{"id":"W4391884755","doi":"10.26434/chemrxiv-2024-1v269","title":"In silico chemical experiments in the Age of AI: From quantum chemistry to machine learning and back","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Chemical space; In silico; Scalability; Artificial intelligence; Transferability; Computational model; Machine learning; Set (abstract data type); Biochemical engineering; Chemistry; Drug discovery; Engineering; Database","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":[0.001229326,0.0003539551,0.0005793297,0.00008832126,0.00003175897,0.0002488626,0.001053885,0.0002696432,0.001792961],"category_scores_gemma":[0.0004786729,0.0002807185,0.00006452107,0.0002490898,0.0002282448,0.00005877992,0.002234579,0.001203328,0.0002189626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008735173,"about_ca_system_score_gemma":0.00008126605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0015412,"about_ca_topic_score_gemma":0.00001456631,"domain_scores_codex":[0.9973716,0.0001992474,0.000620457,0.000978908,0.0004412738,0.0003885012],"domain_scores_gemma":[0.9989672,0.0001986476,0.0001622249,0.0005659648,0.00002620909,0.00007979752],"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":[0.00003634803,0.00006034783,0.002970368,0.0003946668,0.000003393026,0.00005155561,0.003058958,0.0004423501,0.9927659,0.00002990877,0.0001660899,0.00002008473],"study_design_scores_gemma":[0.0002422961,0.0000173079,0.001013262,0.0005426404,0.00001023402,0.000006002426,0.0001552139,0.004182413,0.9898523,0.002769568,0.0008836592,0.0003250705],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966431,0.0006624723,0.00003348272,0.0009851417,0.00044745,0.000309289,0.0000192858,0.00004190025,0.0008578242],"genre_scores_gemma":[0.9976751,0.00001740859,0.001496677,0.0002621173,0.0001504925,0.0000819819,0.00004532587,0.00003500278,0.0002358943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003740063,"threshold_uncertainty_score":0.9999645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01907061937620611,"score_gpt":0.3062933683598154,"score_spread":0.2872227489836092,"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."}}