{"id":"W4391983171","doi":"10.1039/d3dd00183k","title":"ChemGymRL: A customizable interactive framework for reinforcement learning for digital chemistry","year":2024,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Process Optimization and Integration","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; National Research Council Canada; University of Ottawa; University of Waterloo","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Modular design; Python (programming language); Computer science; Reinforcement learning; Reinforcement; Open source; Human–computer interaction; Multimedia; Programming language; Engineering; Software; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00002536803,0.0001544387,0.0001246142,0.00003904194,0.00004353045,0.001652999,0.00008250857,0.00007990191,0.00002865871],"category_scores_gemma":[0.0002879062,0.0001457402,0.0001323073,0.0001098826,0.00001668089,0.003046657,0.00002119865,0.0001415803,0.00002429482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001138743,"about_ca_system_score_gemma":0.00003331962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.351326e-7,"about_ca_topic_score_gemma":6.372318e-8,"domain_scores_codex":[0.9993449,7.024891e-7,0.0001890948,0.0001836208,0.00008555232,0.0001961268],"domain_scores_gemma":[0.9996516,0.0001504111,0.00002235655,0.00008238429,0.00004988576,0.000043373],"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":[0.0001748035,0.00005013687,0.00002281366,0.001542396,0.0002714011,0.000002156364,0.0007638019,0.9404108,0.001251994,0.01575576,0.01054919,0.02920478],"study_design_scores_gemma":[0.0002242761,0.00004988091,0.000001161451,0.0003206183,0.00001484369,0.000002688889,0.0003858352,0.9125248,0.01736216,0.004624328,0.06422126,0.0002681857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002199822,0.0002108992,0.9606944,0.00003678885,0.0002802824,0.0002712435,0.0001238382,0.0004103636,0.03577241],"genre_scores_gemma":[0.9887659,0.00002355801,0.0006571416,0.0000257947,0.0001668172,0.000224606,0.0009273122,0.00005452568,0.009154347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9865661,"threshold_uncertainty_score":0.9993834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006952982326873014,"score_gpt":0.2382086089793232,"score_spread":0.2312556266524501,"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."}}