{"id":"W3009321976","doi":"10.1088/2632-2153/aba947","title":"Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":596,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Office of Naval Research","keywords":"String (physics); Intuition; Representation (politics); Interpretation (philosophy); Task (project management); Generative model","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":[0.001796434,0.0003005696,0.0003919695,0.0005498074,0.0009817964,0.0005268979,0.001239057,0.0001608817,0.0002162975],"category_scores_gemma":[0.00375578,0.0002796632,0.00003384711,0.003021535,0.0009133753,0.0006911394,0.001009144,0.0007077724,0.0001367542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009405947,"about_ca_system_score_gemma":0.0002579745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001653371,"about_ca_topic_score_gemma":0.000007297108,"domain_scores_codex":[0.9964004,0.0001621525,0.0004517807,0.001264905,0.0009155364,0.0008052511],"domain_scores_gemma":[0.9985799,0.00009609911,0.0003304093,0.000429699,0.0003123744,0.000251582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001516132,0.00001997589,0.009794565,0.00004676914,0.000004438455,0.00004423847,0.001006426,0.007683584,0.9725487,0.006041454,0.00001803635,0.00277669],"study_design_scores_gemma":[0.0008285468,0.0006498785,0.001259949,0.00005838949,0.00004053882,0.0001709502,0.001145747,0.3550394,0.6363599,0.001340522,0.002394377,0.0007118171],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827929,0.0001602432,0.009107267,0.004950691,0.0001857841,0.0002738212,0.00000270652,0.001540617,0.0009859506],"genre_scores_gemma":[0.9644852,0.00002624067,0.0349891,0.0003502428,0.00005375462,0.00002079056,0.000003146204,0.00002696415,0.00004459679],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3473558,"threshold_uncertainty_score":0.9999655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01531151723872452,"score_gpt":0.2579600195144782,"score_spread":0.2426485022757537,"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."}}