{"id":"W4403244299","doi":"10.1039/d4sc04630g","title":"Automated electrosynthesis reaction mining with multimodal large language models (MLLMs)","year":2024,"lang":"en","type":"article","venue":"Chemical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Office of Science; Canada First Research Excellence Fund; University of Toronto; U.S. Department of Energy; University of Minnesota; Nanyang Technological University; Ministry of Education - Singapore; Canadian Institute for Advanced Research","keywords":"Electrosynthesis; Computer science; Natural language processing; Data science; Chemistry; Electrochemistry","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":[0.003324568,0.0024317,0.0009627301,0.003182579,0.0007076514,0.003006023,0.002443335,0.00168427,0.007677513],"category_scores_gemma":[0.01160427,0.0008532266,0.003674137,0.00188902,0.0008009464,0.004044559,0.002759419,0.002569899,0.006807871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001306877,"about_ca_system_score_gemma":0.002101488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003112596,"about_ca_topic_score_gemma":0.00674799,"domain_scores_codex":[0.997811,0.000686175,0.0002209975,0.0007322274,0.0004423336,0.0001072493],"domain_scores_gemma":[0.9938361,0.00426465,0.0004235369,0.0007125149,0.0006534891,0.0001096023],"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":[0.0007959101,0.0003967466,0.006652806,0.003910634,0.0006767779,0.001026804,0.0008339496,0.09173276,0.058823,0.02180729,0.057682,0.7556613],"study_design_scores_gemma":[0.00009238512,0.000228557,0.001658841,0.000263733,0.0002037401,0.0005071199,0.0004390581,0.7916519,0.08092254,0.06420809,0.05965909,0.0001649143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0287239,0.002822558,0.857978,0.001795929,0.000325389,0.0004713692,0.02524994,0.07668289,0.00595006],"genre_scores_gemma":[0.1483407,0.001333688,0.799085,0.0008748457,0.0001439476,0.0008518996,0.04169295,0.002668186,0.005008814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007677513,"threshold_uncertainty_score":0.02568388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007185492762374514,"score_gpt":0.2715545567418196,"score_spread":0.264369063979445,"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."}}