{"id":"W4413934934","doi":"10.26434/chemrxiv-2025-1lcpq","title":"The elephant in the lab: Synthesizability in generative small-molecule design","year":2025,"lang":"en","type":"article","venue":"ChemRxiv","topic":"Nanotechnology research and applications","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; University of Toronto; Canada First Research Excellence Fund; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Generative grammar; Computer science; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039103,0.0008052107,0.0009903526,0.000750521,0.0009311479,0.003057721,0.001484629,0.001865167,0.005451079],"category_scores_gemma":[0.007509091,0.0007487886,0.001101981,0.0006588447,0.003453328,0.004584336,0.002860625,0.003278249,0.002033389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001114736,"about_ca_system_score_gemma":0.001293444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004478378,"about_ca_topic_score_gemma":0.0008999385,"domain_scores_codex":[0.9984509,0.0006336357,0.0000904549,0.0002890331,0.0004405476,0.00009551428],"domain_scores_gemma":[0.9965472,0.002002865,0.0001610378,0.001022208,0.0001651793,0.0001015675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002227839,0.0002286295,0.001543596,0.002353384,0.000144652,0.0003105299,0.000917103,0.0930538,0.06865359,0.5895366,0.007831212,0.2352042],"study_design_scores_gemma":[0.00009659828,0.0004402592,0.0004124902,0.0006951017,0.0001482269,0.0004471285,0.0003306001,0.2014278,0.08554868,0.5096673,0.2006464,0.0001393377],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04402686,0.03017433,0.884797,0.007083067,0.0007750377,0.0002389446,0.0003257593,0.002701981,0.02987714],"genre_scores_gemma":[0.3987424,0.0270474,0.5598752,0.002167089,0.0003461064,0.0006404791,0.0006377815,0.001815485,0.008728124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005451079,"threshold_uncertainty_score":0.02067989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01952854007483309,"score_gpt":0.2564613348156651,"score_spread":0.236932794740832,"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."}}