{"id":"W7117144563","doi":"10.1016/j.coche.2025.101217","title":"The elephant in the lab: synthesizability in generative small-molecule design","year":2025,"lang":"en","type":"article","venue":"Current Opinion in Chemical Engineering","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Resources Canada; University of Toronto; Canada First Research Excellence Fund; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Generative grammar; Key (lock); Pace; Generative Design; Generative model","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002688074,0.0001618112,0.0001844784,0.00009012231,0.00005579426,0.0001312874,0.0007657454,0.00005796407,0.00001772862],"category_scores_gemma":[0.001840778,0.0001055868,0.00002976731,0.0005601036,0.00009309431,0.0000739164,0.0001627556,0.0003584341,0.00001008409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001596454,"about_ca_system_score_gemma":0.00006841861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002908059,"about_ca_topic_score_gemma":0.000003768952,"domain_scores_codex":[0.9982877,0.0003192006,0.0004291302,0.0003617104,0.0002063936,0.000395846],"domain_scores_gemma":[0.9984282,0.001147768,0.00005119992,0.0003227333,0.00002144568,0.00002871411],"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":[0.00002877266,0.00009952652,0.00113103,0.0001669715,0.000001076266,0.000001239967,0.0005422368,0.09022024,0.9036319,0.003288654,0.00009391593,0.0007944434],"study_design_scores_gemma":[0.0005180875,0.00002111408,0.004995723,0.0007832422,0.00000251401,0.000003128976,0.00008789949,0.3987249,0.5917497,0.001206385,0.001574588,0.0003326161],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9537418,0.001353776,0.03998283,0.00103463,0.003128815,0.0006152084,0.00000360397,0.0000685362,0.0000707556],"genre_scores_gemma":[0.9961854,0.0000807149,0.003339833,0.00002866574,0.0001037049,0.000245619,0.000002466752,0.000009767251,0.000003795079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3118821,"threshold_uncertainty_score":0.4305705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03306747823853608,"score_gpt":0.3083063967489018,"score_spread":0.2752389185103657,"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."}}