{"id":"W2963742410","doi":"","title":"DOM-Q-NET: Grounded RL on Structured Language","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Task (project management); Machine learning; The Internet; String (physics); Graph; Natural language processing; Theoretical computer science; World Wide Web","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001707169,0.0001926039,0.0001554879,0.0002977721,0.0001944097,0.0004183274,0.001233433,0.0000751849,0.001369931],"category_scores_gemma":[0.0002951385,0.000189168,0.00009010274,0.000301985,0.00005464852,0.0003429629,0.0001848932,0.0006487385,0.002561854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001021509,"about_ca_system_score_gemma":0.00007744149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004976414,"about_ca_topic_score_gemma":0.00002342402,"domain_scores_codex":[0.9980205,0.00016649,0.0002714422,0.0006624539,0.0006439083,0.0002352282],"domain_scores_gemma":[0.9984275,0.0003359741,0.0002083935,0.0007109267,0.0002207183,0.00009646684],"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":[0.00002858221,0.0001027719,0.01172502,0.000004599687,0.00005831782,0.000008548047,0.002660741,0.02563828,0.01025158,0.9303633,0.0002536612,0.0189046],"study_design_scores_gemma":[0.00128345,0.0002845776,0.3327375,0.0000818638,0.000009285497,0.00002373076,0.0008105892,0.6405316,0.001578977,0.01725395,0.00488984,0.0005146061],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6226239,0.000007078439,0.04481931,0.01397267,0.001098545,0.0005676306,0.00001605925,0.0007184354,0.3161764],"genre_scores_gemma":[0.9865697,0.000005119861,0.004932993,0.0004285628,0.0001146383,0.00007123241,0.00009896726,0.00001961245,0.007759178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9131094,"threshold_uncertainty_score":0.999543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02162800985517141,"score_gpt":0.3421921421386386,"score_spread":0.3205641322834673,"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."}}