{"id":"W4411268806","doi":"10.1101/2025.06.11.25329022","title":"Beyond Benchmarks: Towards Robust Artificial Intelligence Bone Segmentation in Socio-Technical Systems","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"RWTH Aachen University","keywords":"Artificial intelligence; Computer science; Segmentation; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.009817717,0.001848483,0.001388226,0.003199436,0.0008175081,0.005241686,0.003481343,0.002517458,0.003041527],"category_scores_gemma":[0.03759545,0.0006857426,0.0009115318,0.001934829,0.002672717,0.003593948,0.004260735,0.002359646,0.001394197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002138205,"about_ca_system_score_gemma":0.002307646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007674661,"about_ca_topic_score_gemma":0.005511458,"domain_scores_codex":[0.9934186,0.003260391,0.0003407691,0.001085759,0.001584844,0.0003096212],"domain_scores_gemma":[0.9849561,0.008570652,0.001412139,0.002170669,0.002403592,0.0004867952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002667801,0.0002068013,0.007657426,0.0005168709,0.0002402761,0.0001415258,0.0004800723,0.7771397,0.003438086,0.04484728,0.006754739,0.1583103],"study_design_scores_gemma":[0.000009224321,0.00004431965,0.0005063791,0.0000409247,0.00000984632,0.00001771641,0.00008703658,0.9633834,0.001245481,0.0329388,0.001706946,0.000009964865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05228075,0.001370505,0.9297847,0.00242739,0.0001726057,0.0002477166,0.0005829949,0.005898772,0.00723455],"genre_scores_gemma":[0.6004701,0.0004424356,0.39441,0.0004161609,0.0001121635,0.0002745232,0.001740142,0.0007008745,0.001433684],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009817717,"threshold_uncertainty_score":0.05192167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03650084209652377,"score_gpt":0.3020240243370009,"score_spread":0.2655231822404772,"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."}}