{"id":"W3118624083","doi":"10.1609/aaai.v35i7.16761","title":"Learning Intuitive Physics with Multimodal Generative Models","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Music Technology and Sound Studies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Object (grammar); Computer vision; Human–computer interaction; Autoencoder; Motion (physics); Perception; Tactile sensor; Modality (human–computer interaction); Generative model; Modalities; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009076435,0.0008804351,0.0008555615,0.0008113675,0.0003815673,0.001205281,0.00105582,0.001339899,0.003329761],"category_scores_gemma":[0.004122966,0.001092511,0.001358639,0.0004407976,0.001229362,0.001548233,0.001750015,0.001755027,0.0003664313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001040805,"about_ca_system_score_gemma":0.0006057766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006185147,"about_ca_topic_score_gemma":0.008799714,"domain_scores_codex":[0.9997149,0.0001093986,0.000009072558,0.00008602773,0.00004976966,0.00003075492],"domain_scores_gemma":[0.9984691,0.00121778,0.00009764171,0.00009391204,0.00006506921,0.00005646317],"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":[0.00004276691,0.00002966257,0.000894457,0.00005308944,0.00005625026,0.00006853407,0.0001064596,0.939123,0.001064229,0.03375574,0.000877575,0.02392828],"study_design_scores_gemma":[0.000004329704,0.000006033581,0.00005880163,0.000003913148,0.00000254178,0.000006518751,0.000004696019,0.982712,0.00005912355,0.01696808,0.0001709236,0.000002945961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03111576,0.0002714891,0.9650325,0.0004670917,0.00003301222,0.00003611541,0.0001450866,0.0005902194,0.002308707],"genre_scores_gemma":[0.8485339,0.0004213498,0.1443871,0.0003760119,0.0001145528,0.0002313559,0.0004522966,0.0002573355,0.005226065],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006185147,"threshold_uncertainty_score":0.01229829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08675555381351376,"score_gpt":0.2865257242889408,"score_spread":0.1997701704754271,"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."}}