{"id":"W4239061568","doi":"10.6028/jres.124.024","title":"Improving Reproducibility in Research: The Role of Measurement Science","year":2019,"lang":"en","type":"article","venue":"Journal of Research of the National Institute of Standards and Technology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Material Measurement Laboratory; Korea Research Institute of Standards and Science; European Commission; Wellcome Trust","keywords":"Reproducibility; Computer science; Data science; Medical physics; Statistics; Medicine; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6827123,0.00007571004,0.001020589,0.002419086,0.0001927393,0.00008640092,0.003280872,0.00007344099,0.0001083707],"category_scores_gemma":[0.3987374,0.00002900703,0.0002751121,0.006206788,0.003201815,0.0003251421,0.0007852918,0.0007140716,0.000002014968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003530949,"about_ca_system_score_gemma":0.003451954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000051039,"about_ca_topic_score_gemma":0.00008289226,"domain_scores_codex":[0.9341757,0.0045171,0.006832763,0.0008896067,0.05317939,0.0004053851],"domain_scores_gemma":[0.9181224,0.002010249,0.003649628,0.002579164,0.07357913,0.00005943243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002754888,0.0004253685,0.1594453,0.000350339,0.000255264,0.000002627876,0.0007959076,0.0004885146,0.3252337,0.380786,0.004267492,0.127674],"study_design_scores_gemma":[0.0009410706,0.0008465297,0.0458412,0.0007815731,0.00003480038,0.00006510887,0.005760188,0.002357127,0.1306419,0.7121491,0.1004696,0.0001118748],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9839278,0.002946681,0.0001037241,0.007884928,0.0001572287,0.0005754171,0.00002265574,5.778639e-7,0.004380955],"genre_scores_gemma":[0.9989704,0.00007609701,0.0008176969,0.000004243529,0.0000206455,0.000003086085,2.845261e-8,0.000002017435,0.0001058098],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3313631,"threshold_uncertainty_score":0.9995109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7945497748693895,"score_gpt":0.6115260820717491,"score_spread":0.1830236927976404,"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."}}