{"id":"W3200661883","doi":"10.1021/acs.cgd.1c00737","title":"Virtual Multicomponent Crystal Screening: Hydrogen Bonding Revisited","year":2021,"lang":"en","type":"article","venue":"Crystal Growth & Design","topic":"Crystallography and molecular interactions","field":"Chemistry","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Hydrogen bond; Crystal structure prediction; Density functional theory; Chemistry; Classifier (UML); Computer science; Virtual screening; Crystal engineering; Hydrogen; Crystal structure; Machine learning; Artificial intelligence; Molecule; Nanotechnology; Computational chemistry; Materials science; Crystallography; Molecular dynamics; Organic chemistry","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002047983,0.0004013559,0.0003919035,0.0001804612,0.000378318,0.0001982532,0.0003151493,0.0002266343,0.001546438],"category_scores_gemma":[0.0002952493,0.0004480692,0.0004877299,0.0004850453,0.0001211673,0.0002595944,0.000201136,0.0004923827,0.00002807541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009259463,"about_ca_system_score_gemma":0.00010114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002879037,"about_ca_topic_score_gemma":0.000003933214,"domain_scores_codex":[0.9975119,0.0001432806,0.0005344626,0.0007289192,0.0004652517,0.0006161904],"domain_scores_gemma":[0.9984171,0.0002651101,0.0001733086,0.0005808478,0.0002411488,0.0003224401],"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":[0.0001307848,0.000242001,0.0002822636,0.00007224725,0.000268349,0.0006422646,0.0002391317,0.0002096676,0.993484,0.001934769,0.001860716,0.0006338138],"study_design_scores_gemma":[0.001913927,0.0001043761,0.0002131193,0.0004220514,0.0003024222,0.000822377,0.001512774,0.0033007,0.9195524,0.0007101183,0.07007256,0.001073137],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5273573,0.001684838,0.4458995,0.0004705329,0.0003176135,0.0003795901,0.0002457973,0.0008516917,0.02279316],"genre_scores_gemma":[0.9900018,0.00003158381,0.00657187,0.0001928367,0.0002339167,0.00004825437,0.0003330744,0.00008383617,0.00250285],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4626445,"threshold_uncertainty_score":0.9997971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02570680234278172,"score_gpt":0.2492986160661931,"score_spread":0.2235918137234114,"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."}}