{"id":"W3173541058","doi":"10.1609/aaai.v35i7.16761","title":"Learning Intuitive Physics with Multimodal Generative Models","year":2021,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Object (grammar); Human–computer interaction; Autoencoder; Motion (physics); Perception; Modality (human–computer interaction); Tactile sensor; Modalities; Generative model; Generative grammar; Deep learning; Robot","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":[0.00002141979,0.00006491538,0.00006623336,0.000005993521,0.0001289332,0.00009477818,0.0001472146,0.00001455314,0.00000920244],"category_scores_gemma":[0.00000175061,0.00004856279,0.00002056498,0.0002564252,0.00001936311,0.0003055127,0.0001139738,0.0001110575,0.00001516179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000934847,"about_ca_system_score_gemma":0.0000410406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008893658,"about_ca_topic_score_gemma":0.000007479291,"domain_scores_codex":[0.9994652,0.00002709245,0.00005592282,0.0002391011,0.00009369191,0.0001190388],"domain_scores_gemma":[0.999612,0.00003759723,0.00002371527,0.0001728482,0.0001131962,0.00004065172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.891299e-7,0.00003534826,0.0000430147,8.355688e-7,0.00001060204,0.00001001863,0.0004806194,0.2990386,0.001296196,0.655388,0.0001699073,0.04352597],"study_design_scores_gemma":[0.0001056897,0.00002786211,0.00005830699,0.000004083624,0.000001731948,0.000006042208,0.00006439957,0.9694178,0.01396816,0.01597419,0.0002850639,0.000086691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00943346,0.00001385324,0.9794056,0.0007545571,0.00001818536,0.00004912482,4.073017e-7,0.00009239941,0.01023246],"genre_scores_gemma":[0.8161861,0.000008640424,0.1817104,0.0004261433,0.00006708395,0.00001875169,0.000003340031,0.00000412197,0.001575325],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8067527,"threshold_uncertainty_score":0.1980333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02041449591591256,"score_gpt":0.2365853314907529,"score_spread":0.2161708355748403,"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."}}