{"id":"W7132906485","doi":"","title":"The Promise of Responsible Research Assessment","year":2025,"lang":"en","type":"dissertation","venue":"Trepo - Institutional Repository of Tampere University","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Alberta; VSNU Vereniging van Universiteiten; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Research England; Koninklijke Nederlandse Akademie van Wetenschappen; Newcastle University","keywords":"Cynicism; Doctoral studies; Accountability","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3139384,0.002011284,0.002860355,0.008409557,0.009690494,0.04067982,0.006578927,0.01709507,0.01773045],"category_scores_gemma":[0.3444013,0.001323109,0.002634022,0.005153691,0.05785061,0.04630243,0.02770541,0.01964539,0.005831965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01928357,"about_ca_system_score_gemma":0.1157648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006816946,"about_ca_topic_score_gemma":0.004891017,"domain_scores_codex":[0.6971552,0.2193383,0.009336715,0.02219703,0.04339136,0.008581376],"domain_scores_gemma":[0.4071186,0.4124897,0.01916434,0.08138276,0.0533313,0.02651336],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006940346,0.000073892,0.001628115,0.0007870306,0.0001165247,0.0001346184,0.002669267,0.0006378287,0.0001218137,0.8764465,0.05717231,0.06014276],"study_design_scores_gemma":[0.00004910435,0.00005078931,0.00049989,0.001200586,0.00003336309,0.00008314243,0.001853325,0.0006235213,0.0001841318,0.7678955,0.2274692,0.00005738636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.00249417,0.02985007,0.0482548,0.7462078,0.008598574,0.0003780428,0.0002461498,0.0005217051,0.1634487],"genre_scores_gemma":[0.4646234,0.05017446,0.1374401,0.2127236,0.01827715,0.003343327,0.0007651695,0.001091931,0.1115609],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6860616,"threshold_uncertainty_score":0.8460361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2129773060336819,"score_gpt":0.5109170586383193,"score_spread":0.2979397526046374,"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."}}