{"id":"W4414929823","doi":"10.1007/s10032-025-00559-1","title":"CalliNet: a triplet network for chinese calligraphy style classification","year":2025,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Color perception and design","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Science Foundation of Jiangxi Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Calligraphy; Discriminative model; Robustness (evolution); Style (visual arts); Feature extraction; Pattern recognition (psychology); Pooling; Feature (linguistics)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006855343,0.0001807759,0.0002891377,0.0009836142,0.0002179574,0.0003026522,0.0002049552,0.0001207212,0.004596058],"category_scores_gemma":[0.00006266651,0.0001444382,0.0004743277,0.0006466256,0.00004473297,0.0001292543,0.00002014684,0.0002260012,0.00008995185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009774775,"about_ca_system_score_gemma":0.00003173186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004348996,"about_ca_topic_score_gemma":0.0001048624,"domain_scores_codex":[0.9983482,0.0001624617,0.0006102929,0.0003339711,0.0003382427,0.0002068521],"domain_scores_gemma":[0.9987035,0.00024957,0.000311899,0.0001365386,0.000483833,0.0001146821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.006719443,0.00183167,0.1121032,0.00002520152,0.02427762,0.00006737115,0.001804003,0.001010812,0.0007410871,0.03036696,0.1598918,0.6611608],"study_design_scores_gemma":[0.007816596,0.0006633647,0.7366803,0.0001551219,0.002441294,0.00004895809,0.0007724312,0.007234667,0.00003831122,0.06329805,0.180165,0.0006858783],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7084631,0.0007729457,0.2516694,0.01367612,0.005463488,0.0008100863,0.000200544,0.0001071884,0.01883707],"genre_scores_gemma":[0.9875935,0.0005164069,0.001145127,0.002846804,0.0009559187,0.0001128533,0.0004103148,0.00001166148,0.006407356],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.660475,"threshold_uncertainty_score":0.9963139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02888770512613196,"score_gpt":0.3700693358111449,"score_spread":0.3411816306850129,"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."}}