{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007736888,0.0005424764,0.002292112,0.0008512696,0.000102558,0.0001498787,0.001028935,0.0004561777,0.0001243645],"category_scores_gemma":[0.01676424,0.0005436615,0.001055424,0.002584734,0.0001753901,0.0001470358,0.001876437,0.001713743,0.00005844212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005665407,"about_ca_system_score_gemma":0.0005316837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006031888,"about_ca_topic_score_gemma":0.00008719129,"domain_scores_codex":[0.9900597,0.002101006,0.001333252,0.005035948,0.0009230534,0.0005470517],"domain_scores_gemma":[0.9914061,0.001321712,0.0007420428,0.004479104,0.001727696,0.0003233697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000945835,0.0007139283,0.01319726,0.0001757417,0.05646653,0.0001248133,0.0005280405,0.0003760867,0.9268442,0.0005999653,0.0000265592,0.000001085473],"study_design_scores_gemma":[0.0004470034,0.001032388,0.8516228,0.00012464,0.03778924,6.770996e-9,0.00005457352,0.00582965,0.101934,0.000147809,0.00005907757,0.0009587766],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931017,0.001366248,0.001043128,0.001164689,0.0002388967,0.001267598,0.001593676,0.0002071861,0.00001686718],"genre_scores_gemma":[0.9871321,0.00002592728,0.01190182,0.0001107122,0.000347796,0.00038775,7.949272e-7,0.00008948537,0.000003561852],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8384256,"threshold_uncertainty_score":0.9997015,"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."}}