{"id":"W4382808681","doi":"10.1039/d3dd00044c","title":"Recent advances in the self-referencing embedded strings (SELFIES) library","year":2023,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of Toronto","funders":"Natural Resources Canada; Stanford Bio-X; Stanford University; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Computer science; State (computer science); Information retrieval; Data science; Algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007917057,0.001979587,0.002134377,0.004598776,0.001073754,0.007167629,0.005968702,0.002027423,0.0266076],"category_scores_gemma":[0.02168977,0.001735673,0.002394181,0.006622564,0.001610712,0.01083372,0.006673178,0.004947127,0.02955754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001322766,"about_ca_system_score_gemma":0.002587704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001483444,"about_ca_topic_score_gemma":0.001265266,"domain_scores_codex":[0.9918012,0.001428231,0.0009272884,0.001119768,0.004163687,0.0005598177],"domain_scores_gemma":[0.9853314,0.005943096,0.001148513,0.003899103,0.002912156,0.0007656578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001217094,0.0004034547,0.00226288,0.002555076,0.0002993035,0.0003020322,0.0005952784,0.004263489,0.01755429,0.1091456,0.1965768,0.6648248],"study_design_scores_gemma":[0.0001278883,0.000152088,0.0008239749,0.0003548407,0.0001402557,0.0006450274,0.00007195811,0.01793053,0.03854467,0.04915206,0.8918327,0.0002239825],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006229079,0.008919331,0.7255728,0.00146497,0.001144364,0.000278098,0.00573404,0.22527,0.02538744],"genre_scores_gemma":[0.03963783,0.01433405,0.7851456,0.003634749,0.001873664,0.0008595413,0.04610652,0.05930018,0.04910781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0266076,"threshold_uncertainty_score":0.08901131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07433177109535727,"score_gpt":0.3395356871112808,"score_spread":0.2652039160159235,"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."}}