{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008815179,0.0005307407,0.0005232415,0.0008115828,0.0002734927,0.001195986,0.001257073,0.001305778,0.004911282],"category_scores_gemma":[0.003517328,0.0002290228,0.0005668103,0.0007452726,0.001107235,0.002205151,0.001707209,0.001259741,0.001501689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004220816,"about_ca_system_score_gemma":0.0004497429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004406336,"about_ca_topic_score_gemma":0.0003265304,"domain_scores_codex":[0.9992873,0.0001912124,0.0000545523,0.0001714712,0.0002316195,0.00006384749],"domain_scores_gemma":[0.9983902,0.0005279091,0.0002085392,0.0006452041,0.0001687035,0.00005957021],"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":[0.0006689352,0.0002082382,0.001644442,0.0002755311,0.00009129002,0.0004043079,0.0001999399,0.305969,0.07017791,0.1938129,0.01028294,0.4162644],"study_design_scores_gemma":[0.00002733001,0.0002245767,0.0003324301,0.00004343159,0.00002264805,0.0001589401,0.00003853915,0.871274,0.03328657,0.08315421,0.01139513,0.00004217016],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1185347,0.001010268,0.8634571,0.001055293,0.0003348245,0.0001021422,0.0008876637,0.004079909,0.01053813],"genre_scores_gemma":[0.7257384,0.0004931223,0.2620565,0.0006327705,0.0001193777,0.0001725433,0.001441983,0.000529811,0.008815417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004911282,"threshold_uncertainty_score":0.01642984,"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."}}