{"id":"W4414861598","doi":"10.1038/s40494-025-02066-2","title":"Dual-stream multi-layer cross encoding network for texture analysis of architectural heritage elements","year":2025,"lang":"en","type":"article","venue":"npj Heritage Science","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Minjiang University","keywords":"Encoding (memory); Texture (cosmology); Feature (linguistics); Deep learning; Joint (building); Binary number; Artificial neural network","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":[],"consensus_categories":[],"category_scores_codex":[0.001281192,0.0001968349,0.0003402946,0.000455399,0.0005189592,0.0004034821,0.001683808,0.00007779458,0.000018817],"category_scores_gemma":[0.0002629484,0.0001705076,0.0002272198,0.006031116,0.0005283447,0.0006819544,0.0004220583,0.0001502059,0.000002480826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009717725,"about_ca_system_score_gemma":0.0002138884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002389526,"about_ca_topic_score_gemma":0.00003229814,"domain_scores_codex":[0.9975932,0.00004930657,0.0005235979,0.0007443178,0.0005056556,0.0005839248],"domain_scores_gemma":[0.9982611,0.000153375,0.0002398325,0.0008218953,0.0004204479,0.0001033774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006271151,0.000441654,0.0483093,0.000214602,0.0004356056,0.00001443034,0.002611409,0.00110961,0.6046968,0.05901008,0.000470806,0.282623],"study_design_scores_gemma":[0.000754129,0.0001790085,0.1324749,0.000121538,0.0001707484,0.000004465957,0.0002720149,0.6324517,0.2277527,0.002049616,0.003169509,0.0005997125],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03933822,0.0001941712,0.9579182,0.0002947563,0.0003116071,0.0004440962,0.00003104467,0.0002208357,0.001247119],"genre_scores_gemma":[0.7976047,0.000009571511,0.2007,0.0002249968,0.00002791405,0.00004832038,0.000005221259,0.0000052563,0.001374006],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7582665,"threshold_uncertainty_score":0.6953096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02893751602113888,"score_gpt":0.342468883202841,"score_spread":0.3135313671817022,"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."}}