{"id":"W4306926354","doi":"10.26434/chemrxiv-2022-hcjzc","title":"MOFTransformer: A Multi-modal Pre-training Transformer for Universal Transfer Learning in Metal-Organic Frameworks","year":2022,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Metal-Organic Frameworks: Synthesis and Applications","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Supercomputing Center, Korea Institute of Science and Technology Information; National Research Foundation of Korea; National Research Foundation","keywords":"Autoencoder; Computer science; Transformer; Modal; Transfer of learning; Grid; Encoder; Artificial intelligence; Machine learning; Deep learning; Engineering; Materials science; Electrical engineering; Mathematics","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":[0.0007460379,0.0008104395,0.0005407981,0.000430993,0.0003259081,0.000555545,0.001605909,0.001028344,0.004928538],"category_scores_gemma":[0.002487386,0.0003529039,0.0006543495,0.0003785657,0.0005346238,0.001511244,0.001112076,0.001742202,0.001746552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007459159,"about_ca_system_score_gemma":0.0009374321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0052484,"about_ca_topic_score_gemma":0.01036157,"domain_scores_codex":[0.9998248,0.00004323062,0.000007586136,0.00004974595,0.00004732766,0.00002730091],"domain_scores_gemma":[0.9996229,0.0001894602,0.00002232081,0.00006952472,0.0000670857,0.0000286973],"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":[0.0002990484,0.000199103,0.002061115,0.0002437905,0.000113634,0.0002041065,0.0001231701,0.53655,0.02227337,0.02168643,0.01289659,0.4033497],"study_design_scores_gemma":[0.000008668037,0.00003156697,0.00008848667,0.000007746693,0.000005327632,0.00002303809,0.00001027242,0.9886856,0.00525519,0.00458839,0.0012891,0.000006598924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05952497,0.0009919668,0.921729,0.0005419001,0.0001720094,0.0001145669,0.0007393981,0.0117939,0.004392226],"genre_scores_gemma":[0.6719835,0.0005580959,0.3125127,0.0006582573,0.00006827941,0.0003056506,0.002047975,0.001198554,0.01066692],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0052484,"threshold_uncertainty_score":0.0164876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02738498116087689,"score_gpt":0.2702536551143191,"score_spread":0.2428686739534422,"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."}}