{"id":"W4392714858","doi":"10.20944/preprints202403.0556.v1","title":"The Use of AI in Software Engineering: Synthetic Knowledge Synthesis of Recent Research Literature","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Software engineering; Software; Data science; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00240825,0.0003879444,0.0005651408,0.0009852065,0.00009395237,0.00030294,0.001574547,0.0004337053,0.0003458232],"category_scores_gemma":[0.009599245,0.0002984557,0.0002042067,0.001804722,0.000254978,0.0003755837,0.00725839,0.002189805,0.0006466258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001061545,"about_ca_system_score_gemma":0.0001850711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005791005,"about_ca_topic_score_gemma":0.0001309766,"domain_scores_codex":[0.9970024,0.0000883227,0.0008887953,0.0008962578,0.0006165705,0.000507604],"domain_scores_gemma":[0.9954005,0.001102507,0.0002889066,0.001858735,0.001327244,0.00002212976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00101104,0.002644681,0.6452954,0.08106438,0.001212391,0.0002074339,0.00288984,0.01023144,0.01092622,0.07732031,0.01278218,0.1544146],"study_design_scores_gemma":[0.0001814834,0.000008835286,0.140277,0.02363068,0.0002801873,0.000007047791,0.000146399,0.01000825,0.03885904,0.01576199,0.7697116,0.00112752],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9825466,0.005621421,0.0001599002,0.002993612,0.003300884,0.001631054,0.0001282057,0.0002692847,0.003348983],"genre_scores_gemma":[0.9965612,0.001955824,0.0001272445,0.00003481702,0.0004106108,0.0002345163,0.00004414489,0.00007809324,0.000553558],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7569293,"threshold_uncertainty_score":0.9999468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3543661060710111,"score_gpt":0.4015801480489085,"score_spread":0.04721404197789736,"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."}}