoneme recognizers to children's speech, reducing word error rate from 13.88% to 8.84% and phoneme error rate from 41.66% to 23.00%. Powered by these child-adapted models, we implement Word Reading (WRE) and Oral Reading Fluency (ORF), two foundational tasks in K-2 screening. The system integrates these recognizers with a web-based teacher-facing interface presenting fluency scores alongside phoneme feedback for potential targeted intervention. KIRA brings modern child-speech recognition into a full-stack, deployable, classroom-ready reading screener.", "url": "https://wpnews.pro/news/kira-a-full-stack-reading-screening-system-with-dual-pathway-analysis-for", "canonical_source": "https://arxiv.org/abs/2610.28840", "published_at": "2026-10-22 04:00:00+00:00", "updated_at": "2026-10-22 04:12:11.747922+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-research", "natural-language-processing"], "entities": ["KIRA", "arXiv", "Word Reading (WRE)", "Oral Reading Fluency (ORF)"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/kira-a-full-stack-reading-screening-system-with-dual-pathway-analysis-for", "markdown": "https://wpnews.pro/news/kira-a-full-stack-reading-screening-system-with-dual-pathway-analysis-for.md", "text": "https://wpnews.pro/news/kira-a-full-stack-reading-screening-system-with-dual-pathway-analysis-for.txt", "jsonld": "https://wpnews.pro/news/kira-a-full-stack-reading-screening-system-with-dual-pathway-analysis-for.jsonld"}}