{"id":"W3116263883","doi":"10.1109/iccv48922.2021.01533","title":"Prediction by Anticipation: An Action-Conditional Prediction Method based on Interaction Learning","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Huawei Technologies (Canada)","funders":"","keywords":"Anticipation (artificial intelligence); Generalization; Probabilistic logic; Computer science; Generative model; Generative grammar; Artificial intelligence; Machine learning; Action (physics); Bayesian probability; Range (aeronautics); Conditional probability distribution; Process (computing); Pedestrian; Conditional probability; Mathematics; Engineering; Econometrics; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031887,0.0003159226,0.000255465,0.0003448039,0.0002642323,0.0001902188,0.0002685453,0.0003238129,0.00254979],"category_scores_gemma":[0.00003682365,0.0003532423,0.0001252056,0.0002554446,0.00004279544,0.0006759564,0.00004186677,0.0009075514,0.0002303013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004181498,"about_ca_system_score_gemma":0.00009207642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009258994,"about_ca_topic_score_gemma":0.00001150291,"domain_scores_codex":[0.9977472,0.0002364164,0.0005283824,0.0006432302,0.0005840124,0.0002606906],"domain_scores_gemma":[0.9987819,0.0001868287,0.0001459616,0.0003260374,0.0004391055,0.0001202123],"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":[0.0002209203,0.000571351,0.0008223571,0.00002945898,0.0001904685,0.00004276835,0.0001436154,0.8192616,0.0267464,0.006090367,0.01315312,0.1327276],"study_design_scores_gemma":[0.0007096614,0.0005204592,0.004360583,0.000149134,0.00002124834,0.00003941556,0.0000826057,0.9650915,0.01762143,0.0005503405,0.01059318,0.0002604587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0835597,0.00001139845,0.9021454,0.001656136,0.0050574,0.000202135,0.0002591358,0.0008720925,0.00623656],"genre_scores_gemma":[0.9897324,0.0000729185,0.005776162,0.0003710616,0.0007506683,0.00005849359,0.002604699,0.00004309191,0.0005905495],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9061726,"threshold_uncertainty_score":0.9998919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04204573715458546,"score_gpt":0.3237950629773097,"score_spread":0.2817493258227243,"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."}}