{"id":"W2942950293","doi":"10.1109/icra.2019.8794214","title":"DeepSignals: Predicting Intent of Drivers Through Visual Signals","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Task (project management); Frame (networking); Artificial intelligence; Deep neural networks; Artificial neural network; Real-time computing; Computer vision; Machine learning; Human–computer interaction; Telecommunications; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002098165,0.0003138943,0.0005700174,0.000121707,0.00003030231,0.00001099228,0.0004379027,0.0008000502,0.0003577634],"category_scores_gemma":[0.00003969179,0.0003110393,0.0002009867,0.00009390178,0.0001064594,0.0000829994,0.000532523,0.0009773384,0.00009213138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001140759,"about_ca_system_score_gemma":0.00005970213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003737634,"about_ca_topic_score_gemma":0.000009703846,"domain_scores_codex":[0.9986052,0.00002790145,0.0005492303,0.0003329482,0.0001739611,0.0003107534],"domain_scores_gemma":[0.9991768,0.0001095038,0.0001427095,0.000433986,0.0001007676,0.0000362333],"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":[0.00002372805,0.00009353635,0.01212866,0.001178569,0.001116025,0.00001351899,0.00172107,0.9606556,0.008331121,0.002754693,0.002494574,0.009488905],"study_design_scores_gemma":[0.0007739968,0.0002277958,0.002626862,0.0009312434,0.0002561721,0.00001320714,0.002236541,0.7868558,0.1939824,0.009014232,0.001804348,0.001277426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6530858,0.0009901434,0.2996219,0.0001192316,0.001369927,0.0007042087,0.00003931292,0.002411676,0.04165772],"genre_scores_gemma":[0.9963288,0.0002602165,0.002977337,0.00005356913,0.00005850851,0.00002301952,0.00002530875,0.00005192811,0.0002213369],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3432429,"threshold_uncertainty_score":0.9999342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01524181555818657,"score_gpt":0.2468644330544139,"score_spread":0.2316226174962273,"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."}}