{"id":"W4409143139","doi":"10.26434/chemrxiv-2025-vzjw3","title":"A Benchmark Set of Bioactive Molecules for Diversity Analysis of Compound Libraries and Combinatorial Chemical Spaces","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Chemical Synthesis and Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Emergent BioSolutions (Canada)","funders":"","keywords":"Benchmark (surveying); Chemical space; Set (abstract data type); Diversity (politics); Molecule; Combinatorial chemistry; Computer science; Chemistry; Drug discovery; Organic chemistry; Geography; Sociology; Biochemistry; Cartography","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":[0.00156982,0.001148258,0.001044641,0.002950712,0.0006874619,0.001162477,0.001265491,0.0008506699,0.003834107],"category_scores_gemma":[0.00437867,0.0002375275,0.00111073,0.004135199,0.0005563044,0.001024773,0.0008519637,0.0008214168,0.001092916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007944366,"about_ca_system_score_gemma":0.001507665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001667916,"about_ca_topic_score_gemma":0.002054467,"domain_scores_codex":[0.9988986,0.0002346137,0.00009466981,0.0001966418,0.0004761049,0.00009932426],"domain_scores_gemma":[0.9982125,0.0007880861,0.0001392068,0.0003041228,0.0004182816,0.0001378626],"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":[0.00349125,0.004116735,0.02080658,0.008108003,0.000920887,0.001442739,0.0002549928,0.3709884,0.1729088,0.02752709,0.06115872,0.3282759],"study_design_scores_gemma":[0.00114731,0.006106158,0.02796517,0.0003635378,0.0004195497,0.002448724,0.0004699527,0.5501571,0.2299712,0.02182448,0.1589319,0.0001947792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7987203,0.009633032,0.07046933,0.000819,0.0001916788,0.001224801,0.08659247,0.00323677,0.02911263],"genre_scores_gemma":[0.5647592,0.004523186,0.1683086,0.0004345032,0.00007626833,0.001593022,0.2536715,0.000500932,0.006132882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003834107,"threshold_uncertainty_score":0.01282632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01316360453917593,"score_gpt":0.2465483892812848,"score_spread":0.2333847847421089,"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."}}