{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002007943,0.001257569,0.000848257,0.001114214,0.0003098016,0.001246402,0.001314654,0.001131937,0.001547283],"category_scores_gemma":[0.005815249,0.0003070321,0.0006537205,0.0006196062,0.0005644648,0.0009433599,0.00093382,0.0005807312,0.0007380195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001067659,"about_ca_system_score_gemma":0.0008807179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004099065,"about_ca_topic_score_gemma":0.003708914,"domain_scores_codex":[0.998293,0.0002894507,0.0001108051,0.0004658921,0.0006963629,0.0001444428],"domain_scores_gemma":[0.9983832,0.0008844074,0.0001943545,0.0001464983,0.0003425185,0.00004899302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001649249,0.0002964454,0.005901236,0.001908277,0.0004386141,0.0002868757,0.000202004,0.2878637,0.2606453,0.005493932,0.004284787,0.4310297],"study_design_scores_gemma":[0.00002674403,0.0005639459,0.002217212,0.00005404871,0.00007350841,0.0002425682,0.00006221834,0.855469,0.1347871,0.001185717,0.005253154,0.00006478365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1917561,0.008647011,0.7803097,0.0003918455,0.000317226,0.0002997969,0.00071519,0.009728161,0.007834896],"genre_scores_gemma":[0.6711833,0.001782346,0.3205993,0.0003206748,0.00004946815,0.0002736064,0.001461112,0.0003741739,0.003955961],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004099065,"threshold_uncertainty_score":0.01061916,"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."}}