{"slug": "seeking-cs-lg-endorsement-on-device-glucose-trend-forecasting-and-int8", "title": "Seeking cs.LG endorsement: on-device glucose trend forecasting and INT8 quantization", "summary": "Independent researcher Mohamed Menasy is seeking a cs.LG endorser on arXiv for \"GlucoEdge,\" an engineering study of on-device five-class glucose trend forecasting from continuous glucose monitor data using a 2,909-parameter 1D CNN. Static INT8 post-training quantization cut the model artifact size by about 31% but dropped macro recall from 0.5060 to 0.4135, with recall falling across all four directional classes. The work covers PyTorch-to-LiteRT conversion, calibration-data coverage and input-range clipping, cross-runtime numerical parity testing, and offline inference on a physical Android device, with code and reproducibility materials on GitHub under endorsement code PC9MML.", "body_md": "Hi everyone,\n\nI’m an independent researcher preparing my first arXiv submission in **cs.LG**, and I’m looking for an eligible endorser willing to look at the work.\n\n**Paper:** GlucoEdge: An Engineering Study of On-Device Five-Class Glucose Trend Forecasting and INT8 Quantization\n\nIt covers an end-to-end on-device ML pipeline for glucose trend forecasting from continuous glucose monitor data: five-class, 15-minute trend forecasting from CGM history; a compact 1D CNN with 2,909 parameters; PyTorch to LiteRT conversion; static INT8 post-training quantization; the effect of quantization on minority-class recall; calibration-data coverage and input-range clipping; cross-runtime numerical parity testing; and offline inference on a physical Android device.\n\nINT8 quantization cut the model artifact size by about 31%, but macro recall dropped from 0.5060 to 0.4135, with recall falling across all four directional classes. So the study looks at deployment size alongside what quantization does to minority-class behavior.\n\nI’ve tried to be explicit about the limitations: overlapping time-series windows, calibration-set selection, context-prefix leakage risk, single-device latency measurements, and the fact that this is a research prototype rather than a medical system.\n\nCode: [GitHub - mohamedmenasy/GlucoEdge · GitHub](https://github.com/mohamedmenasy/GlucoEdge) (Android implementation, training and conversion code, tests, model artifacts, and reproducibility materials)\n\nRequested category: **cs.LG**\n\nEndorsement code: **PC9MML**\n\nIf you’re eligible to endorse in cs.LG and willing to look at the manuscript, I’d appreciate it. I’m also glad to get technical feedback even if you can’t endorse.\n\nThanks,", "url": "https://wpnews.pro/news/seeking-cs-lg-endorsement-on-device-glucose-trend-forecasting-and-int8", "canonical_source": "https://discuss.huggingface.co/t/seeking-cs-lg-endorsement-on-device-glucose-trend-forecasting-and-int8-quantization/180642#post_1", "published_at": "2026-09-20 02:38:04+00:00", "updated_at": "2026-09-20 02:52:57.396634+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "mlops"], "entities": ["Mohamed Menasy", "GlucoEdge", "arXiv", "cs.LG", "PyTorch", "LiteRT", "GitHub", "Android"], "alternates": {"html": "https://wpnews.pro/news/seeking-cs-lg-endorsement-on-device-glucose-trend-forecasting-and-int8", "markdown": "https://wpnews.pro/news/seeking-cs-lg-endorsement-on-device-glucose-trend-forecasting-and-int8.md", "text": "https://wpnews.pro/news/seeking-cs-lg-endorsement-on-device-glucose-trend-forecasting-and-int8.txt", "jsonld": "https://wpnews.pro/news/seeking-cs-lg-endorsement-on-device-glucose-trend-forecasting-and-int8.jsonld"}}