{"id":"W4396721893","doi":"10.1039/d4sc00966e","title":"nach0: multimodal natural and chemical languages foundation model","year":2024,"lang":"en","type":"article","venue":"Chemical Science","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Foundation (evidence); Natural (archaeology); Computer science; Artificial intelligence; Natural language processing; Geography; Archaeology","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":[0.0005693372,0.0009720391,0.0005453216,0.0007587579,0.0004282501,0.00100382,0.002133273,0.0008804817,0.008513831],"category_scores_gemma":[0.001998216,0.0004511418,0.001350289,0.0005499814,0.000469205,0.001916058,0.001388117,0.001660217,0.003195051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001018065,"about_ca_system_score_gemma":0.001975194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01060095,"about_ca_topic_score_gemma":0.02036017,"domain_scores_codex":[0.9997771,0.00005494357,0.00001265937,0.00007278493,0.00005295534,0.00002959625],"domain_scores_gemma":[0.9996014,0.0002009679,0.00002388601,0.00006536767,0.00007954208,0.00002886436],"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":[0.0004096152,0.0001991782,0.001955363,0.0003292661,0.000129583,0.0003656006,0.0001553677,0.6704598,0.004963802,0.06220825,0.0422716,0.2165526],"study_design_scores_gemma":[0.00002216418,0.00002115288,0.00009142162,0.0000102585,0.00001182538,0.00003302494,0.000009825395,0.9790084,0.0009155202,0.0147148,0.005153257,0.000008353867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03380438,0.0006919176,0.9139239,0.001125312,0.0001868666,0.0002495905,0.009940289,0.02698724,0.01309036],"genre_scores_gemma":[0.5265145,0.000706693,0.4219921,0.0009128027,0.0001336297,0.001080355,0.02731244,0.001775776,0.01957167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01060095,"threshold_uncertainty_score":0.0284816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01237814244075251,"score_gpt":0.2880965065878941,"score_spread":0.2757183641471416,"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."}}