{"id":"W4411698202","doi":"10.26434/chemrxiv-2025-rdf97-v2","title":"A molecular fragment database generated through simulated sequential single-bond-breaking","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"U.S. Forest Service; U.S. Department of Agriculture","keywords":"Fragment (logic); Computer science; Chemistry; Algorithm","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":[0.001159542,0.001193038,0.00142254,0.00181705,0.0007750888,0.00142753,0.004087982,0.001727131,0.02323692],"category_scores_gemma":[0.003994622,0.0007345628,0.001017978,0.002544846,0.0004058915,0.001623075,0.00116872,0.001803963,0.00513888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001253308,"about_ca_system_score_gemma":0.001905959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003712078,"about_ca_topic_score_gemma":0.004524496,"domain_scores_codex":[0.9994851,0.00008063781,0.00003381109,0.0001227187,0.0002312259,0.00004642649],"domain_scores_gemma":[0.9990215,0.0003979367,0.00005796279,0.000226489,0.000229951,0.0000661154],"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":[0.002888172,0.0007108111,0.008104425,0.002607442,0.0006246056,0.001656505,0.0004014306,0.5744895,0.03303555,0.06670915,0.1640966,0.1446758],"study_design_scores_gemma":[0.0006201389,0.0002820508,0.0008018431,0.00006972718,0.0001104846,0.0004036367,0.00007658945,0.8876277,0.02215732,0.02266258,0.06511034,0.00007760483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1447669,0.002155535,0.5851002,0.001244902,0.0006971949,0.00119704,0.186753,0.05155656,0.0265287],"genre_scores_gemma":[0.314423,0.001234685,0.4622043,0.0003342961,0.00006216636,0.00187936,0.2122073,0.002746287,0.004908523],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02323692,"threshold_uncertainty_score":0.0777353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0609696490752425,"score_gpt":0.3405491300206834,"score_spread":0.2795794809454409,"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."}}