{"id":"W2942354492","doi":"10.1103/physreve.99.043307","title":"Recognition of polymer configurations by unsupervised learning","year":2019,"lang":"en","type":"article","venue":"Physical review. E","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Unsupervised learning; Artificial intelligence; Cluster analysis; Dimensionality reduction; Curse of dimensionality; Computer science; Pattern recognition (psychology); Competitive learning; Feature learning; Artificial neural network; Representation (politics); Machine learning; Salient; Principal component analysis; Feature (linguistics)","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000479209,0.0001225586,0.0003515263,0.00002199601,0.0000618175,0.00003412177,0.0002579028,0.00002147013,0.005162811],"category_scores_gemma":[0.0003474811,0.0001006356,0.00007967659,0.0001962901,0.000082502,0.0002151107,0.00005295481,0.0001237647,0.003750591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001314395,"about_ca_system_score_gemma":0.0000296525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005346304,"about_ca_topic_score_gemma":3.626735e-7,"domain_scores_codex":[0.9985945,0.0002865258,0.0002960496,0.0002903535,0.0003294797,0.0002031561],"domain_scores_gemma":[0.9992077,0.0001719776,0.0002145598,0.0002501642,0.00009196543,0.00006358541],"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":[0.000004630811,0.00004830923,0.0002125072,0.000317746,0.000001642468,1.493371e-7,0.00005577413,0.0000286845,0.9967409,0.0005014106,0.0005731055,0.001515145],"study_design_scores_gemma":[0.000191685,0.000149263,0.000432171,0.0006912224,0.00003090056,0.000002120844,0.00001524347,0.002050987,0.9910252,0.0007064998,0.00449389,0.000210816],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913588,0.001466596,0.0002772647,0.0004002711,0.0001900643,0.0003013471,0.00002369955,0.00006762877,0.005914308],"genre_scores_gemma":[0.9983814,0.0003981921,0.0002575424,0.0003717037,0.00006333528,0.00002485524,0.00004317613,0.00001393131,0.0004458748],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007022568,"threshold_uncertainty_score":0.9970251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01198072436617097,"score_gpt":0.3015589747893497,"score_spread":0.2895782504231788,"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."}}