{"id":"W4400647264","doi":"10.1109/tse.2024.3428324","title":"Towards Efficient Fine-Tuning of Language Models With Organizational Data for Automated Software Review","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Software engineering; Software; Programming language; Data science","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":[0.005913788,0.001671256,0.001672487,0.002683384,0.0006740881,0.001803408,0.003501476,0.002122004,0.001530378],"category_scores_gemma":[0.03290932,0.0008993102,0.001497829,0.001310255,0.0008327045,0.004214533,0.002694579,0.003635985,0.001743206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001718993,"about_ca_system_score_gemma":0.004149133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009124827,"about_ca_topic_score_gemma":0.01887699,"domain_scores_codex":[0.9945503,0.002802685,0.0003320625,0.001331319,0.0007481574,0.0002355507],"domain_scores_gemma":[0.9804431,0.01230726,0.001524564,0.002093946,0.002849619,0.000781603],"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":[0.000580661,0.0009776854,0.0122742,0.001096026,0.0003317554,0.0003328329,0.001004474,0.2139648,0.02392105,0.003092333,0.02247512,0.719949],"study_design_scores_gemma":[0.00004435338,0.0001183384,0.000690258,0.00003322831,0.00003019186,0.00006240934,0.00008285354,0.989064,0.004625184,0.003090329,0.002135605,0.00002320606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09542399,0.003727717,0.8685994,0.001632009,0.000241258,0.0005717188,0.001089241,0.02698517,0.001729607],"genre_scores_gemma":[0.5518605,0.0007948928,0.4355762,0.001350281,0.0001900616,0.0007630682,0.005290007,0.0009403703,0.003234671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009124827,"threshold_uncertainty_score":0.03127551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02468724325318223,"score_gpt":0.279633167470946,"score_spread":0.2549459242177637,"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."}}