{"id":"W2170646669","doi":"10.5194/isprsannals-ii-3-79-2014","title":"Scene-Layout Compatible Conditional Random Field for Classifying Terrestrial Laser Point Clouds","year":2014,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Conditional random field; Point cloud; Discriminative model; CRFS; Computer science; Artificial intelligence; Laser scanning; Classifier (UML); A priori and a posteriori; Random field; Locality; Graphical model; Pattern recognition (psychology); Mathematics; Laser; Statistics","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":[0.001243855,0.0001436273,0.0002164614,0.00008586881,0.0007100632,0.0001836551,0.0002265978,0.00007866922,0.00002197765],"category_scores_gemma":[0.0005841202,0.0001021604,0.0001396303,0.0003679845,0.0005371273,0.000224227,0.0001015166,0.0001142065,0.0000112748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001432832,"about_ca_system_score_gemma":0.00002855334,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06187376,"about_ca_topic_score_gemma":0.005126699,"domain_scores_codex":[0.9985204,0.0001024674,0.0004600272,0.0001925285,0.0004464541,0.0002780912],"domain_scores_gemma":[0.9988294,0.0004259819,0.000363256,0.0002321869,0.00005378828,0.00009538911],"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":[0.00009114287,0.00001312834,0.0003077515,0.00001227347,0.0000101774,3.717571e-8,0.0004018436,0.004332547,0.001166244,0.00001828981,0.003987989,0.9896586],"study_design_scores_gemma":[0.0006750129,0.0001394039,0.001558162,0.00004390081,0.00001359338,0.000008349872,0.0002011481,0.9449447,0.02811821,0.003129265,0.02102221,0.0001460847],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1563723,0.000005952893,0.8320364,0.004071344,0.0004119849,0.0004674199,0.00001815731,0.00003560545,0.006580808],"genre_scores_gemma":[0.9933148,0.000008536142,0.004700474,0.001818494,0.00009403078,3.350955e-7,0.00001559032,0.000005035897,0.00004267227],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9895125,"threshold_uncertainty_score":0.9443733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04015097871206972,"score_gpt":0.3013347659142,"score_spread":0.2611837872021303,"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."}}