{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006243998,0.001329682,0.00116824,0.002387974,0.0005270522,0.0008349897,0.001264829,0.001253588,0.0008547091],"category_scores_gemma":[0.01642456,0.0002860152,0.0008048935,0.001307809,0.0007560657,0.001297859,0.0007337441,0.00111758,0.0001674051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002054006,"about_ca_system_score_gemma":0.001620982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009845695,"about_ca_topic_score_gemma":0.008115111,"domain_scores_codex":[0.9984145,0.0007770825,0.0001287006,0.0002787815,0.0002427699,0.0001581552],"domain_scores_gemma":[0.983642,0.01346957,0.0006634626,0.0007560209,0.001192284,0.0002767311],"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":[0.0003141325,0.0002945294,0.004707709,0.0001782001,0.0001061959,0.00003247153,0.00002538226,0.9625155,0.0004302002,0.001734211,0.0009854817,0.02867594],"study_design_scores_gemma":[0.00003083346,0.0001211303,0.0007074394,0.00000766312,0.00001314835,0.000009717682,0.00001509403,0.9974642,0.0004180878,0.001036174,0.0001717307,0.000004728533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9121177,0.004975393,0.07407974,0.0008874754,0.0001283508,0.0002828438,0.00106394,0.001193905,0.005270734],"genre_scores_gemma":[0.9536452,0.0005886529,0.04320208,0.00008273772,0.00002377494,0.0001506123,0.001641827,0.00008094962,0.0005842112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009845695,"threshold_uncertainty_score":0.03302187,"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."}}