{"id":"W3034366985","doi":"10.48550/arxiv.2004.12485","title":"Learning To Navigate The Synthetically Accessible Chemical Space Using\\n Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"BIM and Construction Integration","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; HEC Montréal","funders":"","keywords":"Reinforcement learning; Space (punctuation); Chemical space; Computer science; Reinforcement; Human–computer interaction; Artificial intelligence; Engineering; Biology; Bioinformatics","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"],"consensus_categories":[],"category_scores_codex":[0.0001050543,0.0002658672,0.0002266995,0.00008825971,0.0001689117,0.0001183527,0.0004419525,0.0002304516,0.0001301645],"category_scores_gemma":[0.00005919048,0.0002589738,0.0001433631,0.0003705416,0.0000754068,0.000107483,0.0004647262,0.001394536,0.0001170968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002362331,"about_ca_system_score_gemma":0.00006211743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005436117,"about_ca_topic_score_gemma":0.000004682282,"domain_scores_codex":[0.9989613,0.00006227088,0.0001860669,0.0004320375,0.00009385501,0.0002644935],"domain_scores_gemma":[0.9993504,0.00004904886,0.00008144218,0.0002832617,0.00008636764,0.0001494706],"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":[0.00002011481,0.000003459001,0.0004215118,0.0000572088,0.00007006645,0.00001750036,0.0003077216,0.9839993,0.004231044,0.01013221,0.00006967844,0.0006702401],"study_design_scores_gemma":[0.0001341994,0.00002378095,0.00004532046,0.000164757,0.0001053886,0.000005923355,0.0005866619,0.9881771,0.005246452,0.00118814,0.003975299,0.0003469787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6851283,0.00003013086,0.3057688,0.0002008815,0.0004894768,0.0002518346,0.000001878698,0.0005209175,0.007607783],"genre_scores_gemma":[0.9987164,0.00005049412,0.0003555636,0.00005400291,0.0001266315,0.000001927013,0.00001174048,0.00003754566,0.0006457667],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.313588,"threshold_uncertainty_score":0.9999862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04460590330305823,"score_gpt":0.1891779005994102,"score_spread":0.144571997296352,"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."}}