{"id":"W2952769376","doi":"10.48550/arxiv.1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Intelligence Advanced Research Projects Activity; Samsung; Nvidia","keywords":"Computer science; Task (project management); Variety (cybernetics); Representation (politics); Human–computer interaction; Interface (matter); Code (set theory); Game engine; Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":[],"category_scores_codex":[0.0002298367,0.0004014802,0.0003530354,0.0002717163,0.0003629374,0.0002934936,0.002506396,0.0003266273,0.00001960311],"category_scores_gemma":[0.00004200534,0.0004770791,0.0002141588,0.0006889025,0.0002177057,0.0004446304,0.003196988,0.0009286389,0.0001363531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002200111,"about_ca_system_score_gemma":0.0001418911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007280677,"about_ca_topic_score_gemma":0.0000344658,"domain_scores_codex":[0.9975629,0.0001809396,0.0002304092,0.001408186,0.000147063,0.0004704896],"domain_scores_gemma":[0.9971197,0.0001981546,0.0003932961,0.001979498,0.0001160929,0.0001933022],"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":[0.00002350255,0.0004039093,0.03633821,0.0001429299,0.0001934427,0.0001297218,0.001052712,0.866677,0.0002191529,0.07543692,0.0001291357,0.01925333],"study_design_scores_gemma":[0.0002611741,0.00007553476,0.004788926,0.00007715503,0.00003883706,0.000005168748,0.00003452593,0.973366,0.0001021928,0.02024621,0.0004576693,0.0005466051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4604985,0.000008922174,0.5367246,0.00007284093,0.0002276806,0.0003194821,0.0000056581,0.0008222294,0.001320115],"genre_scores_gemma":[0.9871736,0.00001026248,0.01182927,0.0000596545,0.0001845272,0.000006056541,0.00002376118,0.00004210676,0.0006707837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5266751,"threshold_uncertainty_score":0.9997681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0827059822227267,"score_gpt":0.21093085153612,"score_spread":0.1282248693133933,"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."}}