{"id":"W4408629203","doi":"10.26434/chemrxiv-2024-zvcb4-v4","title":"3D2SMILES: Translating Physical Molecular Models into Digital DeepSMILES Notations Using Deep Learning","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Notation; Computer science; Deep learning; Artificial intelligence; Natural language processing; Mathematics; Arithmetic","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":[0.0005701149,0.001742972,0.0006706949,0.001099492,0.00032809,0.002036517,0.002863261,0.001364491,0.007071703],"category_scores_gemma":[0.002013351,0.000614484,0.001754233,0.0007725496,0.0006149078,0.002310506,0.001869632,0.00186565,0.003279763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001232441,"about_ca_system_score_gemma":0.0008930315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007052877,"about_ca_topic_score_gemma":0.01229571,"domain_scores_codex":[0.9997563,0.00004380993,0.0000152895,0.00007226517,0.000083254,0.00002903364],"domain_scores_gemma":[0.9996145,0.0001434972,0.00003238174,0.0001130378,0.00006497812,0.0000316487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003502113,0.0003086206,0.002363052,0.0008066065,0.0002656903,0.0004130132,0.0001849226,0.5723165,0.01788196,0.02703524,0.05021101,0.327863],"study_design_scores_gemma":[0.00002067039,0.00003819264,0.0001229452,0.00002738223,0.00001066659,0.00004299346,0.00001678526,0.9764317,0.006978877,0.008995481,0.007300389,0.00001393006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04442437,0.001086886,0.8656192,0.0009346069,0.0003834548,0.0002883499,0.006880912,0.07001217,0.01036992],"genre_scores_gemma":[0.3213743,0.001330356,0.6431804,0.0009260317,0.00008408644,0.0006034723,0.01954086,0.003502635,0.009457885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007071703,"threshold_uncertainty_score":0.0236572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02126373074935713,"score_gpt":0.2989196104639774,"score_spread":0.2776558797146202,"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."}}