{"id":"W3200137854","doi":"10.33774/chemrxiv-2021-9nhm1","title":"Sanitize It Yourself: human-based sanitization checker against machine-generated chemical structures","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Chemical space; Theoretical computer science; Distributed computing; Drug discovery; Bioinformatics","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":[0.004621864,0.001342558,0.0009849562,0.001395167,0.0007058625,0.001337962,0.002349908,0.002150628,0.02102036],"category_scores_gemma":[0.01325153,0.0006032001,0.001233936,0.0006528246,0.001364264,0.001926136,0.003015239,0.001739807,0.005686292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006482262,"about_ca_system_score_gemma":0.001692189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001145569,"about_ca_topic_score_gemma":0.002010574,"domain_scores_codex":[0.9979565,0.0005992022,0.0001263859,0.000412773,0.0007187328,0.0001863454],"domain_scores_gemma":[0.9933456,0.003491919,0.0004251195,0.001996054,0.0005633221,0.0001780329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004094032,0.001569888,0.0101278,0.001464179,0.0005336583,0.001138777,0.0005551846,0.1212955,0.06589331,0.04038667,0.1957426,0.5571985],"study_design_scores_gemma":[0.0005040279,0.00048728,0.0008909221,0.0001194685,0.00008234906,0.0003024506,0.00007727086,0.840045,0.08345926,0.02502381,0.04892906,0.00007899676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08933298,0.001194913,0.5111257,0.001590759,0.0006615344,0.0005139281,0.003636427,0.3755465,0.01639719],"genre_scores_gemma":[0.4408241,0.0006069563,0.5217739,0.001611003,0.0001124076,0.0004830571,0.008042207,0.01529972,0.01124669],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02102036,"threshold_uncertainty_score":0.07032007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04334115709802902,"score_gpt":0.3252583540189249,"score_spread":0.2819171969208959,"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."}}