{"id":"W4393164122","doi":"10.1162/qss_a_00304","title":"Evaluating approaches to identifying research supporting the United Nations Sustainable Development Goals","year":2024,"lang":"en","type":"article","venue":"Quantitative Science Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Syddansk Universitet","keywords":"Sustainable development; Environmental resource management; Environmental planning; Political science; Process management; Management science; Computer science; Business; Geography; Environmental science; Engineering","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","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4608741,0.002285219,0.003691139,0.06993212,0.004282686,0.03251079,0.004320587,0.004231043,0.007298524],"category_scores_gemma":[0.6369351,0.0009948057,0.004491198,0.07737795,0.005785411,0.01480029,0.01381382,0.002910874,0.001147131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02792151,"about_ca_system_score_gemma":0.02898259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01384014,"about_ca_topic_score_gemma":0.01592558,"domain_scores_codex":[0.4400063,0.4345978,0.04188757,0.01102982,0.06796208,0.004516481],"domain_scores_gemma":[0.1460358,0.718133,0.04110901,0.02194346,0.06709166,0.005687026],"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":[0.003913003,0.001354886,0.1289577,0.03206429,0.008349464,0.0004766541,0.013139,0.05188225,0.002670664,0.1770367,0.01298872,0.5671667],"study_design_scores_gemma":[0.002244409,0.00584762,0.1203484,0.02838407,0.01025719,0.0004150692,0.05717437,0.163287,0.01524477,0.4884771,0.1075301,0.0007898745],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3868699,0.06136462,0.3090342,0.03869872,0.001968444,0.02035639,0.02076739,0.001940816,0.1589995],"genre_scores_gemma":[0.7090423,0.00593853,0.2722049,0.0009266956,0.0002977959,0.006353749,0.003841911,0.0001371136,0.001256875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9300679,"threshold_uncertainty_score":0.6648383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.949022836235384,"score_gpt":0.7319454571991254,"score_spread":0.2170773790362586,"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."}}