{"id":"W3023468469","doi":"10.1145/3385678.3385681","title":"The ACM SIGSOFT Paper and Peer Review Quality Initiative","year":2020,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Technical peer review; Peer review; Computer science; Quality (philosophy); Empirical research; Software technical review; Peer-to-peer; Data science; Software quality; Engineering ethics; World Wide Web; Engineering management; Software; Engineering; Political science; Software development","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"],"consensus_categories":[],"category_scores_codex":[0.00728168,0.0002910452,0.0004432281,0.00007861215,0.0004128579,0.0007489275,0.003700588,0.00006546631,0.0001959916],"category_scores_gemma":[0.9530837,0.000190982,0.0001438145,0.001058435,0.0001189119,0.0004655785,0.003534446,0.000321511,0.0003239615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002606076,"about_ca_system_score_gemma":0.00004944499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001984282,"about_ca_topic_score_gemma":0.000006526163,"domain_scores_codex":[0.9954082,0.0001944169,0.0008635028,0.0009664877,0.002123793,0.0004436139],"domain_scores_gemma":[0.07933364,0.9053816,0.0008439044,0.01125602,0.002205011,0.0009797777],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002791838,0.000041651,0.1426478,0.0004872087,0.0001054096,0.00002561971,0.002190386,0.0003619257,0.0001832539,0.001176472,0.6389089,0.2138435],"study_design_scores_gemma":[0.0002761591,0.00006083791,0.2448808,0.000314047,0.000043825,0.000005277454,0.0002200374,0.0002279763,0.0001042543,0.000872879,0.7525114,0.0004825167],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2184861,0.07770711,0.05123764,0.6375689,0.006753559,0.003208287,0.0008678224,0.00392695,0.0002435912],"genre_scores_gemma":[0.9641243,0.0008934602,0.02202637,0.01180537,0.0003790972,0.00004894099,0.00006925676,0.00005108539,0.000602185],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.945802,"threshold_uncertainty_score":0.7788022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.243728938492969,"score_gpt":0.3970486452683754,"score_spread":0.1533197067754064,"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."}}