{"id":"W3096222855","doi":"10.1101/2020.10.26.354274","title":"Embrace heterogeneity to improve reproducibility: A perspective from meta-analysis of variation in preclinical research","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Animal testing and alternatives","field":"Veterinary","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generalizability theory; Reproducibility; Variation (astronomy); Disease; Perspective (graphical); Meta-analysis; Standardization; Population; Psychology; Medicine; Computer science; Statistics; Pathology; Artificial intelligence; Developmental psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"meta_analysis","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reproducibility","study_design":"meta_analysis","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3659377,0.002726404,0.0101675,0.0081802,0.001394324,0.009286903,0.007984866,0.007890334,0.00172684],"category_scores_gemma":[0.5076141,0.001687498,0.01395626,0.006745261,0.008937967,0.006691229,0.006899877,0.01149169,0.0002420798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005755188,"about_ca_system_score_gemma":0.006933367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004934142,"about_ca_topic_score_gemma":0.004066297,"domain_scores_codex":[0.531558,0.4318262,0.01188602,0.01204861,0.01131769,0.001363509],"domain_scores_gemma":[0.3069769,0.6394351,0.01094314,0.03422653,0.007472483,0.0009459378],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001695126,0.0001884053,0.017659,0.03280525,0.1393517,0.00199326,0.004404919,0.08963449,0.002045063,0.5319117,0.01761856,0.1606927],"study_design_scores_gemma":[0.0004306271,0.0003666519,0.003336573,0.005656241,0.01581976,0.0003230081,0.0003612782,0.03550114,0.0009906725,0.9207821,0.01620904,0.0002228999],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007622503,0.1223758,0.7854054,0.07458407,0.003379364,0.0006879229,0.0006978018,0.0004426063,0.004804546],"genre_scores_gemma":[0.5360524,0.04056638,0.3670101,0.04221885,0.008971415,0.003023466,0.0004950074,0.0005047119,0.00115769],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6340623,"threshold_uncertainty_score":0.7819118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3934915570689531,"score_gpt":0.4572305628876313,"score_spread":0.0637390058186782,"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."}}