{"id":"W4400582781","doi":"10.1145/3643775","title":"Improving the Learning of Code Review Successive Tasks with Cross-Task Knowledge Distillation","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Task (project management); Code (set theory); Distillation; Artificial intelligence; Machine learning; Programming language; Engineering; Chemistry; Chromatography","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":[0.005159675,0.002470593,0.001672955,0.001907115,0.0008182088,0.001709602,0.003367693,0.002824067,0.00236571],"category_scores_gemma":[0.02558921,0.0007266336,0.001224848,0.001075203,0.0009384231,0.004269854,0.003131546,0.004149023,0.001845647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001955242,"about_ca_system_score_gemma":0.003066886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007547219,"about_ca_topic_score_gemma":0.01272766,"domain_scores_codex":[0.9955831,0.001512805,0.0002755578,0.001565814,0.0007542328,0.0003084509],"domain_scores_gemma":[0.9782507,0.01180626,0.00153018,0.00292512,0.004623816,0.0008640044],"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":[0.0008641625,0.001025524,0.00734001,0.0008170148,0.0002262129,0.0002686762,0.0006103847,0.1064522,0.02308233,0.001472967,0.02162093,0.8362196],"study_design_scores_gemma":[0.00009363012,0.0004002453,0.001384846,0.00004594806,0.0000744547,0.0001102891,0.00009769373,0.9759151,0.01554587,0.002893822,0.003390454,0.00004756882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2945325,0.006119653,0.6512368,0.002197416,0.001041046,0.0008699957,0.001280678,0.0360985,0.006623368],"genre_scores_gemma":[0.76029,0.0007936453,0.2196056,0.001519648,0.0003421916,0.0005174946,0.005151483,0.0009187917,0.01086116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007547219,"threshold_uncertainty_score":0.0272873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01315232630338241,"score_gpt":0.2774240932908377,"score_spread":0.2642717669874553,"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."}}