{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005731852,0.001749411,0.000671369,0.001101738,0.0003292337,0.002041128,0.002879004,0.001367328,0.007071391],"category_scores_gemma":[0.002022718,0.0006161903,0.001758749,0.0007736436,0.0006164819,0.002315664,0.001876369,0.001871933,0.003287391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001237432,"about_ca_system_score_gemma":0.0008958926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007094299,"about_ca_topic_score_gemma":0.01238255,"domain_scores_codex":[0.9997548,0.00004403682,0.00001537641,0.00007271109,0.0000837523,0.0000291909],"domain_scores_gemma":[0.9996125,0.0001442853,0.00003249196,0.0001136165,0.00006527432,0.00003178602],"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":[0.0003511756,0.0003100631,0.002377566,0.0008075346,0.0002665188,0.0004130988,0.0001855251,0.5714923,0.01787509,0.02703656,0.05043147,0.3284532],"study_design_scores_gemma":[0.00002074735,0.00003825579,0.0001231547,0.00002743999,0.00001070989,0.00004291155,0.00001680361,0.9764276,0.006978179,0.008989555,0.007310649,0.00001397472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04451217,0.001090916,0.8648431,0.0009375855,0.0003847449,0.0002898598,0.00690446,0.07065048,0.01038675],"genre_scores_gemma":[0.3215742,0.001331075,0.6428852,0.0009290096,0.00008413759,0.0006049671,0.01963483,0.003513488,0.00944302],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007094299,"threshold_uncertainty_score":0.02365619,"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."}}