{"id":"W4296087229","doi":"10.3390/app12189017","title":"Evidence-Based Software Engineering: A Checklist-Based Approach to Assess the Abstracts of Reviews Self-Identifying as Systematic Reviews","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Software Engineering Research","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Systematic review; Checklist; Computer science; Management science; Data science; Engineering ethics; Psychology; Risk analysis (engineering); MEDLINE; Medicine; Political science; Engineering; Cognitive psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.01560013,0.0003045193,0.0007291001,0.0004236029,0.0006070539,0.000438965,0.005152268,0.00004297742,0.00001856743],"category_scores_gemma":[0.007974318,0.0002105028,0.0001980399,0.00395215,0.0001071227,0.0003505745,0.0006707531,0.0004190403,0.00008397661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002153347,"about_ca_system_score_gemma":0.0005263017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000280082,"about_ca_topic_score_gemma":8.19747e-7,"domain_scores_codex":[0.9951568,0.0004244146,0.001003473,0.0008446174,0.001955027,0.0006156469],"domain_scores_gemma":[0.9930235,0.004765208,0.0004685413,0.001442785,0.000101631,0.0001984038],"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":[0.00001958118,0.0006829597,0.00150072,0.06008135,0.00007057825,0.00002022782,0.004990678,0.8943245,0.009453123,0.0202891,0.005157338,0.003409794],"study_design_scores_gemma":[0.002013691,0.001764693,0.01359109,0.03444911,0.0003971897,0.0001893963,0.001468841,0.8280394,0.04364593,0.0006845896,0.06837656,0.005379497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01363968,0.01430725,0.9624291,0.0005172674,0.0006417789,0.007342487,0.000003453735,0.0006963059,0.0004226436],"genre_scores_gemma":[0.7585072,0.0000650161,0.2367397,0.0005618655,0.00004026841,0.004017123,0.000001587309,0.00002133141,0.00004595067],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7448675,"threshold_uncertainty_score":0.9574282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1682083824029681,"score_gpt":0.3307259528974853,"score_spread":0.1625175704945172,"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."}}