{"id":"W7131658085","doi":"10.5220/0014376400004918","title":"Evaluating Vision-Based Object Recognition Algorithms for Autonomous Vehicles with Varying Environmental Conditions: A Benchmark Study","year":2025,"lang":"","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Object (grammar); Cognitive neuroscience of visual object recognition; Noise (video); Pattern recognition (psychology); Feature (linguistics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001164276,0.0006903514,0.000705299,0.0005775451,0.001222867,0.0001266469,0.0003730601,0.0004996334,0.0008052446],"category_scores_gemma":[0.0001010859,0.0007012821,0.0002196748,0.0005452591,0.0002928949,0.0003727534,0.0001171137,0.0006966503,0.00007328548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007684559,"about_ca_system_score_gemma":0.0003825952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005196659,"about_ca_topic_score_gemma":0.0000307642,"domain_scores_codex":[0.9965166,0.0001956888,0.001062201,0.001059305,0.0003488046,0.0008173939],"domain_scores_gemma":[0.9977747,0.001134575,0.0002225419,0.0006741915,0.00008059111,0.0001134005],"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":[0.001104205,0.004445544,0.009615635,0.0006343168,0.002491362,0.00006650748,0.001420978,0.1650789,0.01206343,0.0003222734,0.0003094836,0.8024473],"study_design_scores_gemma":[0.008697788,0.004161131,0.01401892,0.0005374899,0.001040934,0.00001203658,0.002793484,0.9535191,0.01174758,0.002308926,0.0001427931,0.00101982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8663615,0.0007959795,0.1198102,0.0005383351,0.0005659942,0.006745163,0.0004770751,0.001303299,0.00340242],"genre_scores_gemma":[0.9630865,0.00002926879,0.03432586,0.0002522112,0.00006559263,0.00144446,0.0003671527,0.00008814843,0.000340815],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8014275,"threshold_uncertainty_score":0.9995438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02449752033413881,"score_gpt":0.3081456771123923,"score_spread":0.2836481567782534,"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."}}