{"id":"W2732894280","doi":"10.1371/journal.pbio.2002212","title":"Can cancer researchers accurately judge whether preclinical reports will reproduce?","year":2017,"lang":"en","type":"article","venue":"PLoS Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Replication (statistics); Pace; Optimism; Biology; Cancer; Cognitive psychology; Psychology; Statistics; Computer science; Data science; Social psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0075808,0.0002456824,0.0009639082,0.00005131613,0.0003097743,0.00008362895,0.0008236825,0.0005493701,0.001612588],"category_scores_gemma":[0.5132942,0.000184493,0.000177672,0.00006937407,0.001139162,0.00008806909,0.0005524986,0.0007904748,0.00004850236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008149531,"about_ca_system_score_gemma":0.0002439192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003284287,"about_ca_topic_score_gemma":0.0002140226,"domain_scores_codex":[0.9947764,0.001783727,0.001313573,0.001175823,0.0002871006,0.0006634357],"domain_scores_gemma":[0.9682922,0.02704332,0.001016747,0.003033255,0.0003207524,0.0002937298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002458389,0.003540447,0.3535927,0.0009409069,0.003150496,0.001269515,0.001270582,0.000001888091,0.04175447,0.2495518,0.09496996,0.2474989],"study_design_scores_gemma":[0.0005142419,0.0002424184,0.006283748,0.00009383204,0.0001025399,0.00001285284,0.00001300874,0.00002564407,0.00542673,0.979056,0.007964864,0.0002641072],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8520523,0.0007025978,0.002983613,0.09061114,0.009178306,0.003852554,0.0006364943,0.000676013,0.03930696],"genre_scores_gemma":[0.6652522,0.0004825348,0.3245658,0.0009768,0.002794384,0.00047244,0.000006900495,0.0001309243,0.005317991],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7295042,"threshold_uncertainty_score":0.9993001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8966954757372453,"score_gpt":0.6814503299149918,"score_spread":0.2152451458222535,"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."}}