{"id":"W3204771293","doi":"10.1016/j.procs.2021.08.206","title":"A Deep Learning-based Surrogate for the XRF Approximation of Elemental Composition within Archaeological Artefacts before Restoration","year":2021,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Colegiul Consultativ pentru Cercetare-Dezvoltare şi Inovare; Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii; Ministerio de Ciencia e Innovación; Ontario Ministry of Research, Innovation and Science; Universidad de Málaga","keywords":"Context (archaeology); Computer science; Task (project management); Artificial intelligence; Object (grammar); Deep learning; Composition (language); Archaeology; History; Linguistics","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":[0.001194209,0.0001255226,0.0001415721,0.0001240642,0.0004950888,0.0002777011,0.0006221595,0.00004531761,0.000001938535],"category_scores_gemma":[0.0001687766,0.00009376504,0.00005852266,0.0008898184,0.0005181494,0.0008833032,0.0001920381,0.0001578283,0.00000440025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007386458,"about_ca_system_score_gemma":0.0006032697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002746067,"about_ca_topic_score_gemma":0.00001301677,"domain_scores_codex":[0.9982707,0.00006998138,0.0003174818,0.0004892754,0.000583989,0.0002686013],"domain_scores_gemma":[0.9982683,0.0001512471,0.0002900755,0.0002570542,0.0009674791,0.00006583185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008449867,0.0004071584,0.006274025,0.0004629198,0.00003093244,0.00001058736,0.01549994,0.1658879,0.03069908,0.02693484,0.00005431166,0.7536538],"study_design_scores_gemma":[0.0003399834,0.0001949562,0.002196557,0.00004781708,0.000006984254,0.00006029064,0.00005839385,0.9302244,0.06380184,0.002944525,0.00002389256,0.0001003853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07442495,0.00008032406,0.9233825,0.001113051,0.0006279674,0.0002593115,7.273825e-7,0.00008815444,0.00002305983],"genre_scores_gemma":[0.6828125,0.000001825914,0.3169683,0.000108995,0.00007233644,0.00002014302,0.000006161793,0.000003387386,0.000006392044],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7643365,"threshold_uncertainty_score":0.3823627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01359874698868825,"score_gpt":0.2454831659511555,"score_spread":0.2318844189624672,"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."}}