{"id":"W4322098240","doi":"10.58286/26642","title":"Correlative Laser Confocal Microscopy Study and Multimodal 2D/3D Registration as Ground Truth for X-ray Inspection of Internal Defects in LPBF Manufacturing","year":2022,"lang":"en","type":"article","venue":"e-Journal of Nondestructive Testing","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Object Research Systems (Canada); École de Technologie Supérieure; National Research Council Canada; Polytechnique Montréal","funders":"Consortium de Recherche et d’innovation en Aérospatiale au Québec","keywords":"Ground truth; Confocal; Correlative; Materials science; Confocal microscopy; Image registration; Volume (thermodynamics); Resolution (logic); Laser; Image resolution; Microscopy; Computer science; Computer vision; Optics; Artificial intelligence; Image (mathematics); Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004381336,0.0001751223,0.0002995729,0.0002431784,0.0001667403,0.00003094781,0.0001099666,0.00003205366,0.000009234379],"category_scores_gemma":[0.0003455705,0.0001885068,0.00005110506,0.0001670142,0.00006541658,0.0004940848,0.00004726826,0.0005768482,2.677023e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002997984,"about_ca_system_score_gemma":0.00004725473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007337399,"about_ca_topic_score_gemma":0.00001893136,"domain_scores_codex":[0.9987948,0.00007444956,0.0005469965,0.0001695932,0.0002173064,0.0001968577],"domain_scores_gemma":[0.9988095,0.0005395052,0.0004095929,0.00007388193,0.0001144518,0.00005311651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.001319101,0.0004389271,0.2411868,0.0002325453,0.0003409474,0.0002964293,0.01808764,0.5879709,0.1317013,0.0002335329,0.000009813173,0.01818213],"study_design_scores_gemma":[0.01345365,0.00574106,0.7005125,0.0006496268,0.0002605186,0.002356413,0.05610932,0.1343009,0.07581066,0.00981905,0.00003319246,0.0009530231],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9730667,0.00009902191,0.02568993,0.000003612819,0.0004897663,0.0003109434,0.000008475577,0.00003497443,0.0002965815],"genre_scores_gemma":[0.9803327,0.00000154721,0.01950649,0.000007662582,0.00009850006,0.00001565964,0.00000152742,0.00002886314,0.000007033722],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4593258,"threshold_uncertainty_score":0.7687086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01376662142825042,"score_gpt":0.2687119277679121,"score_spread":0.2549453063396617,"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."}}