{"id":"W4416176098","doi":"10.1039/d5sc05004a","title":"Grammar-driven SMILES standardization with <i>TokenSMILES</i>","year":2025,"lang":"en","type":"article","venue":"Chemical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Centro de Investigación y de Estudios Avanzados del Instituto Politécnico Nacional","keywords":"Parsing; Redundancy (engineering); Syntax; Standardization; Scalability; Consistency (knowledge bases); Semantics (computer science); Implementation","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":[],"consensus_categories":[],"category_scores_codex":[0.001046985,0.0001798538,0.0002125723,0.0001230495,0.0004385064,0.00042783,0.001230495,0.00005724084,0.0003419247],"category_scores_gemma":[0.0005722399,0.0001304867,0.00002861793,0.001440265,0.0020112,0.0004827298,0.0003570584,0.0001362835,0.000111924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001691782,"about_ca_system_score_gemma":0.0004076652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000397598,"about_ca_topic_score_gemma":0.000004305917,"domain_scores_codex":[0.997527,0.00004861386,0.0002635457,0.0007379029,0.0008378648,0.0005850816],"domain_scores_gemma":[0.9988915,0.00009777226,0.0001111654,0.000483741,0.0002528515,0.0001629591],"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":[0.00002682645,0.00002157586,0.00121501,0.00002059906,8.330833e-7,0.000003727552,0.00010156,0.001619875,0.9929207,0.00312656,0.0003827051,0.0005600267],"study_design_scores_gemma":[0.0002469483,0.00003383462,0.00106844,0.00007991103,0.000006715159,0.000009152624,0.00003478467,0.003910512,0.9880908,0.00102701,0.005289355,0.0002025278],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.934566,0.00003448183,0.05154234,0.0006639178,0.000497931,0.0002002175,0.00001144069,0.000259069,0.01222465],"genre_scores_gemma":[0.973033,0.000004437069,0.0261644,0.0004736111,0.0000536293,0.00002127696,0.000003342748,0.000008421343,0.000237909],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03846702,"threshold_uncertainty_score":0.741035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00302477281127441,"score_gpt":0.2426292945020754,"score_spread":0.239604521690801,"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."}}