{"id":"W3093967600","doi":"10.48550/arxiv.2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Perception; Psychology; Data science; Sociology; Computer science","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001550967,0.0002150619,0.0002465497,0.00009017943,0.0003653033,0.0002460636,0.0004825101,0.0002602652,0.000006741288],"category_scores_gemma":[0.00002525064,0.0002675015,0.00007524528,0.0002057344,0.00009150902,0.0003823482,0.001029967,0.0003468794,0.00001013679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001358103,"about_ca_system_score_gemma":0.00008722548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002528984,"about_ca_topic_score_gemma":0.00001680153,"domain_scores_codex":[0.9987163,0.00007580306,0.0001564913,0.0007618116,0.00008392542,0.0002056725],"domain_scores_gemma":[0.9991953,0.0000470384,0.0001917262,0.0002919433,0.0001791538,0.00009487531],"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":[0.00004790146,0.00004197969,0.001014613,0.0004346662,0.0001150027,0.00003057491,0.00667821,0.276655,0.0003990214,0.7126338,0.001081012,0.0008681951],"study_design_scores_gemma":[0.0007232334,0.0002120683,0.002246718,0.00003783228,0.00007918345,9.456425e-7,0.0003519927,0.9757034,0.00001466327,0.01802515,0.002218846,0.0003860271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05522892,0.00001196226,0.940413,0.002861005,0.0002061701,0.0004983207,0.000007061451,0.0001789415,0.000594623],"genre_scores_gemma":[0.9963109,0.0001203414,0.002193872,0.0001578109,0.0001606718,0.00000271818,0.00003495339,0.0000152438,0.001003527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9410819,"threshold_uncertainty_score":0.9999777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1105636904725638,"score_gpt":0.2406638957461023,"score_spread":0.1301002052735385,"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."}}