{"id":"W4405104540","doi":"10.2139/ssrn.5038730","title":"Retrogfn: Diverse and Feasible Retrosynthesis Using Gflownets","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Retrosynthetic analysis; Computer science; Chemistry","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":[0.001072724,0.0015377,0.0007923896,0.0009173367,0.0008519251,0.001459418,0.001767307,0.001121945,0.01697145],"category_scores_gemma":[0.001931582,0.0004949067,0.0009374419,0.000739752,0.0008204542,0.002709339,0.002210832,0.001348914,0.005739866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004582338,"about_ca_system_score_gemma":0.0007497661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000528788,"about_ca_topic_score_gemma":0.001252242,"domain_scores_codex":[0.9994367,0.0001369701,0.00002468467,0.0001747245,0.0001295671,0.00009741278],"domain_scores_gemma":[0.9992886,0.0002719707,0.00002862441,0.0002951789,0.00006679754,0.000048865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002916092,0.0003742652,0.001275137,0.001348987,0.0001990401,0.001183007,0.0003584592,0.07944861,0.1541647,0.1976561,0.02779814,0.5332775],"study_design_scores_gemma":[0.000377092,0.0008259451,0.0004494774,0.0001913683,0.0001486887,0.000728203,0.0002383946,0.2729984,0.1660593,0.4664579,0.09137448,0.0001508215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0635215,0.001197695,0.8766582,0.0006596365,0.0006130472,0.0002826984,0.002614031,0.0106246,0.04382867],"genre_scores_gemma":[0.3903403,0.0007498009,0.5893925,0.0004159182,0.0001370321,0.0003788943,0.004198452,0.002499581,0.01188745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01697145,"threshold_uncertainty_score":0.05677509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.137056112287881,"score_gpt":0.3864037975971876,"score_spread":0.2493476853093065,"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."}}