{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005942634,0.0001723939,0.0002404845,0.0000876512,0.00008907606,0.00008806653,0.002258745,0.00006786083,0.00002784082],"category_scores_gemma":[0.0002954526,0.0001182167,0.000098239,0.0006458167,0.0001299232,0.0003813674,0.0006414875,0.0003390391,0.000004211931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004611068,"about_ca_system_score_gemma":0.0001022494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000109982,"about_ca_topic_score_gemma":0.00001467461,"domain_scores_codex":[0.998401,0.00001158927,0.0005283556,0.0003963798,0.0003502016,0.0003124842],"domain_scores_gemma":[0.9989045,0.00009873446,0.0002196152,0.0004518296,0.0002905605,0.00003471289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004011295,0.0001964942,0.0002727498,0.00008428309,0.00001645752,7.201447e-7,0.01181674,0.001446859,0.1215737,0.8324325,0.00003035055,0.03208899],"study_design_scores_gemma":[0.00003138067,0.00001242835,0.00008122053,0.0002858138,0.000003126745,5.942723e-7,0.002214547,0.3738106,0.5654804,0.05797379,0.00001243785,0.0000936976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8724363,0.00007438699,0.1052551,0.002554299,0.0002996377,0.0003286483,0.000003912776,0.00005669174,0.01899092],"genre_scores_gemma":[0.9977285,0.00002548892,0.00184357,0.0001320025,0.00001845923,0.00004026224,1.597777e-7,0.000006227723,0.0002053334],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7744587,"threshold_uncertainty_score":0.4820739,"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."}}