{"id":"W2946704039","doi":"10.65109/xthn2283","title":"Meta-learning for Predictive Knowledge Architectures: A Case Study Using TIDBD on a Sensor-rich Robotic Arm","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Computer science; Machine learning; Representation (politics); Meta learning (computer science); Robotics; Key (lock); Temporal difference learning; Feature learning; Robot; Reinforcement learning; 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":[0.001313975,0.0005704138,0.0005935294,0.0003836985,0.0006773601,0.001285783,0.001836629,0.001976494,0.002531316],"category_scores_gemma":[0.003427998,0.0003016614,0.0004265228,0.0005029999,0.001019234,0.001484458,0.001438746,0.001414664,0.0003518357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001231607,"about_ca_system_score_gemma":0.0009650338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007164915,"about_ca_topic_score_gemma":0.00869243,"domain_scores_codex":[0.9995409,0.0001373096,0.00003495589,0.0001169092,0.0001177012,0.00005223579],"domain_scores_gemma":[0.9983854,0.001013238,0.00008504037,0.0002668285,0.0001676119,0.00008189342],"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":[0.0003936373,0.0004270293,0.002522525,0.0002611135,0.00006679817,0.0009465846,0.0004529312,0.8487939,0.007971654,0.007684337,0.0009310062,0.1295485],"study_design_scores_gemma":[0.00002983152,0.0001853406,0.0003955186,0.00001366036,0.00001568556,0.00008987185,0.00007470141,0.9880619,0.005135947,0.004236922,0.00174654,0.00001404214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4695542,0.0008219091,0.5141643,0.001424282,0.00006611562,0.0003579505,0.0002706463,0.002684473,0.01065607],"genre_scores_gemma":[0.8981655,0.0001263066,0.09849581,0.0000835077,0.000009584596,0.00009956358,0.00008989382,0.00004542331,0.002884345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007164915,"threshold_uncertainty_score":0.01424646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04605331356600618,"score_gpt":0.2874396850777456,"score_spread":0.2413863715117394,"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."}}