{"id":"W4405098729","doi":"10.22215/etd/2024-16309","title":"Beyond Verbal Self-Explanations: Student Annotations of a Code-Tracing Example Produced by ChatGPT","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Flowchart; Tracing; Computer science; Process tracing; Code (set theory); Constructive; Annotation; Expression (computer science); Quality (philosophy); Variety (cybernetics); Domain (mathematical analysis); Process (computing); Mathematics education; Programming language; Natural language processing; Artificial intelligence; Psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01311189,0.0008257153,0.0005499565,0.001951705,0.001345464,0.003096701,0.001396684,0.001571415,0.003429994],"category_scores_gemma":[0.1137452,0.0003455662,0.0004543738,0.001367746,0.00169586,0.003448882,0.003430613,0.001794644,0.001137608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107432,"about_ca_system_score_gemma":0.00126715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001241797,"about_ca_topic_score_gemma":0.002757156,"domain_scores_codex":[0.983097,0.01210625,0.0006911355,0.00117472,0.002523643,0.0004073579],"domain_scores_gemma":[0.8129489,0.1519685,0.009390515,0.009236725,0.01488658,0.001568716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.001099956,0.0006172305,0.06978074,0.001626591,0.00008657706,0.001843483,0.5084612,0.005484608,0.05109133,0.004606869,0.006888716,0.3484127],"study_design_scores_gemma":[0.0002575399,0.003503942,0.1320942,0.004143965,0.0004450583,0.004165375,0.3349904,0.1346843,0.1911449,0.02376794,0.1696933,0.001109132],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8505205,0.0002176005,0.133465,0.00143337,0.0001180353,0.0003520526,0.0004065339,0.002268951,0.01121798],"genre_scores_gemma":[0.8900295,0.0001791114,0.1028038,0.0002141815,0.00002767467,0.0003376141,0.0004142168,0.000502607,0.005491271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01311189,"threshold_uncertainty_score":0.06934315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01338513526125205,"score_gpt":0.3064894869946401,"score_spread":0.2931043517333881,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}