{"id":"W4409369201","doi":"10.1609/aaai.v39i1.32020","title":"ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Power (physics); Computer science; Chemistry; Linguistics; Philosophy; Physics; Thermodynamics","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":[0.003070945,0.002462151,0.0009349372,0.00194746,0.0008951384,0.002119902,0.002726026,0.002253287,0.006390597],"category_scores_gemma":[0.01073804,0.0006515051,0.002279078,0.001278921,0.000570807,0.004216803,0.002505903,0.003541608,0.003675709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002165279,"about_ca_system_score_gemma":0.002290777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02397725,"about_ca_topic_score_gemma":0.03441338,"domain_scores_codex":[0.9986615,0.0006134119,0.00007665068,0.0003919789,0.0001821806,0.00007431577],"domain_scores_gemma":[0.9951762,0.003590568,0.0001475145,0.0005712219,0.0003539512,0.0001605798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009805865,0.001175179,0.008672677,0.001733956,0.0009416296,0.0006852472,0.000645268,0.3783983,0.008280212,0.01605445,0.1262907,0.4561417],"study_design_scores_gemma":[0.0001295915,0.0001412815,0.0006918648,0.00006510373,0.00008189741,0.000109226,0.0001324669,0.9698312,0.003327346,0.01210563,0.01333606,0.00004844817],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2221451,0.01315577,0.5806561,0.007369004,0.001448209,0.001406215,0.05912485,0.09246098,0.02223381],"genre_scores_gemma":[0.4777415,0.002712648,0.39782,0.002821398,0.0003981272,0.001557094,0.1035977,0.003130578,0.010221],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02397725,"threshold_uncertainty_score":0.04767537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0846630502594492,"score_gpt":0.2956609110330076,"score_spread":0.2109978607735584,"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."}}