{"id":"W4388043400","doi":"10.1016/j.culher.2023.10.007","title":"Computational framework for the evaluation of the composition and degradation state of metal heritage assets by deep learning","year":2023,"lang":"en","type":"article","venue":"Journal of Cultural Heritage","topic":"Conservation Techniques and Studies","field":"Arts and Humanities","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Colegiul Consultativ pentru Cercetare-Dezvoltare şi Inovare; Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii; Ontario Ministry of Research, Innovation and Science","keywords":"Asset (computer security); Corrosion; Artificial intelligence; Object (grammar); Computer science; Composition (language); Base metal; Engineering; Metallurgy; Materials science; Computer security; Art","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":[0.0009186871,0.00006246393,0.0001395268,0.0000276224,0.0002880036,0.0000503052,0.00007617617,0.00002055743,0.00003508116],"category_scores_gemma":[0.0001562419,0.0000328748,0.00009606692,0.00006039439,0.0001186132,0.0002068484,0.00002191344,0.000129703,2.682473e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002153438,"about_ca_system_score_gemma":0.00001620657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001431911,"about_ca_topic_score_gemma":0.00004570911,"domain_scores_codex":[0.9990801,0.0001398467,0.0003294698,0.00004668233,0.0003434735,0.00006047631],"domain_scores_gemma":[0.9982464,0.0004371084,0.0004663962,0.00003841173,0.0008005538,0.00001112127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008573029,0.0005121663,0.008414042,0.0008844644,0.002502249,0.000003067651,0.3028747,0.03157326,0.04040757,0.2065999,0.03576832,0.3696029],"study_design_scores_gemma":[0.005884954,0.002445758,0.2029396,0.001480726,0.002395877,0.00006693014,0.1821439,0.2349489,0.01382369,0.2871092,0.0657125,0.001048022],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943041,0.0009817112,0.002616562,0.001514226,0.0001619138,0.0002634765,0.00004922907,0.00001184947,0.00009690988],"genre_scores_gemma":[0.9985098,0.0001162838,0.00106662,0.00003703728,0.00004977196,0.000008665947,0.00002045603,0.000004201414,0.0001871333],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3685549,"threshold_uncertainty_score":0.221512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07977103712031668,"score_gpt":0.3270678913792531,"score_spread":0.2472968542589364,"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."}}