{"id":"W4317393625","doi":"10.26434/chemrxiv-2022-hcjzc-v2","title":"A Multi-modal Pre-training Transformer for Universal Transfer Learning in Metal-Organic Frameworks","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Metal-Organic Frameworks: Synthesis and Applications","field":"Chemistry","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Chemical space; Transformer; Encoder; Transfer of learning; Autoencoder; Modal; Grid; Ranging; Artificial intelligence; Deep learning; Machine learning; Theoretical computer science; Materials science; Drug discovery; Engineering; Electrical engineering","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","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0006168212,0.00072887,0.001072529,0.000221953,0.0002156388,0.0001337703,0.0009127439,0.002779959,0.002043775],"category_scores_gemma":[0.0004484005,0.0007905153,0.0007250268,0.000429312,0.0001484541,0.0001109369,0.0001424723,0.004700753,0.0000691792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002381141,"about_ca_system_score_gemma":0.0003649327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006082793,"about_ca_topic_score_gemma":0.0001162164,"domain_scores_codex":[0.9964478,0.00004774167,0.0008953213,0.001374586,0.0003525853,0.0008819483],"domain_scores_gemma":[0.9978837,0.0007221816,0.0001773796,0.0008872218,0.0001047845,0.0002247399],"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":[0.0001315523,0.0006334453,0.0007803275,0.002459331,0.001036215,0.00002326814,0.01212428,0.005137348,0.9609869,0.001402556,0.0001864738,0.01509833],"study_design_scores_gemma":[0.005752916,0.00007965986,0.002166322,0.00517136,0.001900714,0.00001626926,0.01010541,0.07991187,0.8556222,0.008770644,0.02556841,0.004934253],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7380879,0.0006068949,0.2557912,0.001490922,0.0004200172,0.001142653,0.00008763837,0.0009799425,0.001392806],"genre_scores_gemma":[0.9823009,0.0003319818,0.009776599,0.00006885383,0.0003578663,0.0009781377,0.000387592,0.0003334844,0.005464582],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2460147,"threshold_uncertainty_score":0.9994546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04059306887675799,"score_gpt":0.2797703074272163,"score_spread":0.2391772385504583,"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."}}