{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05276158,0.001403084,0.002170167,0.002085573,0.005142018,0.01521005,0.003613336,0.008032538,0.01939906],"category_scores_gemma":[0.2512854,0.001150399,0.002256954,0.003661441,0.006936001,0.01112404,0.01602472,0.00650182,0.01907251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002571804,"about_ca_system_score_gemma":0.008563511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01183961,"about_ca_topic_score_gemma":0.009925471,"domain_scores_codex":[0.9576645,0.01856687,0.001740112,0.008016923,0.01298237,0.001029212],"domain_scores_gemma":[0.8292251,0.08097063,0.005499925,0.05138888,0.02715054,0.005764944],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0007410113,0.0001044389,0.008757537,0.001166395,0.0006240893,0.0004698154,0.002522172,0.007583304,0.004089573,0.06136293,0.7311052,0.1814736],"study_design_scores_gemma":[0.0003658589,0.0001293613,0.007862728,0.0008968909,0.0002186766,0.0004827159,0.00287167,0.01587167,0.005435844,0.3938248,0.571698,0.0003418359],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03504467,0.01340847,0.5311453,0.2329218,0.04406619,0.001103675,0.04773158,0.01682462,0.07775377],"genre_scores_gemma":[0.3570614,0.005865733,0.3541141,0.06667592,0.01560698,0.002862975,0.09893882,0.02693515,0.07193882],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9472384,"threshold_uncertainty_score":0.2790332,"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."}}