{"id":"W3101099968","doi":"10.1038/s41598-020-76457-9","title":"From remote sensing and machine learning to the history of the Silk Road: large scale material identification on wall paintings","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Cultural Heritage Materials Analysis","field":"Arts and Humanities","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; Engineering and Physical Sciences Research Council; Ministry of Science and Technology of the People's Republic of China; Trent University; Nottingham Trent University; Capital Normal University","keywords":"Scale (ratio); SILK; Identification (biology); Painting; Remote sensing; Computer science; Artificial intelligence; Biology; Cartography; Geology; Geography; Art history; Botany; Art; Telecommunications","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":[0.0009801495,0.0001051227,0.0001667557,0.00003186269,0.0005114098,0.0004974407,0.0001213157,0.00002307649,0.0008388307],"category_scores_gemma":[0.0001926011,0.00006018698,0.00007987478,0.00006655067,0.000193759,0.00009114382,0.0001346479,0.00008193095,0.00002292667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005487486,"about_ca_system_score_gemma":0.0000206803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003363931,"about_ca_topic_score_gemma":0.002039978,"domain_scores_codex":[0.9985505,0.000136179,0.0004188432,0.0004184148,0.0003323875,0.0001436873],"domain_scores_gemma":[0.9990466,0.00001790162,0.0003768625,0.0003909589,0.0001174089,0.00005031338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005233546,0.00002560472,0.0001860574,0.00006130193,0.00005176655,0.00002961808,0.3095748,0.000107415,0.6380804,0.00009518052,0.03844517,0.01329039],"study_design_scores_gemma":[0.00007944699,0.00002467038,0.0006122977,0.00007130254,0.00008409292,0.000006304098,0.005028315,0.006366959,0.01998004,0.0005705411,0.9670026,0.0001734694],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9902972,0.00007697916,0.0000273414,0.002323498,0.006356122,0.0001838162,0.00001986951,0.00004104288,0.0006741302],"genre_scores_gemma":[0.9827787,0.000001100357,0.00005025729,0.0002851105,0.0003916354,6.191842e-7,0.00005265731,0.00001219894,0.01642771],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9285574,"threshold_uncertainty_score":0.9184608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02786122940857058,"score_gpt":0.2056157235154074,"score_spread":0.1777544941068368,"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."}}