{"id":"W4416291187","doi":"10.26434/chemrxiv-2025-6c250","title":"A Robust and Versatile Generative Model for Inverse Design of Polymers","year":2025,"lang":"","type":"article","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Heuristics; Inverse; Generator (circuit theory); Polymer; Generative Design; Generative grammar","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"],"consensus_categories":[],"category_scores_codex":[0.001654172,0.0003449415,0.0005772247,0.000192504,0.0003392049,0.0001880081,0.0005776333,0.0001889896,0.0005344868],"category_scores_gemma":[0.0009084576,0.0003431243,0.00008596956,0.0003886498,0.0009879997,0.0003234762,0.000319794,0.0001215927,0.00001258881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000846828,"about_ca_system_score_gemma":0.0006080252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007262922,"about_ca_topic_score_gemma":0.000007043722,"domain_scores_codex":[0.997501,0.0002268562,0.0006206775,0.0008399285,0.0002683209,0.0005432085],"domain_scores_gemma":[0.9983186,0.00044085,0.0003954822,0.0005007409,0.0002067142,0.0001376831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002103681,0.00005264994,0.00007793119,0.0003504004,0.00002047291,7.108804e-7,0.001717148,0.30337,0.6906154,0.002266179,0.001137682,0.0001810552],"study_design_scores_gemma":[0.0006175219,0.00008493436,0.0000305528,0.0001078169,0.0000658822,8.334142e-7,0.0001641463,0.6113697,0.3858104,0.001521029,0.00004496745,0.0001822471],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2818618,0.0003667585,0.7146733,0.0007117002,0.0008503667,0.0009098919,0.00002950783,0.00004016154,0.0005564063],"genre_scores_gemma":[0.7402267,0.0001056842,0.2549118,0.0004106592,0.00006730544,0.0001058562,0.000004233716,0.00002765327,0.004140056],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4597615,"threshold_uncertainty_score":0.9999021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05087801357612837,"score_gpt":0.2794875518969959,"score_spread":0.2286095383208676,"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."}}