{"id":"W4416639837","doi":"10.1061/jtepbs.teeng-9214","title":"Evaluating Semantic Segmentation–Based Scene Descriptions for Multilane Rural Highway Point Clouds against Ground Truth","year":2025,"lang":"en","type":"article","venue":"Journal of Transportation Engineering Part A Systems","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Segmentation; Ground truth; Point cloud; Transformer; Point (geometry); Robustness (evolution); Consistency (knowledge bases); Intersection (aeronautics); Visual reasoning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000458367,0.0002182497,0.0003590024,0.0003097162,0.00008555066,0.0000757396,0.0001214523,0.00008749156,0.000002760357],"category_scores_gemma":[0.0000477161,0.000210879,0.000181499,0.0002371542,0.00001096401,0.0002571014,0.000001283776,0.0001985343,8.704895e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002224379,"about_ca_system_score_gemma":0.00006678492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006995674,"about_ca_topic_score_gemma":0.000004110037,"domain_scores_codex":[0.9984215,0.00001788111,0.0009157128,0.0001071722,0.0002605784,0.0002770917],"domain_scores_gemma":[0.9991875,0.0001331145,0.0001898806,0.0001237982,0.0002877913,0.0000779285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000300101,0.0000130264,0.0002798897,0.0008010254,0.0001484965,0.000006246579,0.0003316106,0.9512078,0.04583541,0.0003090976,0.0001990344,0.0008384208],"study_design_scores_gemma":[0.002196156,0.0001019943,0.004875991,0.001887413,0.0002281764,0.00001029723,0.0007821548,0.9760901,0.01205683,0.0000298984,0.001455765,0.0002852262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4452852,0.0004992296,0.547419,0.00002275186,0.00630511,0.0003074153,0.00003524001,0.0001121671,0.00001382354],"genre_scores_gemma":[0.9806097,0.0000230933,0.01864086,0.00001353803,0.0005081319,0.00006674681,0.0000698952,0.000040809,0.00002729287],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5353244,"threshold_uncertainty_score":0.8599395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01864355470874573,"score_gpt":0.2687108066678812,"score_spread":0.2500672519591355,"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."}}