{"id":"W4408391914","doi":"10.1088/2632-2153/adc072","title":"Hybrid vision transformer framework for efficient and explainable SEM image-based nanomaterial classification","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nanomaterials; Computer science; Artificial intelligence; Computer vision; Transformer; Pattern recognition (psychology); Materials science; Nanotechnology; Engineering; Electrical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.002974096,0.0002469663,0.0003190125,0.0007899334,0.001623451,0.0005619329,0.0006391056,0.0001539575,0.00007722739],"category_scores_gemma":[0.002281995,0.0002110831,0.00002703538,0.001055149,0.002204895,0.000295488,0.0001793094,0.0002958648,0.00001822903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008995194,"about_ca_system_score_gemma":0.0002466277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000498042,"about_ca_topic_score_gemma":0.000003065009,"domain_scores_codex":[0.9974934,0.00009708521,0.0003652055,0.0009824581,0.0003908771,0.0006709264],"domain_scores_gemma":[0.998809,0.000247828,0.000180854,0.0003759596,0.0002958027,0.00009054684],"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":[0.00006899308,0.0000410393,0.001481796,0.0001002096,0.000001498064,0.000002093808,0.00007514649,0.0005603139,0.9531506,0.03736596,0.00002781146,0.007124518],"study_design_scores_gemma":[0.0008845098,0.0005141246,0.002510795,0.0001640124,0.00002489089,0.00002714703,0.0001801737,0.3506052,0.623529,0.01529835,0.005892022,0.0003698013],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8416682,0.0001389182,0.1504965,0.006003634,0.0005270748,0.0004730007,0.00001111113,0.0004054185,0.0002761041],"genre_scores_gemma":[0.9413594,0.00001265557,0.05815426,0.0001866492,0.00002788491,0.0001138494,0.00000573393,0.00001580867,0.0001237809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3500449,"threshold_uncertainty_score":0.9996763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005869917712779618,"score_gpt":0.2800227234781797,"score_spread":0.2741528057654001,"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."}}