{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004178314,0.0002797374,0.0003210536,0.0003932631,0.0000842623,0.0001089588,0.001129534,0.0000840685,0.00002457017],"category_scores_gemma":[0.0003541996,0.0002561659,0.0000857755,0.001550066,0.00002523715,0.0004699941,0.00002462636,0.0003176116,0.00001131826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001251596,"about_ca_system_score_gemma":0.0002953506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001153854,"about_ca_topic_score_gemma":0.000001716199,"domain_scores_codex":[0.9980215,0.00001947648,0.0003475733,0.0006323078,0.0005933425,0.0003858148],"domain_scores_gemma":[0.9974506,0.001022012,0.00003798035,0.001145082,0.0002175357,0.0001268255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005414103,0.00004847954,0.000004449031,0.002621303,0.0001131704,0.00002350261,0.0002460214,0.9868396,0.000207301,0.0002747973,0.0004509329,0.009165066],"study_design_scores_gemma":[0.0002143932,0.000082263,0.00002683378,0.002912835,0.00004885622,0.00004837097,0.000005123821,0.9932243,0.002882365,0.000007598252,0.0002595395,0.000287483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000923429,0.003792858,0.9890337,0.00008655494,0.0005462379,0.0005027704,0.000341067,0.004771214,0.000002186564],"genre_scores_gemma":[0.2998173,0.0001527795,0.6995085,0.00003969072,0.00005544447,0.0001428229,0.00008954907,0.0001255277,0.00006836892],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2988939,"threshold_uncertainty_score":0.999989,"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."}}