{"id":"W4416702585","doi":"10.21203/rs.3.rs-8066940/v1","title":"ACRerNet:Implement adaptive convolution in anchor-based lane detection","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; British Columbia Innovation Council","keywords":"Robustness (evolution); Convolution (computer science); Kernel (algebra); Convolutional neural network; Rotation (mathematics); Representation (politics); Feature (linguistics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005979859,0.0008153139,0.0005477314,0.0006380292,0.0003319875,0.0008326799,0.001827443,0.0009814893,0.01265439],"category_scores_gemma":[0.001890757,0.0004685399,0.0005027144,0.0004923541,0.0002840932,0.001156188,0.001606049,0.0008089596,0.004188248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004342073,"about_ca_system_score_gemma":0.0006332727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00403465,"about_ca_topic_score_gemma":0.005129223,"domain_scores_codex":[0.9995061,0.00004951094,0.00002511621,0.000132722,0.0002046519,0.00008178286],"domain_scores_gemma":[0.9995824,0.0001010205,0.00002699815,0.0001228033,0.0001237251,0.00004314486],"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":[0.002114143,0.0003958039,0.003281921,0.0002473957,0.0001945787,0.0003053866,0.0001925897,0.03988368,0.1246836,0.008128029,0.02979876,0.7907742],"study_design_scores_gemma":[0.0001048819,0.0001785179,0.0009438784,0.00001862743,0.00002677614,0.0001516532,0.00002516904,0.8703033,0.1142034,0.002717447,0.01129373,0.00003261934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02255927,0.0001314336,0.9259278,0.00008449477,0.0001650641,0.0000892566,0.0004317413,0.04843893,0.00217217],"genre_scores_gemma":[0.2497332,0.0001037474,0.7371389,0.0001881442,0.00006079809,0.0001836439,0.00132447,0.002222269,0.009044866],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01265439,"threshold_uncertainty_score":0.04233319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05325007972574079,"score_gpt":0.3661794265783029,"score_spread":0.3129293468525621,"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."}}