{"id":"W4402118623","doi":"10.1038/s41597-024-03785-0","title":"A comprehensive dataset for digital restoration of Dunhuang murals","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Mural; Computer science; Cultural heritage; Inpainting; Segmentation; Safeguarding; Digital preservation; Digital image; Resource (disambiguation); Artificial intelligence; Visual arts; Image processing; World Wide Web; Archaeology; Image (mathematics); History; Art","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000340806,0.00111084,0.0007955366,0.002629595,0.0008519292,0.0009999188,0.001198342,0.001138029,0.006817362],"category_scores_gemma":[0.001007341,0.0002509589,0.0006930154,0.002108777,0.0005166781,0.0005619766,0.001158117,0.0006949787,0.006183919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006286869,"about_ca_system_score_gemma":0.0006745144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01700741,"about_ca_topic_score_gemma":0.05895024,"domain_scores_codex":[0.9994202,0.00006204948,0.00004904157,0.0001487326,0.0002095972,0.0001104387],"domain_scores_gemma":[0.9996479,0.00004214443,0.00003106869,0.0001217196,0.0001172966,0.00003987648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006469613,0.0005335147,0.01600852,0.003168323,0.0002806525,0.001824584,0.0008010141,0.0066495,0.02787929,0.001972649,0.6876329,0.252602],"study_design_scores_gemma":[0.0001070103,0.0001476077,0.07208903,0.0005569384,0.0001187305,0.002199171,0.001885401,0.0106511,0.01321616,0.001318955,0.8975947,0.0001152798],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.16834,0.009826011,0.01415013,0.001176381,0.001238328,0.0009365751,0.7516889,0.01367404,0.03896968],"genre_scores_gemma":[0.1031346,0.001265495,0.01969166,0.000223687,0.0001170925,0.0002908266,0.8678322,0.0004395332,0.007004967],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01700741,"threshold_uncertainty_score":0.03381681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1500181300858176,"score_gpt":0.3204950890234499,"score_spread":0.1704769589376322,"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."}}