{"id":"W4408256992","doi":"10.1145/3711403.3711450","title":"Automated Generation of Challenge Questions for Student Code Evaluation Using Abstract Syntax Tree Embeddings and RAG: An Exploratory Study","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Abstract syntax tree; Computer science; Programming language; Syntax; Tree (set theory); Abstract syntax; Code (set theory); Exploratory research; Code generation; Theoretical computer science; Natural language processing; Mathematics; Operating system; Sociology; Combinatorics","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":[0.01119339,0.001268549,0.0008828999,0.001639465,0.0005798175,0.001811125,0.001668963,0.001792412,0.001526806],"category_scores_gemma":[0.08589006,0.0004061338,0.0006167382,0.0008724997,0.0009009131,0.001996378,0.002319494,0.001554452,0.0008336953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00067152,"about_ca_system_score_gemma":0.0007934864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006805226,"about_ca_topic_score_gemma":0.0009937542,"domain_scores_codex":[0.9810771,0.01340036,0.000844829,0.001821885,0.002267978,0.0005877601],"domain_scores_gemma":[0.8214889,0.1474102,0.006110145,0.008453824,0.01457934,0.001957531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00405918,0.01356979,0.1238221,0.002821772,0.000305005,0.00245182,0.06900129,0.04541132,0.1030728,0.004620166,0.009430264,0.6214346],"study_design_scores_gemma":[0.001070753,0.02580586,0.1441655,0.0007569731,0.0004024957,0.003540222,0.03548845,0.4679765,0.2688235,0.00898229,0.04234806,0.0006393043],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9268885,0.0001245454,0.06903183,0.0001460271,0.00003428542,0.001022543,0.0004736641,0.001009601,0.001269018],"genre_scores_gemma":[0.9006214,0.00008846987,0.09537876,0.0001043654,0.00002735464,0.001109497,0.001099604,0.0002410753,0.001329485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01119339,"threshold_uncertainty_score":0.05919701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1557444919559349,"score_gpt":0.4252905517489088,"score_spread":0.2695460597929739,"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."}}