{"id":"W3133261350","doi":"","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Task (project management); Computer science; Perception; Benchmark (surveying); Social intelligence; Human–computer interaction; Artificial intelligence; Human intelligence; Intelligent agent; Knowledge management; Data science; Psychology; Engineering; Social psychology","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":[0.00582766,0.001258802,0.0009696573,0.0005045511,0.001282043,0.002199191,0.002075882,0.002963025,0.003440544],"category_scores_gemma":[0.02919288,0.0004084609,0.0007489056,0.0003921377,0.002724348,0.00484169,0.004691558,0.002738305,0.001352686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001270095,"about_ca_system_score_gemma":0.001495791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004603507,"about_ca_topic_score_gemma":0.004926256,"domain_scores_codex":[0.9916809,0.005471017,0.0002799572,0.001104181,0.001175094,0.0002888383],"domain_scores_gemma":[0.9793653,0.01262033,0.001068339,0.003426799,0.001386469,0.002132579],"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":[0.003124324,0.005704275,0.03188486,0.003411466,0.000692414,0.0007740424,0.006197098,0.2614747,0.02526963,0.05075198,0.09375185,0.5169635],"study_design_scores_gemma":[0.0005769595,0.004151502,0.01925237,0.0003500478,0.0001192174,0.0008361341,0.005247478,0.716012,0.02245962,0.1400115,0.09066201,0.000321201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5998609,0.005042514,0.3343049,0.01329931,0.001377494,0.001638793,0.003636122,0.006127564,0.03471237],"genre_scores_gemma":[0.8681168,0.0006041285,0.121829,0.001248715,0.0001454417,0.0007473466,0.003092064,0.0003494842,0.00386703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00582766,"threshold_uncertainty_score":0.03082001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07150864535425586,"score_gpt":0.2259253734584515,"score_spread":0.1544167281041957,"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."}}