{"id":"W4391448089","doi":"10.55458/neurolibre.00023","title":"Paper is not enough: Crowdsourcing the T1 mappingcommon ground via the ISMRM reproducibility challenge","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Hospital; McGill University; Philips (Canada); Hôpital Maisonneuve-Rosemont; McGill University Health Centre; University of British Columbia","funders":"","keywords":"Crowdsourcing; Reproducibility; Common ground; Data science; Computer science; Statistics; Psychology; Mathematics; World Wide Web; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00325359,0.0004509786,0.0003393482,0.00002636997,0.0005415692,0.0003690686,0.001189054,0.0002446808,0.005864101],"category_scores_gemma":[0.0001939874,0.0002488601,0.0002493595,0.0001757891,0.0004343656,0.00006754493,0.007187252,0.001513809,0.001745048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002865397,"about_ca_system_score_gemma":0.0000317464,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01350075,"about_ca_topic_score_gemma":0.001620553,"domain_scores_codex":[0.9958481,0.0001917837,0.0005528493,0.002201986,0.0006794396,0.0005258779],"domain_scores_gemma":[0.9950482,0.0003566274,0.0001878749,0.004294897,0.00001990197,0.00009254051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001087676,0.000796123,0.004097487,0.001464558,0.0009144224,0.0001671578,0.1058123,0.01005775,0.008445849,0.02236677,0.2310256,0.6147432],"study_design_scores_gemma":[0.0002540724,0.00008625763,0.073097,0.0002790861,0.0003289987,0.00004113639,0.00251847,0.02088104,0.001525651,0.2979586,0.6014842,0.001545574],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2920527,0.004218275,0.00661132,0.2278821,0.00603209,0.0036093,0.0001861338,0.0007023221,0.4587058],"genre_scores_gemma":[0.9851981,0.0003034783,0.0008295242,0.004863797,0.0004812973,0.0001476571,0.00001595887,0.00005715287,0.008103004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6931454,"threshold_uncertainty_score":0.9999964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03481400893182039,"score_gpt":0.2590818146967644,"score_spread":0.224267805764944,"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."}}