{"id":"W4384664219","doi":"10.1109/tpami.2023.3296446","title":"Flow-Based Spatio-Temporal Structured Prediction of Motion Dynamics","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Curse of dimensionality; Autoregressive model; Generative model; Probabilistic logic; Time series; Trajectory; Probability distribution; Prior probability; Machine learning; Bayesian probability; Pattern recognition (psychology); Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002805981,0.0001856891,0.0003281525,0.0008752155,0.0001880835,0.00008415567,0.0002968027,0.00007237408,0.0001234112],"category_scores_gemma":[0.000005528535,0.0001657414,0.0003136584,0.002691525,0.00005857498,0.0002201842,0.000006002287,0.0001661863,0.0000105079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003987486,"about_ca_system_score_gemma":0.00001836245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001025777,"about_ca_topic_score_gemma":0.003623584,"domain_scores_codex":[0.998465,0.00007046144,0.0004915479,0.0004400828,0.0003316411,0.0002012354],"domain_scores_gemma":[0.9990857,0.00007662294,0.0001907716,0.0004453774,0.0001151057,0.00008647527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007891031,0.00004369622,0.003257787,0.00001666175,0.0002345903,0.000002332934,0.0001206359,0.4685282,0.00005809987,0.00005630918,0.000003317349,0.5276705],"study_design_scores_gemma":[0.0000787462,0.00009805281,0.005137213,0.00001466804,0.0003032541,0.000001622087,0.00004435469,0.9764946,0.01751007,0.0001832736,0.00001107394,0.0001231066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01595334,0.0000148064,0.9831795,0.0002121317,0.000176024,0.00008716249,0.0002164579,0.0001386696,0.0000219824],"genre_scores_gemma":[0.996491,0.00004713995,0.003175099,0.00004626401,0.00001425652,0.000009583448,0.0001282723,0.000009874452,0.00007848211],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9805377,"threshold_uncertainty_score":0.6758739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01793283909350398,"score_gpt":0.239294455972538,"score_spread":0.221361616879034,"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."}}