{"id":"W3126633874","doi":"10.1145/3437479.3437483","title":"ACM SIGSOFT Empirical Standards Released","year":2021,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Empirical research; Computer science; Task (project management); Quality (philosophy); Engineering; Systems engineering; Statistics; Mathematics","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":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.02906772,0.0006704296,0.003496477,0.0004289216,0.0002174438,0.001223997,0.004151768,0.0002765338,0.01344455],"category_scores_gemma":[0.982414,0.000426141,0.00212022,0.002647781,0.00005632943,0.0003799265,0.001049803,0.0005038166,0.00229903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000152229,"about_ca_system_score_gemma":0.0004419441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009552863,"about_ca_topic_score_gemma":0.00001265875,"domain_scores_codex":[0.9826062,0.001575645,0.005857474,0.001710995,0.007545767,0.0007039529],"domain_scores_gemma":[0.1209322,0.8459521,0.002935888,0.02282011,0.006285548,0.001074204],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001049552,0.00009362282,0.8472453,0.0001821466,0.0003255894,0.0001824243,0.0004622133,0.0009841779,0.001144665,0.0001465941,0.1292347,0.01998805],"study_design_scores_gemma":[0.0005724464,0.0000815583,0.3337461,0.00021899,0.0003654977,0.0001094465,0.0001467981,0.0005704523,0.003232327,0.0007689571,0.6591533,0.001034039],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8764507,0.008175737,0.1066485,0.004909829,0.001985293,0.0008263161,0.0004817298,0.0004198006,0.0001020831],"genre_scores_gemma":[0.908035,0.00003910449,0.08851753,0.0007489485,0.0003305117,0.00005456372,0.00006726983,0.00007807063,0.002128978],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9533463,"threshold_uncertainty_score":0.999819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5303859496964192,"score_gpt":0.4933538232445762,"score_spread":0.03703212645184295,"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."}}