{"id":"W4404781933","doi":"10.18653/v1/2024.findings-emnlp.202","title":"Enhancing Agent Learning through World Dynamics Modeling","year":2024,"lang":"en","type":"article","venue":"","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Dynamics (music); Artificial intelligence; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000974957,0.0006234727,0.0009077049,0.0004556752,0.00040019,0.00101568,0.001181544,0.001059734,0.001807757],"category_scores_gemma":[0.00708485,0.0004039106,0.0004722261,0.0003454059,0.0004949669,0.002279773,0.00172926,0.001197479,0.0003336335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000726356,"about_ca_system_score_gemma":0.0006989824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003341138,"about_ca_topic_score_gemma":0.004351694,"domain_scores_codex":[0.9996092,0.0001597343,0.00001426473,0.00007936766,0.00009230494,0.00004510212],"domain_scores_gemma":[0.9963923,0.002856826,0.0001960274,0.0002081843,0.0002259438,0.0001207144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008521428,0.000234968,0.002194392,0.00005599158,0.00006223124,0.000046629,0.00009899577,0.925905,0.002058553,0.01746136,0.001070457,0.0507262],"study_design_scores_gemma":[0.000003416381,0.000005628804,0.00002649828,7.664425e-7,0.000002754554,0.000001920375,0.000002320492,0.9971076,0.0001754393,0.002597855,0.00007510743,7.914744e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1205729,0.0002261697,0.8721058,0.0007651856,0.00007229886,0.00006421311,0.00005852104,0.0006083981,0.005526521],"genre_scores_gemma":[0.9219127,0.0001437177,0.07530791,0.0001307189,0.00004203999,0.00007771148,0.00007935106,0.00006113971,0.002244618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003341138,"threshold_uncertainty_score":0.006643355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01672674798537873,"score_gpt":0.2935096321556399,"score_spread":0.2767828841702612,"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."}}