{"id":"W4416077476","doi":"10.1021/jacs.5c11789","title":"MOF-ChemUnity: Literature-Informed Large Language Models for Metal–Organic Framework Research","year":2025,"lang":"en","type":"article","venue":"Journal of the American Chemical Society","topic":"Metal-Organic Frameworks: Synthesis and Applications","field":"Chemistry","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; National Research Council Canada; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Canada First Research Excellence Fund; National Research Council Canada; Concordia University; Schmidt Futures","keywords":"Leverage (statistics); Inference; Knowledge graph; Scalability; Trustworthiness; Applications of artificial intelligence; Knowledge base; Scope (computer science); Information extraction; Graph","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002826732,0.00135843,0.0008608035,0.00463613,0.001005072,0.002289777,0.00290428,0.001907944,0.007639795],"category_scores_gemma":[0.01939388,0.0006819866,0.002549427,0.002760237,0.0008323237,0.003675499,0.003256202,0.002360217,0.003452334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0019296,"about_ca_system_score_gemma":0.004107272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01679681,"about_ca_topic_score_gemma":0.03675283,"domain_scores_codex":[0.9983537,0.0007130132,0.0001380251,0.0003697392,0.0003508568,0.00007461039],"domain_scores_gemma":[0.9920271,0.005958909,0.0003941086,0.0008041601,0.000628648,0.0001870018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005326995,0.0004387233,0.004518466,0.002103723,0.0004800387,0.0008034506,0.0008929195,0.36783,0.006466067,0.1053311,0.1090418,0.4015611],"study_design_scores_gemma":[0.00008765121,0.00005801673,0.0003350105,0.0001330465,0.00007038527,0.00009452532,0.00009506322,0.8490475,0.002442434,0.1011442,0.04644123,0.00005092115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01438646,0.002340544,0.9007865,0.002966464,0.0003082163,0.0005961638,0.02735192,0.04394593,0.007317784],"genre_scores_gemma":[0.128883,0.001334451,0.8218875,0.0009344466,0.0001805694,0.001167476,0.04083654,0.001703639,0.003072302],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01679681,"threshold_uncertainty_score":0.03339803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.023640637718059,"score_gpt":0.339124657384002,"score_spread":0.315484019665943,"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."}}