{"id":"W4318214958","doi":"10.20944/preprints202301.0483.v1","title":"Pulsed Thermography Dataset for Training Deep Learning Models","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"European Regional Development Fund","keywords":"Thermography; Deep learning; Preprocessor; Artificial intelligence; Segmentation; Computer science; Field (mathematics); Data pre-processing; Market segmentation; Pattern recognition (psychology); Image segmentation; Machine learning; Data mining","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":[0.0009621176,0.0006082215,0.0006441126,0.0004972818,0.0001658837,0.00005262676,0.0009685375,0.000624665,0.0001745856],"category_scores_gemma":[0.00009376936,0.0006904548,0.0005005886,0.0003134562,0.00009030532,0.0001380204,0.0006308174,0.001526821,0.00004392336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005754814,"about_ca_system_score_gemma":0.00003594483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008017686,"about_ca_topic_score_gemma":0.00001968519,"domain_scores_codex":[0.997392,0.00009118011,0.0006036233,0.0009401949,0.0002786841,0.0006943159],"domain_scores_gemma":[0.9980638,0.0002706308,0.0001605749,0.001260948,0.00007247533,0.0001715533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001143081,0.00008053976,0.007254174,0.001918206,0.001443203,0.00002781312,0.00783549,0.9337853,0.03199587,0.0005115355,0.0009522442,0.01408127],"study_design_scores_gemma":[0.001328253,0.00009554848,0.02251326,0.001298895,0.0007735959,0.00001631588,0.001292904,0.753795,0.04184339,0.1492707,0.02393353,0.003838517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5067332,0.001050454,0.4429411,0.0000901188,0.002653364,0.004490899,0.02307145,0.01363224,0.005337233],"genre_scores_gemma":[0.9910299,0.0005096121,0.001378349,0.00003501603,0.000232816,0.001581494,0.004856575,0.0002811339,0.00009508935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4842968,"threshold_uncertainty_score":0.9995546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2206849506113399,"score_gpt":0.3302805733537706,"score_spread":0.1095956227424307,"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."}}