{"id":"W4283395419","doi":"10.26434/chemrxiv-2022-x49mh","title":"ChemSpacE: Toward Steerable and Interpretable Chemical Space Exploration","year":2022,"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":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Chemical space; Interpretability; Generative model; Space (punctuation); Computer science; Inference; Generative grammar; Oracle; Artificial intelligence; Machine learning; Drug discovery; Theoretical computer science; Chemistry","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":[0.001085549,0.001114605,0.001162302,0.0008441789,0.0004413776,0.001572608,0.001798591,0.001688882,0.003534343],"category_scores_gemma":[0.003457359,0.0008615486,0.00162959,0.0007180821,0.001780451,0.002473849,0.003329718,0.002744505,0.001090412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001001484,"about_ca_system_score_gemma":0.001388623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002449692,"about_ca_topic_score_gemma":0.004644072,"domain_scores_codex":[0.999333,0.0002360574,0.00002021743,0.0001641026,0.0001939424,0.00005266445],"domain_scores_gemma":[0.9986749,0.0008140206,0.0000913649,0.000267748,0.00007166377,0.00008039529],"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":[0.0003073892,0.0001642535,0.001389408,0.0002889126,0.0001022015,0.0001836892,0.0002634545,0.7212152,0.0155752,0.09937583,0.006590113,0.1545444],"study_design_scores_gemma":[0.00002086854,0.0000258274,0.00003903527,0.00000584695,0.000003800245,0.00002204885,0.00001231681,0.9742532,0.001860267,0.02233344,0.001416787,0.000006446581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02129907,0.0004879478,0.9697015,0.0004345145,0.00003714918,0.00005341198,0.0002997691,0.005527453,0.002159311],"genre_scores_gemma":[0.3700657,0.0006882228,0.6223671,0.0004849724,0.00006839191,0.0002472826,0.001187535,0.001229132,0.003661611],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003534343,"threshold_uncertainty_score":0.01182359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02583142095755384,"score_gpt":0.279881617487518,"score_spread":0.2540501965299642,"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."}}