{"id":"W6910551761","doi":"10.48448/86bh-9021","title":"Can Language Models Serve as Text-Based World Simulators?","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Merck Canada Inc. (Canada)","funders":"","keywords":"Benchmarking; Context (archaeology); Key (lock); Benchmark (surveying); Virtual world; Work (physics); Language model","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001196703,0.0008078777,0.0006385567,0.00407749,0.0001797805,0.0005876126,0.002006878,0.0002930574,0.004666511],"category_scores_gemma":[0.0001663769,0.0007179286,0.0001861874,0.005534387,0.00168215,0.0002747766,0.0004435584,0.0008349546,0.03112071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008881659,"about_ca_system_score_gemma":0.002594142,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.006827353,"about_ca_topic_score_gemma":0.03278959,"domain_scores_codex":[0.9941616,0.00008575345,0.0004926358,0.001819226,0.002186117,0.00125467],"domain_scores_gemma":[0.9971255,0.00009190556,0.0003423806,0.001696273,0.0001651479,0.0005787833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000305881,0.000341329,0.00004981912,0.0004527985,0.0001463579,0.0006003746,0.001044143,0.04323833,0.002739986,0.04168451,0.9066023,0.003069428],"study_design_scores_gemma":[0.0008758219,0.0001245766,0.000004520303,0.001489893,0.0002282647,0.00001782273,0.0005014755,0.6792644,0.001330312,0.01353166,0.3006704,0.001960865],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0005495631,0.00218098,0.0004977122,0.0008187903,0.001300505,0.0009920888,0.001400156,0.003077048,0.9891831],"genre_scores_gemma":[0.2593085,0.00000298546,0.003226151,0.0009975773,0.0005947378,0.00002990639,0.000169967,0.001979833,0.7336903],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6360261,"threshold_uncertainty_score":0.9997863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02412718222446021,"score_gpt":0.3182231397096635,"score_spread":0.2940959574852033,"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."}}