{"id":"W7011720527","doi":"","title":"NeurIPS’22 Cross-Domain MetaDL Challenge:Results and lessons learned","year":2023,"lang":"en","type":"article","venue":"TU/e Research Portal","topic":"Folate and B Vitamins Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Agence Nationale de la Recherche","keywords":"Task (project management); Competition (biology); Domain (mathematical analysis); Baseline (sea); Adaptation (eye); Conjunction (astronomy); Training set","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00521449,0.0002308058,0.0004491178,0.0008993485,0.0004808983,0.0001890868,0.0003010989,0.0002190703,0.0006764538],"category_scores_gemma":[0.00173636,0.0001903726,0.0001444519,0.00150782,0.0007725263,0.0002182494,0.0005566339,0.001450126,0.001561772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005018709,"about_ca_system_score_gemma":0.0004561697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002969271,"about_ca_topic_score_gemma":0.0001236563,"domain_scores_codex":[0.994738,0.0003465354,0.0004456506,0.0008290116,0.002112482,0.001528274],"domain_scores_gemma":[0.9973774,0.0005590153,0.00004785361,0.0007814143,0.0004642998,0.0007700421],"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":[0.009905219,0.003007108,0.0317845,0.002500687,0.002003785,0.06638066,0.00803533,0.00002665926,0.1350056,0.02684967,0.4559861,0.2585147],"study_design_scores_gemma":[0.01764432,0.005979119,0.4481159,0.0004001354,0.00009639032,0.0008819781,0.006487311,0.002681844,0.008282392,0.008211714,0.5001539,0.001064932],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9045008,0.0008017212,0.00000167709,0.02137626,0.00008658679,0.0006855293,0.00009349309,0.0002281561,0.07222571],"genre_scores_gemma":[0.9436291,0.003578626,0.00006391301,0.00005339295,0.0003687914,0.00008122149,0.000197752,0.00006764047,0.05195951],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4163314,"threshold_uncertainty_score":0.9992156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2790812992901041,"score_gpt":0.5148689908232,"score_spread":0.235787691533096,"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."}}