{"name":"macau-hidden-bites","repo":"Lico124378/macau-hidden-bites","url":"https://midorreal.com/project/lico124378-macau-hidden-bites","repository":"https://github.com/Lico124378/macau-hidden-bites","description":"A Macau food recommendation Agent built on Thompson Sampling + StackedPareto weight fusion, with a full evaluation pipeline (5-fold CV, bootstrap CIs, stress tests) on 5,000 simulated users and 100k interactions. Competition entry for the QwenPaw AI Developer Challenge.","facts":{"license":{"value":"MIT","source":"https://github.com/Lico124378/macau-hidden-bites","checked":"21 Nov 2026"},"language":{"value":"Python","source":"https://github.com/Lico124378/macau-hidden-bites","checked":"21 Nov 2026"},"releases":{"value":"0","source":"https://github.com/Lico124378/macau-hidden-bites/releases","checked":"20 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/Lico124378/macau-hidden-bites/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/Lico124378/macau-hidden-bites","checked":"21 Nov 2026"}},"stars":122.0,"writeup":{"what_it_is":"A Macau food recommendation agent that takes a user's budget, group size, weather and waiting tolerance, then ranks restaurants using four weighted dimensions (taste match, quality stability, convenience, value for money). It is packaged as a QwenPaw custom skill. All restaurant, user and interaction data are fictional simulated data.","audience":"Tourists in Macau choosing restaurants, and developers evaluating recommendation pipelines","claims":[{"kind":"specific","claim":"Uses fictional simulated data and is not validated on real users","excerpt":"本项目所有食店、用户与交互数据均为比赛用虚构/模拟数据","status":"not_checked"},{"kind":"specific","claim":"Evaluation uses 5,000 simulated users and 100,000 interactions","excerpt":"5,000 名仿真用户、100,000 条模拟交互","status":"not_checked"},{"kind":"specific","claim":"Includes a knowledge base of 50 fictional restaurants","excerpt":"50 家虚构澳门食店，含区域、菜系、价格与四维特征","status":"not_checked"},{"kind":"specific","claim":"Uses five-fold cross-validation with bootstrap confidence intervals","excerpt":"按用户 ID 划分 5 个互斥测试折，五折交叉验证","status":"not_checked"},{"kind":"specific","claim":"Reports that the individual DR method did not outperform Naive","excerpt":"单独 DR 未优于 Naive（差值 −0.005227","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-28"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":42,"reality":19,"gap":23,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-21T16:53:47+00:00","text":"Repository created","source":"https://github.com/Lico124378/macau-hidden-bites"}],"cite":"macau-hidden-bites is a GitHub project at https://github.com/Lico124378/macau-hidden-bites written mainly in Python, described there as \"A Macau food recommendation Agent built on Thompson Sampling + StackedPareto weight fusion, with a full evaluation pipeline (5-fold CV, bootstrap CIs, stress tests) on 5,000 simulated users and 100k interactions. Competition entry for the QwenPaw AI Developer Challenge\".","attribution":"Data from Mid or Real, https://midorreal.com/project/lico124378-macau-hidden-bites, checked 22 November 2026. Attribution with a link is required.","still_real":null}