{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001063052,0.00008603956,0.0001004521,0.00004325875,0.0003482694,0.0001218747,0.000148539,0.00007359283,0.00001075806],"category_scores_gemma":[0.0000190791,0.0001051703,0.00003140921,0.0002589819,0.000052371,0.000505432,0.0001602016,0.00008013416,0.000006947454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005974155,"about_ca_system_score_gemma":0.00004489171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007229028,"about_ca_topic_score_gemma":0.00002349454,"domain_scores_codex":[0.9993307,0.00004802159,0.00008056272,0.0003426242,0.00004895395,0.0001491113],"domain_scores_gemma":[0.9995224,0.000038438,0.00005621367,0.0001605724,0.000172997,0.00004940357],"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":[0.00001522685,0.00004078712,0.002213889,0.00005762849,0.00003465892,0.00003509952,0.002780932,0.04489533,0.001916557,0.9464908,0.0004690234,0.00105003],"study_design_scores_gemma":[0.001515732,0.0002528288,0.009148941,0.00001957005,0.00005206428,0.000005824309,0.001263038,0.9714877,0.0002142944,0.008796099,0.006897051,0.0003468354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1901025,0.00001010567,0.8076829,0.001188109,0.00007780163,0.0001192242,0.000001217198,0.00006723416,0.0007509597],"genre_scores_gemma":[0.9952587,0.00005666523,0.001485901,0.0001250627,0.00005512519,6.526108e-7,0.000008155811,0.000005862027,0.003003832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9376947,"threshold_uncertainty_score":0.4288721,"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."}}