{"id":"W4416275364","doi":"10.52783/tangence.19","title":"Benchmarking YOLOv4–YOLOv11 for Autonomous Driving: Small-Object Detection, Adverse Conditions and Confidence Calibration","year":2025,"lang":"","type":"article","venue":"Tangence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Calibration; Inference; Brier score; Benchmarking; Detector; Confidence interval; Benchmark (surveying); Throughput","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0003856263,0.0004336344,0.00039436,0.0002831037,0.001561985,0.0002779822,0.000893475,0.0002304509,0.00004427841],"category_scores_gemma":[0.0002888237,0.0005196861,0.0001334329,0.001535055,0.0005056187,0.001035372,0.0004643597,0.0003524034,0.00001623975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002190897,"about_ca_system_score_gemma":0.0004092395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005715123,"about_ca_topic_score_gemma":0.0004967889,"domain_scores_codex":[0.9967732,0.0001409425,0.0007623166,0.001393456,0.0002181282,0.000711911],"domain_scores_gemma":[0.9969215,0.001069065,0.000439684,0.0009858786,0.0003610128,0.0002228691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009338496,0.0003134439,0.003588333,0.0004164585,0.0002234471,0.00002575616,0.00220342,0.02190811,0.05142827,0.5669142,0.001634092,0.3512511],"study_design_scores_gemma":[0.0006253679,0.0003009255,0.009276276,0.0003209747,0.0001575689,0.0000517464,0.000141819,0.9253746,0.01999686,0.03352671,0.00951674,0.0007104492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02307466,0.001008545,0.9697486,0.001694471,0.001366845,0.00198642,0.00004401665,0.0002896208,0.000786835],"genre_scores_gemma":[0.9631596,0.0004070371,0.03361228,0.0007963096,0.000247139,0.0007785591,0.00001920734,0.00002435403,0.000955496],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9400849,"threshold_uncertainty_score":0.9997379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01963533826006436,"score_gpt":0.2798121024682078,"score_spread":0.2601767642081435,"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."}}