{"id":"W4414816606","doi":"10.1016/j.talanta.2025.128939","title":"Generating a chemical database of organic nanomers and applying active learning to predict HOMO, LUMO and band gap: Accelerating optoelectronic nanopolymer materials discovery","year":2025,"lang":"en","type":"article","venue":"Talanta","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of Education and Child Care","funders":"National Key Research and Development Program of China; Graduate Research and Innovation Projects of Jiangsu Province; National Natural Science Foundation of China","keywords":"HOMO/LUMO; Range (aeronautics); Chemical database; Construct (python library); Active layer; Molecular descriptor; Density functional theory; Sample (material)","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":[0.0008789773,0.0002573145,0.000444489,0.000141492,0.0003372448,0.0004526588,0.0003114763,0.00007670687,0.0002903743],"category_scores_gemma":[0.0005309283,0.0002345409,0.00002146711,0.0002902305,0.0002084232,0.0005552139,0.000597016,0.000176649,0.000007778432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005865116,"about_ca_system_score_gemma":0.0001320245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001629794,"about_ca_topic_score_gemma":0.00001560796,"domain_scores_codex":[0.9978704,0.0002216078,0.0004617894,0.0006798789,0.0002686096,0.0004977376],"domain_scores_gemma":[0.9991329,0.0002077708,0.0002353661,0.0002767792,0.00004349876,0.0001037207],"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":[0.00008471031,0.00001776151,0.002022375,0.0001933417,0.00001189558,0.000003623058,0.0006021052,0.0001185091,0.9961413,0.00009597251,0.00002407372,0.0006843255],"study_design_scores_gemma":[0.0003797619,0.0000836879,0.0004462756,0.0002797463,0.00003254273,0.00003026077,0.00042212,0.001216673,0.99682,0.00002516559,0.00003423818,0.0002294884],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978822,0.0002150811,0.000771712,0.00008559502,0.0002550884,0.0004242467,0.0000632039,0.00007602476,0.0002268329],"genre_scores_gemma":[0.9967233,0.00004422607,0.00260269,0.000101071,0.00008438601,0.00006554333,0.00003083546,0.00002568143,0.0003222862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001830978,"threshold_uncertainty_score":0.9564298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008912698705609049,"score_gpt":0.2551498907988669,"score_spread":0.2462371920932578,"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."}}