{"id":"W4283381069","doi":"10.26434/chemrxiv-2022-x49mh-v2","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; Space (punctuation); Generative model; Computer science; Inference; Oracle; Generative grammar; Artificial intelligence; Machine learning; Drug discovery; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001466381,0.0004400701,0.00058719,0.0001054531,0.0002195993,0.0006671688,0.0009859215,0.0002609044,0.006704598],"category_scores_gemma":[0.0004829232,0.000445259,0.00008974112,0.0001755119,0.0002641756,0.0004049793,0.003511864,0.0008373576,0.00017623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002143421,"about_ca_system_score_gemma":0.0001853802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001993398,"about_ca_topic_score_gemma":0.000002581814,"domain_scores_codex":[0.9969353,0.0001951142,0.0004487477,0.001248106,0.0006258065,0.0005469271],"domain_scores_gemma":[0.998345,0.0001126099,0.0003917558,0.0008753029,0.00008772549,0.0001876319],"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":[0.00004194696,0.0000465709,0.0003295873,0.0004177143,0.00000791314,0.000009666215,0.001939657,0.002969539,0.9911244,0.0004763808,0.002546881,0.0000897237],"study_design_scores_gemma":[0.0003457871,0.00006049982,0.0001589636,0.0001682438,0.00004743708,0.000022882,0.0004702265,0.01004864,0.9721907,0.004213192,0.01140506,0.0008683495],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9857452,0.0004565768,0.003454937,0.00198728,0.002330909,0.0004834092,0.00001674733,0.0004156068,0.00510935],"genre_scores_gemma":[0.9804703,0.0001045151,0.01596759,0.0001903099,0.0003263938,0.0003277228,0.00007504907,0.00006837671,0.002469768],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0189337,"threshold_uncertainty_score":0.9997999,"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."}}