{"id":"W3045928028","doi":"10.5445/ir/1000128111","title":"Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation","year":2020,"lang":"en","type":"article","venue":"Repository KITopen (Karlsruhe Institute of Technology)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":726,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto; Vector Institute","funders":"Office of Naval Research; Tata Steel; Austrian Science Fund; European Commission","keywords":"Computer science; String (physics); Representation (politics); Intuition; Theoretical computer science; Generative model; Artificial intelligence; Generative grammar; Machine learning; Cognitive science; Physics; Theoretical physics","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":[0.000866636,0.0006228894,0.0006018092,0.0008856196,0.0003749789,0.001496051,0.0015315,0.001543348,0.004927034],"category_scores_gemma":[0.003770076,0.0003227416,0.000812851,0.0009741213,0.001497375,0.002872401,0.002027889,0.001435441,0.001797395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000484722,"about_ca_system_score_gemma":0.0005246756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004882821,"about_ca_topic_score_gemma":0.000463571,"domain_scores_codex":[0.9992829,0.0001897074,0.00005683005,0.0001743811,0.0002416412,0.00005463729],"domain_scores_gemma":[0.9987867,0.0004301448,0.0001662752,0.0004501701,0.0001223593,0.00004419932],"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":[0.0005507647,0.0001379862,0.001632088,0.000336953,0.00008212278,0.000330581,0.0002840872,0.1965561,0.04563454,0.2918669,0.01396889,0.448619],"study_design_scores_gemma":[0.00003731056,0.0002586025,0.0004353106,0.0000857018,0.0000423359,0.0002972643,0.00007491573,0.727138,0.0355152,0.1950496,0.04099869,0.00006706161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04501054,0.001104948,0.9405452,0.0009021524,0.000263449,0.00007601207,0.001017499,0.003707868,0.007372334],"genre_scores_gemma":[0.480362,0.001262987,0.5010131,0.0007658768,0.0001669174,0.0002870702,0.00293446,0.001074295,0.01213328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004927034,"threshold_uncertainty_score":0.01648259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02080048192199228,"score_gpt":0.2598707362992504,"score_spread":0.2390702543772581,"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."}}