{"id":"W4410730207","doi":"10.1007/978-3-031-91585-7_18","title":"The BRAVO Semantic Segmentation Challenge Results in UNCV2024","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"European Commission","keywords":"Computer science; Segmentation; Artificial intelligence; Natural language processing; Computer vision","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":[0.0009429502,0.0002967306,0.0002482315,0.0005758051,0.0003906101,0.0004668055,0.002385792,0.0002082167,0.000002987332],"category_scores_gemma":[0.00006021066,0.0002333205,0.00008231095,0.0008889518,0.0003462251,0.0002791357,0.0008660902,0.0006425058,0.00002424645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002996859,"about_ca_system_score_gemma":0.0003415851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004783308,"about_ca_topic_score_gemma":0.0004196323,"domain_scores_codex":[0.9974129,0.00003296956,0.0005528083,0.001082329,0.0005195941,0.0003994529],"domain_scores_gemma":[0.9978073,0.0005513143,0.0002234193,0.001224813,0.0001326558,0.00006044705],"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":[0.000004628006,0.00001763436,0.000004774725,0.00001673878,0.000003953342,0.00001166573,0.0003119411,0.001943778,0.00004604211,0.0904096,0.0001035035,0.9071257],"study_design_scores_gemma":[0.0003661594,0.0001895062,0.0001836224,0.0005137729,0.000006886489,0.00001968842,9.174701e-7,0.5108182,0.002682183,0.4670761,0.01754435,0.0005985697],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001228329,0.0004008345,0.9800899,0.005950471,0.0006326781,0.0005469379,0.000004128682,0.0001777072,0.01218505],"genre_scores_gemma":[0.4301359,0.002158116,0.5501791,0.003301362,0.000733836,0.000254253,0.00001995461,0.00006674622,0.0131507],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9065272,"threshold_uncertainty_score":0.9514534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0150621976276409,"score_gpt":0.2642194236241006,"score_spread":0.2491572259964597,"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."}}