{"id":"W4226197958","doi":"10.48550/arxiv.2204.00056","title":"SELFIES and the future of molecular string representations","year":2022,"lang":"en","type":"preprint","venue":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Austrian Science Fund; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Cheminformatics; Computer science; Artificial intelligence; Interpretability; Popularity; String (physics); Context (archaeology); Representation (politics); Interpretation (philosophy); Interface (matter); Data science; Cognitive science; Chemistry; Programming language; Mathematics; Computational chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004640879,0.000512036,0.0007510962,0.002084663,0.0008205363,0.00420107,0.001640445,0.002175503,0.006153677],"category_scores_gemma":[0.01484415,0.0004090778,0.0007293848,0.001911401,0.005314403,0.01368253,0.002653268,0.003790381,0.0018274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001574932,"about_ca_system_score_gemma":0.0009353613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000721939,"about_ca_topic_score_gemma":0.0004290541,"domain_scores_codex":[0.9975395,0.001001841,0.0001847091,0.0004208002,0.0007086702,0.0001445638],"domain_scores_gemma":[0.9927484,0.004170176,0.0004720294,0.001597143,0.0007894887,0.0002226504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003987001,0.00001358395,0.0001592908,0.0000979722,0.00001003584,0.00002611442,0.0001668551,0.006592284,0.0006568396,0.915865,0.003352771,0.07301955],"study_design_scores_gemma":[0.000007742676,0.00002277357,0.00008908242,0.00009135538,0.000008961912,0.00005322364,0.00006696093,0.0320681,0.001493718,0.9290455,0.0370299,0.00002266323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03204133,0.02675879,0.8591642,0.03175908,0.001880235,0.00008013247,0.0007685865,0.002553258,0.04499437],"genre_scores_gemma":[0.477807,0.02481351,0.4685908,0.004442219,0.002600907,0.0003476589,0.00156535,0.0009970986,0.01883537],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006153677,"threshold_uncertainty_score":0.02454358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02421626748547631,"score_gpt":0.2747418245114769,"score_spread":0.2505255570260005,"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."}}