{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005714823,0.00004371012,0.00004072564,0.0002458095,0.0001191729,0.0008057425,0.0002346038,0.00001270081,0.000003089795],"category_scores_gemma":[0.00002338621,0.00003812748,0.000009673201,0.0005809128,0.00005945011,0.000564703,0.0000602334,0.0001341812,0.00001867574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003940076,"about_ca_system_score_gemma":0.0002045987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009362412,"about_ca_topic_score_gemma":0.000008967118,"domain_scores_codex":[0.9993906,0.00002207695,0.00008434545,0.0002738931,0.00009804508,0.0001310549],"domain_scores_gemma":[0.9996904,0.00007845641,0.00001051565,0.0001569312,0.00001709833,0.00004656331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[6.183418e-8,0.0000125811,0.001027926,0.000003558913,4.669394e-7,9.31672e-7,0.001143969,0.00002322858,0.0001058694,0.2528729,0.00004026711,0.7447683],"study_design_scores_gemma":[0.00008461588,0.00003947263,0.1113047,0.0001593011,0.00000223145,0.00007632037,0.0000910151,0.7956824,0.0001564597,0.002894175,0.08929596,0.0002134134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05430094,0.000396737,0.9412526,0.002184987,0.0005601813,0.00005936286,4.288902e-8,0.0002671474,0.000977968],"genre_scores_gemma":[0.8046331,0.000005072925,0.195105,0.00006997732,0.00005090615,0.000003000132,2.359199e-7,0.00000200704,0.0001307284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7956591,"threshold_uncertainty_score":0.7769793,"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."}}