{"id":"W7117693941","doi":"10.3390/act15010016","title":"Benchmarking Robust AI for Microrobot Detection with Ultrasound Imaging","year":2025,"lang":"en","type":"article","venue":"Actuators","topic":"Micro and Nano Robotics","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation","funders":"","keywords":"Benchmarking; Robustness (evolution); Detector; Fidelity; Object detection; Speckle pattern; Sensitivity (control systems)","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":[],"consensus_categories":[],"category_scores_codex":[0.00006945401,0.0001248749,0.0001186052,0.00007166604,0.0001969714,0.00006753515,0.0000849706,0.0000216038,0.00007124821],"category_scores_gemma":[0.000004474718,0.0001088659,0.00006474505,0.0001612072,0.00002867827,0.0001043609,0.0000167192,0.00009379006,0.00000469171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003356025,"about_ca_system_score_gemma":0.0000622027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001003063,"about_ca_topic_score_gemma":0.00001961723,"domain_scores_codex":[0.9994043,0.000009852066,0.0001238565,0.0001957525,0.00004785318,0.0002183876],"domain_scores_gemma":[0.9996096,0.0001050896,0.00005312835,0.0001442974,0.00005550664,0.00003235284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000163096,0.0002327324,0.3313427,0.0001110157,0.0005116079,0.000001785119,0.000656451,0.003470961,0.1046109,0.01213916,0.01132002,0.5354396],"study_design_scores_gemma":[0.004707956,0.0002135675,0.01398859,0.0004015863,0.0006667797,0.0000103166,0.001874467,0.009168527,0.8778368,0.01269896,0.0769618,0.00147067],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1164335,0.00003042417,0.8811033,0.00008962902,0.0002601306,0.0002177042,0.000007673008,0.00002947618,0.001828176],"genre_scores_gemma":[0.9939791,0.000001103167,0.005236921,0.000176347,0.0001821068,0.0000223738,0.00002503897,0.00001493146,0.0003620988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8775456,"threshold_uncertainty_score":0.4439423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004378345485722055,"score_gpt":0.2262915971569606,"score_spread":0.2219132516712386,"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."}}