{"id":"W4408614039","doi":"10.1021/acs.jctc.4c01780","title":"Comparative Analysis of Reinforcement Learning Algorithms for Finding Reaction Pathways: Insights from a Large Benchmark Data Set","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Theory and Computation","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Japan Society for the Promotion of Science","keywords":"Benchmark (surveying); Reinforcement learning; Computer science; Set (abstract data type); Data set; Machine learning; Artificial intelligence; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0004842265,0.00007910795,0.0002894104,0.0001322459,0.00004887816,0.00001290174,0.0001128216,0.00007374758,0.000002748256],"category_scores_gemma":[0.00008747166,0.00006984523,0.0001234731,0.0002351501,0.0000298514,0.00001265581,0.00007820585,0.00007868681,5.275141e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000148833,"about_ca_system_score_gemma":0.00003548063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001364351,"about_ca_topic_score_gemma":0.00000102485,"domain_scores_codex":[0.9991857,0.000126465,0.0003620216,0.0001554708,0.00009974847,0.00007062764],"domain_scores_gemma":[0.9991099,0.0001711659,0.0004030757,0.0001176747,0.0001662945,0.0000319319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007212404,0.00006340825,0.0004594459,0.00002208697,0.004065222,6.271079e-7,0.0004904562,0.05328431,0.9359681,0.00111275,0.0001749102,0.003637421],"study_design_scores_gemma":[0.001702207,0.0002860731,0.001970621,0.0001051486,0.003823224,0.000002812346,0.001677669,0.517437,0.4564492,0.01425996,0.002072015,0.0002140528],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6910083,0.0005550861,0.3082984,0.000008781798,0.00003066437,0.00004031634,0.0000117155,0.000001176079,0.00004553273],"genre_scores_gemma":[0.9969814,0.00005024389,0.001347429,0.00002745954,0.00008065402,0.000001407949,0.001494584,0.000002574113,0.00001420964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4795189,"threshold_uncertainty_score":0.2848206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0312515664154304,"score_gpt":0.3167783314802967,"score_spread":0.2855267650648663,"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."}}