{"id":"W4392564473","doi":"10.1145/3626252.3630929","title":"Specifications and Contract Grading in Computer Science Education","year":2024,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Grading (engineering); Terminology; Popularity; Computer science; Engineering management; Risk analysis (engineering); Management science; Engineering ethics; Engineering; Political science; Business; Linguistics; Law","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":[0.06105759,0.0006377182,0.0006380164,0.008364487,0.001802954,0.008399352,0.001615338,0.002239261,0.005783067],"category_scores_gemma":[0.2112247,0.000348437,0.0005971344,0.01034625,0.009040656,0.009558704,0.003333857,0.003184383,0.0009402318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008331861,"about_ca_system_score_gemma":0.00936641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008066867,"about_ca_topic_score_gemma":0.008888981,"domain_scores_codex":[0.8703628,0.078278,0.008913436,0.003530266,0.03734987,0.001565686],"domain_scores_gemma":[0.7009997,0.2173289,0.02569523,0.00855988,0.04418191,0.003234371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001466653,0.0001776383,0.01216286,0.002225131,0.00005043776,0.00006659899,0.003174221,0.004503049,0.0004407984,0.3998301,0.00825738,0.5689652],"study_design_scores_gemma":[0.0001150705,0.0008501626,0.03705893,0.01263118,0.0001307851,0.000584404,0.008196928,0.0244952,0.006521598,0.6359702,0.2730879,0.0003575891],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1051785,0.1120142,0.448479,0.04245128,0.003046894,0.001180122,0.0006139959,0.0008082917,0.2862277],"genre_scores_gemma":[0.8357421,0.0294096,0.1174776,0.003181233,0.0007033919,0.0007801669,0.000341891,0.0002837343,0.01208042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06105759,"threshold_uncertainty_score":0.3229073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03091792833329753,"score_gpt":0.2962016101914191,"score_spread":0.2652836818581215,"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."}}