{"id":"W4390856231","doi":"10.5281/zenodo.7989955","title":"Fingerprinting and Building Large Reproducible Datasets - Artefact","year":2023,"lang":"en","type":"preprint","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Data mining","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":[0.0169755,0.001561527,0.001762552,0.003969532,0.001492786,0.004474449,0.0041866,0.003230998,0.00248524],"category_scores_gemma":[0.07508834,0.00147765,0.003860907,0.005524628,0.002573974,0.00677044,0.007282522,0.003441182,0.001672709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009266713,"about_ca_system_score_gemma":0.001932332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001257621,"about_ca_topic_score_gemma":0.001918345,"domain_scores_codex":[0.9768142,0.008647147,0.002048611,0.004667734,0.007229562,0.0005928082],"domain_scores_gemma":[0.8834087,0.04177746,0.002910827,0.06508252,0.005829738,0.0009907373],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001576764,0.0005407453,0.02110964,0.002631611,0.001712532,0.002350232,0.001398288,0.1446831,0.07216587,0.06883007,0.0614531,0.6215481],"study_design_scores_gemma":[0.0002760007,0.0004531803,0.008546744,0.000332657,0.0004011963,0.00302374,0.0005568422,0.5773759,0.1175166,0.2103937,0.08085994,0.0002634936],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01780938,0.0004594388,0.9700434,0.0006855512,0.0001884142,0.0002491682,0.003269249,0.006581106,0.0007143941],"genre_scores_gemma":[0.09742384,0.0002805372,0.8868303,0.0003041444,0.0001468071,0.000602395,0.01150827,0.001647009,0.001256667],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9830245,"threshold_uncertainty_score":0.08977616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0676906354289249,"score_gpt":0.2918482265493038,"score_spread":0.2241575911203789,"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."}}