{"id":"W4415772725","doi":"10.21203/rs.3.rs-7398508/v1","title":"nablaColors: A 3D Benchmark for Optical Property Prediction with Solvent-aware Graph Neural Networks","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Russian Academy of Sciences; Ministero dello Sviluppo Economico","keywords":"Benchmark (surveying); Artificial neural network; Property (philosophy); Fidelity; Graph; Invariant (physics); Deep neural networks","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","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","sts","research_integrity"],"category_scores_codex":[0.01693659,0.001382035,0.001705908,0.001231692,0.003405614,0.003768234,0.004117822,0.00145421,0.002343894],"category_scores_gemma":[0.003380283,0.0009389964,0.000495285,0.002562846,0.003232086,0.0009798382,0.004917285,0.004323997,0.00008534437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001014173,"about_ca_system_score_gemma":0.002875954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00111278,"about_ca_topic_score_gemma":0.000245238,"domain_scores_codex":[0.9811701,0.003479016,0.001897332,0.004532811,0.004577138,0.004343669],"domain_scores_gemma":[0.9889905,0.002439369,0.0006828061,0.002749657,0.004081418,0.001056188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009327007,0.001329743,0.004881171,0.01326446,0.0002244174,0.0001562459,0.001401016,0.9317815,0.0215272,0.001168824,0.009845855,0.005092589],"study_design_scores_gemma":[0.001759381,0.005944848,0.002582581,0.005537619,0.0001659806,0.00004633483,0.000647008,0.9746341,0.002611178,0.0006847215,0.004204333,0.001181984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4687911,0.001560877,0.4353141,0.009921386,0.01815936,0.05133163,0.005092936,0.001764302,0.008064265],"genre_scores_gemma":[0.950697,0.0005599729,0.0262066,0.0001922762,0.003052684,0.00981482,0.000897368,0.000215036,0.008364232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4819059,"threshold_uncertainty_score":0.999893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03850612676877199,"score_gpt":0.3604433967246575,"score_spread":0.3219372699558855,"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."}}