{"id":"W4404506028","doi":"10.26434/chemrxiv-2024-zvcb4-v3","title":"3D2SMILES: Translating Physical Molecular Models into Digital DeepSMILES Notations Using Deep Learning","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Notation; Computer science; Natural language processing; Artificial intelligence; Deep learning; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006395886,0.0006524746,0.0007029269,0.0002241391,0.0004025073,0.001882908,0.001050053,0.0003063252,0.0001673204],"category_scores_gemma":[0.0003747266,0.0006449663,0.0003413417,0.0003528286,0.00039557,0.0004485906,0.001610725,0.001341572,0.0004043255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001979224,"about_ca_system_score_gemma":0.0002685249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001445674,"about_ca_topic_score_gemma":0.000005859418,"domain_scores_codex":[0.9961566,0.000193622,0.0006709117,0.001484963,0.0007887761,0.0007051593],"domain_scores_gemma":[0.9983938,0.0001821959,0.0003591876,0.0006916629,0.0001641809,0.0002090206],"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":[0.00000498871,0.00003002484,0.00002553751,0.0004133955,0.0000136135,0.00002838539,0.004689714,0.5043083,0.4887786,0.0009023238,0.000003627855,0.0008015041],"study_design_scores_gemma":[0.0001020817,0.000023429,0.000008133918,0.0004765551,0.00009491614,0.00001478903,0.0003275827,0.7990772,0.0955322,0.1036783,0.00002993501,0.0006349136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8703665,0.0005648227,0.124619,0.0001629127,0.0009776967,0.00033256,0.00001293456,0.0006738182,0.002289735],"genre_scores_gemma":[0.9557928,0.000006997362,0.04335288,0.00004269707,0.0004561478,0.00007419335,0.00005871695,0.00014257,0.00007297708],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3932464,"threshold_uncertainty_score":0.9996002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02188401366898515,"score_gpt":0.2960103563065681,"score_spread":0.274126342637583,"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."}}