{"paper":{"title":"Computational Thinking Development in AI Agent Creation_A Mixed-Methods Study","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Students with moderate initial computational thinking levels show the largest gains from AI agent creation workshops.","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Gaowei Chen, Haiyang Xin, Lingyun Huang, Qiannan Niu, Shuang Li, Yimeng Sun","submitted_at":"2026-05-14T03:48:08Z","abstract_excerpt":"This mixed-methods study examined computational thinking (CT) development among 93 pre-high school students in a five-day AI agent creation workshop using CocoFlow, a no-code platform. Integrating pre-post assessments, behavioral logs, and interviews, we investigated CT development and how initial CT levels shape learning trajectories. Results revealed significant improvements in abstract thinking (effect size d = 0.71) and algorithmic thinking (effect size d = 0.70). Hierarchical regression identified iterative testing engagement as a predictor of self-efficacy gains (beta = 0.20, p = 0.05). "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Notably, students with moderate initial CT levels demonstrated substantially greater gains than both high-CT and low-CT peers, revealing an Optimal Development Zone effect (eta squared = 0.55).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the pre-post assessments and behavioral logs validly isolate computational thinking development from workshop-specific factors such as platform novelty, instructor effects, or student motivation without additional controls or validation data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Pre-high school students with moderate initial computational thinking skills gained the most from an AI agent creation workshop, exhibiting an Optimal Development Zone effect.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Students with moderate initial computational thinking levels show the largest gains from AI agent creation workshops.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e1e57fbc030792f2151c4e7ccd32139d3392c71c1bf034f4fd6da074eaa2e8e3"},"source":{"id":"2605.14330","kind":"arxiv","version":1},"verdict":{"id":"0ad6269e-c651-4b20-b95c-e55e385bedff","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:33:08.034431Z","strongest_claim":"Notably, students with moderate initial CT levels demonstrated substantially greater gains than both high-CT and low-CT peers, revealing an Optimal Development Zone effect (eta squared = 0.55).","one_line_summary":"Pre-high school students with moderate initial computational thinking skills gained the most from an AI agent creation workshop, exhibiting an Optimal Development Zone effect.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the pre-post assessments and behavioral logs validly isolate computational thinking development from workshop-specific factors such as platform novelty, instructor effects, or student motivation without additional controls or validation data.","pith_extraction_headline":"Students with moderate initial computational thinking levels show the largest gains from AI agent creation workshops."},"references":{"count":13,"sample":[{"doi":"","year":2026,"title":"Carnegie Mellon University, https://link.cs.cmu.edu/article.php?a=600, last ac-cessed 2026/03/26","work_id":"1bd6d07b-1152-409d-95ab-6d9c44d2089f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/1118178.1118215","year":2006,"title":"Communications of the ACM 49(3), 33–35 (2006)","work_id":"dc760b7d-4bfe-417e-95d2-de36027889b1","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1093/comjnl/bxs074","year":2012,"title":"The Computer Journal 55(7), 832–835 (2012)","work_id":"fccf64b8-6832-4750-8ddc-db8ce29b3eef","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.edurev.2017.09.003","year":2017,"title":"Educational Research Review 22, 142–158 (2017)","work_id":"aa4718dc-d03f-4407-9c5a-5717c0e707cd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.3102/0013189x12463051","year":2013,"title":"Educational Researcher 42(1), 38–43 (2013)","work_id":"19ee7606-45d0-47dc-b188-6a5948ade0c9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":13,"snapshot_sha256":"5430eefec23a1abdbb39b8bb9b648024fd23c7bdc518b1df28a46a394b853f38","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}