{"id":"W3113563511","doi":"10.1007/978-3-030-01258-8_25","title":"End-to-End Deep Structured Models for Drawing Crosswalks","year":2018,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Schema crosswalk; Leverage (statistics); Computer science; Lidar; Artificial intelligence; Convolutional neural network; Pedestrian; Computer vision; Automation; Geography; Remote sensing; Transport engineering; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005897454,0.003336214,0.002333882,0.001248391,0.0008555028,0.00325388,0.005111697,0.003941655,0.01956167],"category_scores_gemma":[0.00334001,0.002454667,0.003131991,0.001594785,0.0007823525,0.00296968,0.003763733,0.006078991,0.009407083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001423566,"about_ca_system_score_gemma":0.002085606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01425633,"about_ca_topic_score_gemma":0.03729818,"domain_scores_codex":[0.9993731,0.00006542855,0.00003108243,0.0002701572,0.0001659721,0.00009428778],"domain_scores_gemma":[0.9988995,0.0003078397,0.00005897414,0.0003674779,0.0002199102,0.0001462773],"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":[0.0003768724,0.0002451092,0.0008776278,0.0002002547,0.0001678441,0.0001918418,0.0001373002,0.6497217,0.006826426,0.01123895,0.02417597,0.3058402],"study_design_scores_gemma":[0.0000107499,0.00001747663,0.00003454819,0.000010495,0.000006265491,0.00001755963,0.00001113108,0.9922804,0.001176483,0.005297597,0.001130406,0.000006966196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006891279,0.0001779632,0.9794456,0.0001887898,0.0001079297,0.00009376662,0.001061208,0.01047086,0.001562568],"genre_scores_gemma":[0.1827637,0.0004675332,0.7918253,0.0005227167,0.0001200017,0.0003318021,0.0092622,0.003141359,0.01156548],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01956167,"threshold_uncertainty_score":0.06544036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01708518583944227,"score_gpt":0.2699851509327337,"score_spread":0.2528999650932914,"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."}}