{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1220488,0.001667718,0.002309386,0.01183851,0.006032804,0.0321591,0.004714651,0.0082128,0.04691932],"category_scores_gemma":[0.2758744,0.001250714,0.001243138,0.01182364,0.005112573,0.01178283,0.009351701,0.007172364,0.05195412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008240216,"about_ca_system_score_gemma":0.06718112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005588226,"about_ca_topic_score_gemma":0.007096113,"domain_scores_codex":[0.7515194,0.05194411,0.01502877,0.008420479,0.1697178,0.003369459],"domain_scores_gemma":[0.4794274,0.1002826,0.04279193,0.06932166,0.2532745,0.0549019],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000545919,0.0001336657,0.0007542734,0.0005113152,0.0000383748,0.00005391515,0.0001726358,0.0003744449,0.0003177379,0.01780685,0.6693246,0.3104576],"study_design_scores_gemma":[0.00006452947,0.00009363596,0.001277746,0.000459585,0.00002227777,0.00008095044,0.00009641372,0.0006717665,0.0003581053,0.01088088,0.9859419,0.00005224465],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.005054003,0.03070171,0.1722864,0.1993277,0.1045446,0.007034892,0.005827816,0.02455353,0.4506694],"genre_scores_gemma":[0.07372333,0.05233452,0.2904131,0.03203131,0.0472046,0.01037148,0.02026216,0.01005303,0.4636065],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8779512,"threshold_uncertainty_score":0.6454635,"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."}}