{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002260343,0.00009499406,0.00008884394,0.00005872002,0.00007874143,0.0004407098,0.0007304274,0.00004458842,0.000003928142],"category_scores_gemma":[0.0002133444,0.00007123714,0.00002786332,0.0004380603,0.0005030318,0.0007832512,0.0004177614,0.0001427514,0.00002790795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005639338,"about_ca_system_score_gemma":0.00009930409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000141041,"about_ca_topic_score_gemma":6.681404e-7,"domain_scores_codex":[0.9987923,0.000005076964,0.0001051104,0.0005033337,0.0003119334,0.0002822472],"domain_scores_gemma":[0.9995351,0.00009477683,0.00001415873,0.0002217315,0.00003834651,0.00009592326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000141448,0.00001021687,0.00005302031,0.00001650404,0.000001852518,0.000009052306,0.0004106782,0.000008250949,0.8899338,0.0420115,0.0001377335,0.06740602],"study_design_scores_gemma":[0.00005238963,0.000004069973,0.0001654308,0.00001660483,0.000002011473,0.00002982122,0.00002177182,0.7307106,0.2639284,0.004880365,0.00008735398,0.0001011938],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9244803,0.000718891,0.07046026,0.001703714,0.0002957078,0.00006710582,5.776972e-7,0.000387125,0.001886389],"genre_scores_gemma":[0.9534249,0.000007475531,0.04627543,0.0001534644,0.00005333362,0.000004381026,0.000001025092,0.000002899717,0.00007710431],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7307023,"threshold_uncertainty_score":0.4249775,"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."}}