{"id":"W2973447102","doi":"10.18438/eblip29579","title":"Publons Peer Evaluation Metrics are not Reliable Measures of Quality or Impact","year":2019,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Altmetrics; Computer science; Metric (unit); Bibliometrics; Data science; Information retrieval; Library science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2083437,0.001573442,0.003451176,0.03707824,0.003743948,0.02536719,0.004111325,0.002416951,0.01287753],"category_scores_gemma":[0.5924971,0.001018809,0.001835144,0.05094213,0.007644835,0.02275303,0.007369634,0.003283389,0.00843853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01033624,"about_ca_system_score_gemma":0.01754353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004411305,"about_ca_topic_score_gemma":0.007747927,"domain_scores_codex":[0.6298797,0.1141103,0.04854886,0.0131824,0.191251,0.003027763],"domain_scores_gemma":[0.2297945,0.2720587,0.08601236,0.04501402,0.3611116,0.006008882],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002735115,0.0001382321,0.0368615,0.02342542,0.001308681,0.0001396403,0.00442281,0.000700681,0.001075336,0.0496098,0.2099276,0.6721168],"study_design_scores_gemma":[0.00007832214,0.0003348532,0.05795752,0.01641868,0.0006565724,0.000320758,0.005435958,0.001509327,0.002624271,0.03799266,0.8763872,0.0002838598],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.07901116,0.2124127,0.1000756,0.1361929,0.05062327,0.004913572,0.03958098,0.003341613,0.3738482],"genre_scores_gemma":[0.6836799,0.08783612,0.0957185,0.02191599,0.02280287,0.007422898,0.02439434,0.003755621,0.05247388],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9629217,"threshold_uncertainty_score":0.9762532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6195672100766529,"score_gpt":0.5780895375151042,"score_spread":0.04147767256154877,"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."}}