{"id":"W4377013849","doi":"10.1007/s00371-023-02875-1","title":"Feature fusion and decomposition: exploring a new way for Chinese calligraphy style classification","year":2023,"lang":"en","type":"article","venue":"The Visual Computer","topic":"Color perception and design","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Calligraphy; Computer science; Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Classifier (UML); Feature extraction; Painting","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001821594,0.0001046252,0.0001031146,0.000111421,0.0001923468,0.00005613227,0.00009888006,0.00006303868,0.0001153424],"category_scores_gemma":[0.000003208696,0.00007068351,0.0000656804,0.0003182994,0.00002712883,0.00006417597,0.00004849404,0.00009680294,0.0002276379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001034566,"about_ca_system_score_gemma":0.00000631468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001394049,"about_ca_topic_score_gemma":0.00001098735,"domain_scores_codex":[0.9993573,0.00007592686,0.00009619992,0.0002251498,0.00008556877,0.0001598327],"domain_scores_gemma":[0.999525,0.0001740464,0.00003578004,0.0001696687,0.0000288541,0.00006667712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0008694131,0.0001971893,0.003928432,0.00004207767,0.0001148687,0.000009305518,0.01781374,0.00005325786,0.0177509,0.009907308,0.5733222,0.3759914],"study_design_scores_gemma":[0.001350895,0.0005275625,0.9093986,0.00002380129,0.00002494138,0.00002181725,0.000484706,0.03819304,0.00004271248,0.001122251,0.04858369,0.0002259866],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9372324,0.00005396685,0.05615615,0.004807606,0.0008462257,0.000385548,0.000004331981,0.0002346405,0.0002790857],"genre_scores_gemma":[0.9947673,0.00002646097,0.001298746,0.0007041162,0.001091399,0.0001187218,0.00005101024,0.00001918838,0.001923021],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9054701,"threshold_uncertainty_score":0.29259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1120091449120094,"score_gpt":0.4017412024759889,"score_spread":0.2897320575639795,"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."}}