{"id":"W4413887080","doi":"10.1016/j.optlastec.2025.113813","title":"DL-DHM: A novel approach for out of distribution datasets in Deep Learning based off-axis Digital Holographic Microscopy","year":2025,"lang":"en","type":"article","venue":"Optics & Laser Technology","topic":"Digital Holography and Microscopy","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Bhabha Atomic Research Centre; Calgary Arts Development","keywords":"Digital holographic microscopy; Holography; Microscopy; Digital holography; Deep learning; Distribution (mathematics); Artificial intelligence; Computer science; Materials science; Optics; Physics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001174485,0.0002216924,0.0003548274,0.0004392071,0.00008267895,0.00005605023,0.0003595444,0.000221376,0.000003683485],"category_scores_gemma":[0.00004386167,0.0002311879,0.0001518157,0.0008993964,0.0003983551,0.0001591045,0.0001361826,0.0003172057,0.000002303015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001896425,"about_ca_system_score_gemma":0.00005138285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009150319,"about_ca_topic_score_gemma":0.000004615196,"domain_scores_codex":[0.99871,0.00001122642,0.0003734725,0.00042911,0.00006272706,0.0004134725],"domain_scores_gemma":[0.9992643,0.00007918161,0.0001541219,0.0003869098,0.00008235068,0.00003312022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008251009,0.01012704,0.5240343,0.0005483626,0.0007305847,0.000009177747,0.0001363908,0.002549859,0.1310909,0.182253,0.001691581,0.1460037],"study_design_scores_gemma":[0.02367917,0.002825833,0.01147754,0.0007144712,0.0006303921,0.000007194943,0.004430767,0.03844168,0.7438421,0.04304263,0.1279103,0.002997842],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4964445,0.0001292309,0.4948443,0.0001226731,0.0001220088,0.0005954158,0.005342848,0.0001100712,0.002288955],"genre_scores_gemma":[0.9818885,0.000004647888,0.01038873,0.00002172295,0.00001146322,0.0001338719,0.007469715,0.00001636818,0.00006502221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6127512,"threshold_uncertainty_score":0.942757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006226788431686014,"score_gpt":0.2548408500948362,"score_spread":0.2486140616631502,"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."}}