{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008098101,0.0002534977,0.0002964902,0.0001624521,0.0001124191,0.0002045209,0.003072938,0.00007178909,0.000004028885],"category_scores_gemma":[0.01625851,0.0001471998,0.0001365948,0.00142843,0.0001014173,0.0004423972,0.001106576,0.0006458196,0.000008558858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001027989,"about_ca_system_score_gemma":0.00009954267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001046298,"about_ca_topic_score_gemma":3.407343e-7,"domain_scores_codex":[0.9982295,0.00001062781,0.0003605625,0.0004343548,0.0006217792,0.0003431991],"domain_scores_gemma":[0.9967979,0.001700936,0.0001802723,0.0007565554,0.0004935979,0.00007077146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002261332,0.0005144976,0.3348988,0.140386,0.001672386,0.00004498147,0.01303138,0.1901091,0.0444808,0.07874799,0.02305408,0.172834],"study_design_scores_gemma":[0.001421326,0.001555452,0.1787711,0.05703035,0.0003685741,0.000247469,0.00009107517,0.6117726,0.1061053,0.0006571054,0.03951287,0.002466807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4102978,0.04786804,0.5322793,0.002083475,0.001730587,0.002169824,0.00003915747,0.003341269,0.0001905495],"genre_scores_gemma":[0.9890178,0.00016698,0.01033333,0.00002163548,0.00009376583,0.00006905632,0.000001323662,0.00005696795,0.0002391026],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.57872,"threshold_uncertainty_score":0.9920279,"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."}}