{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004928787,0.0003551233,0.000621899,0.0003089143,0.0003552221,0.0002345091,0.001691902,0.0003292823,0.00008886599],"category_scores_gemma":[0.0006916034,0.0003527599,0.0001158152,0.001076636,0.0003934961,0.0009276057,0.0008542067,0.0004421846,0.0001030128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001360417,"about_ca_system_score_gemma":0.0003004271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002265585,"about_ca_topic_score_gemma":0.00000586959,"domain_scores_codex":[0.9967385,0.0001210395,0.0009330715,0.0009961035,0.0006822897,0.0005290132],"domain_scores_gemma":[0.9978824,0.00003943219,0.0007308415,0.000924669,0.0002446891,0.0001779776],"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":[0.00004174675,0.00005340108,0.001507253,0.0001573017,0.00002772029,0.000198565,0.0003905699,0.01716144,0.9763092,0.003462943,0.0001452184,0.000544609],"study_design_scores_gemma":[0.0004929365,0.000200017,0.0003555075,0.0001343794,0.00006701292,0.0001206928,0.000255486,0.005141864,0.989603,0.0002104457,0.003036636,0.0003819906],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827669,0.0001373853,0.009337416,0.001109691,0.001226661,0.0005608493,0.000005585558,0.001174713,0.003680808],"genre_scores_gemma":[0.8991983,0.00001463848,0.1003748,0.00009862767,0.0001458447,0.00004246489,0.000005209933,0.00003430226,0.00008580588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09103741,"threshold_uncertainty_score":0.9998924,"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."}}