{"id":"W2772390091","doi":"10.1007/s11263-019-01165-5","title":"Learning from Longitudinal Face Demonstration—Where Tractable Deep Modeling Meets Inverse Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"International Journal of Computer Vision","topic":"Face recognition and analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Face (sociological concept); Reinforcement learning; Convolutional neural network; Path (computing); Deep learning; Probabilistic logic; Generative model; Machine learning; Bayesian probability; Trajectory; Generative grammar","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006974738,0.0003594169,0.0005598891,0.0006537215,0.0001432123,0.001199145,0.001889634,0.0002502139,0.0001487854],"category_scores_gemma":[0.00006405019,0.0003425638,0.0005582063,0.0001617576,0.00002496231,0.001315502,0.00128754,0.001691829,0.0001135392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003009465,"about_ca_system_score_gemma":0.0002712613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009813979,"about_ca_topic_score_gemma":0.00001896037,"domain_scores_codex":[0.9961422,0.0002530313,0.001191734,0.0005469603,0.001600853,0.0002652232],"domain_scores_gemma":[0.9964373,0.0001975278,0.001458987,0.000298855,0.001427982,0.0001794119],"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":[0.00003805209,0.00006741309,0.0006330748,0.0000166011,0.0004539383,0.00009627318,0.0005915376,0.9438137,0.0002160367,0.0001112027,0.0002133993,0.05374872],"study_design_scores_gemma":[0.0007531,0.0002198033,0.0001832194,0.0009874187,0.00006833095,0.00008263173,0.00008754494,0.9949484,0.0001617408,0.0007550967,0.001424602,0.000328097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07251315,0.000357922,0.9221945,0.001576387,0.002914795,0.0001102319,0.000001808927,0.00006500352,0.0002662296],"genre_scores_gemma":[0.9215403,0.0007218996,0.07655998,0.0001445706,0.0007660497,0.000002041369,0.00006946342,0.00002066433,0.0001750423],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8490272,"threshold_uncertainty_score":0.9999027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02653599767657171,"score_gpt":0.2850311849948104,"score_spread":0.2584951873182387,"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."}}