{"id":"W4408959880","doi":"10.1186/s13063-025-08747-4","title":"Tolerating bad health research (part 2): still as many bad trials, but more good ones too","year":2025,"lang":"en","type":"article","venue":"Trials","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Health Research Board","keywords":"Medicine; Research design","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","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8058837,0.0004384161,0.01352955,0.001172672,0.0006412781,0.002651553,0.002537572,0.0002061723,0.01690956],"category_scores_gemma":[0.6818262,0.0002104648,0.003290758,0.00339907,0.0001218824,0.000280546,0.0003839985,0.000462346,0.00647823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001311607,"about_ca_system_score_gemma":0.001116216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003482449,"about_ca_topic_score_gemma":0.00009754075,"domain_scores_codex":[0.5103964,0.3899947,0.07136294,0.004050586,0.02225293,0.001942385],"domain_scores_gemma":[0.640645,0.3026553,0.03029382,0.01615074,0.008982143,0.001272972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001099039,0.0001087427,0.0007744199,0.0001153254,0.0005245513,0.000008155998,0.0007256292,0.00004806804,0.0003252093,0.02491616,0.8847229,0.08762094],"study_design_scores_gemma":[0.001654571,0.0001833238,0.001445042,0.0004074277,0.0003686443,0.000005287706,0.002698885,0.001283307,0.0006329818,0.0259307,0.9650999,0.0002899826],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.3412751,0.07468713,0.038223,0.2604835,0.01957994,0.04233643,0.0008432989,0.0002003072,0.2223713],"genre_scores_gemma":[0.2610711,0.0009510142,0.01124914,0.006314315,0.003686136,0.0009369288,0.00005716753,0.00006034895,0.7156739],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.4933026,"threshold_uncertainty_score":0.9983838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.952134657605543,"score_gpt":0.6958360006416626,"score_spread":0.2562986569638804,"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."}}