{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001716181,0.001072958,0.001648064,0.0006720875,0.00009980502,0.0003978703,0.002948256,0.000760555,0.0001468686],"category_scores_gemma":[0.03981585,0.001187156,0.0008390548,0.001797713,0.00005817008,0.000438545,0.004130129,0.002799793,0.00002038147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001370235,"about_ca_system_score_gemma":0.0006825131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002283861,"about_ca_topic_score_gemma":0.000001226857,"domain_scores_codex":[0.9924989,0.0001000472,0.001315082,0.001648012,0.003093892,0.001344041],"domain_scores_gemma":[0.9919074,0.003740402,0.0002991048,0.002507664,0.0009183132,0.00062711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00001653861,0.0004723098,0.1026565,0.1548562,0.001941619,0.001599717,0.002166798,0.694303,0.000656747,0.001128385,0.0369544,0.003247793],"study_design_scores_gemma":[0.004287657,0.0008337898,0.225594,0.3545582,0.001135502,0.001124358,0.0002000067,0.2254487,0.008421434,0.0006747181,0.1568438,0.02087785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004221763,0.02129701,0.9671869,0.0009962153,0.002613877,0.0006569602,0.00004259712,0.0029492,0.00003545551],"genre_scores_gemma":[0.186005,0.00644964,0.8034418,0.0009238784,0.0009537641,0.0005051087,0.0004756442,0.0006742362,0.0005710017],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4688543,"threshold_uncertainty_score":0.9995008,"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."}}