{"id":"W3082966820","doi":"10.1007/s10664-021-10005-5","title":"Understanding peer review of software engineering papers","year":2021,"lang":"en","type":"preprint","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Novelty; Quality (philosophy); Computer science; Technical peer review; Peer review; Software technical review; Psychology; Medical education; Software; Engineering ethics; Software quality; Software development; Engineering; Medicine; Political science; Social 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06389796,0.0007631439,0.001471231,0.01077629,0.003957869,0.02156978,0.002711388,0.005812689,0.02369917],"category_scores_gemma":[0.5207444,0.0008405281,0.0009225585,0.008372445,0.00387933,0.02534781,0.0054076,0.003528923,0.005495473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004606027,"about_ca_system_score_gemma":0.0100724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003804906,"about_ca_topic_score_gemma":0.003199942,"domain_scores_codex":[0.898334,0.057305,0.005584836,0.005611496,0.03056058,0.002604023],"domain_scores_gemma":[0.334793,0.4773779,0.03902,0.03054651,0.1109027,0.007359863],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004276187,0.0002615686,0.02927126,0.002817381,0.0005214743,0.001079447,0.02276625,0.004742279,0.002015527,0.3810637,0.2088623,0.3461712],"study_design_scores_gemma":[0.0001926729,0.0001899068,0.02111658,0.001713575,0.0003232741,0.000727453,0.01002611,0.01549628,0.002432113,0.5948268,0.3527358,0.0002195318],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1677242,0.06764422,0.2090632,0.1880231,0.01476741,0.001147602,0.002394943,0.002843864,0.3463915],"genre_scores_gemma":[0.9002807,0.01576282,0.03147718,0.005168047,0.008312127,0.0003569263,0.002143123,0.001127869,0.03537134],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.936102,"threshold_uncertainty_score":0.3379287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1029158298489965,"score_gpt":0.3172505489139484,"score_spread":0.2143347190649519,"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."}}