{"id":"W4405259287","doi":"10.1007/s10664-024-10597-8","title":"Harnessing pre-trained generalist agents for software engineering tasks","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Reinforcement learning; Software engineering; Generalizability theory; Scheduling (production processes); Machine learning; Software; Domain (mathematical analysis); Human–computer interaction; Engineering; Operations management","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000680193,0.0006729741,0.0005399033,0.0006593839,0.0001998679,0.0011132,0.001516134,0.0003171391,0.00003950874],"category_scores_gemma":[0.006388935,0.0006922217,0.0003976762,0.001612976,0.0000450948,0.001035545,0.0005418199,0.0007786489,0.00007466984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005131269,"about_ca_system_score_gemma":0.0002117189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001380932,"about_ca_topic_score_gemma":8.405021e-7,"domain_scores_codex":[0.9957702,0.00003170504,0.0006363588,0.00127273,0.0008334679,0.001455565],"domain_scores_gemma":[0.9949417,0.003332436,0.00004773644,0.0009669708,0.0001600593,0.000551159],"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":[0.00003363849,0.0002148305,0.0389718,0.004677472,0.0006932817,0.0008248025,0.002534417,0.8669565,0.003382016,0.003987578,0.03841651,0.0393072],"study_design_scores_gemma":[0.0005772442,0.0001354187,0.03699505,0.0006843411,0.00003957738,0.000121186,0.000003547311,0.7994063,0.001854127,0.0001320706,0.1586978,0.001353285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0454347,0.001970346,0.9407122,0.0004013945,0.002837183,0.0005890769,0.00004341049,0.008008216,0.000003479216],"genre_scores_gemma":[0.3248587,0.00002314531,0.6715576,0.0002372925,0.001388184,0.0006050072,0.00008436262,0.0003501191,0.000895603],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.279424,"threshold_uncertainty_score":0.9999238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03556022016790315,"score_gpt":0.3148634202315637,"score_spread":0.2793032000636606,"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."}}