{"id":"W4409367125","doi":"10.1609/aaai.v39i7.32769","title":"RealisID: Scale-Robust and Fine-Controllable Identity Customization via Local and Global Complementation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Cognitive Computing and Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Complementation; Personalization; Scale (ratio); Identity (music); Computer science; Human–computer interaction; World Wide Web; Biology; Geography; Art; Genetics; Aesthetics; Cartography","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":[0.0008509324,0.0008505693,0.0008083404,0.0006054819,0.0004416643,0.0008437146,0.002204742,0.0007363752,0.002472456],"category_scores_gemma":[0.001507225,0.0004551159,0.0007046785,0.0003938404,0.001264079,0.001353115,0.002122034,0.001430908,0.0009971063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007423423,"about_ca_system_score_gemma":0.0007605427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003248725,"about_ca_topic_score_gemma":0.004066017,"domain_scores_codex":[0.9994349,0.00007358316,0.00002080641,0.0002230841,0.0001756224,0.00007191268],"domain_scores_gemma":[0.999566,0.00009436608,0.00005072253,0.0001628534,0.00008265642,0.00004333161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003509136,0.0002623808,0.001638118,0.0001505718,0.00006789539,0.0002860305,0.0004560614,0.1991566,0.1348703,0.01936832,0.006993177,0.6363996],"study_design_scores_gemma":[0.00003161509,0.00009520983,0.0004450478,0.000009654223,0.00001270316,0.0001029238,0.00005994075,0.9574817,0.03067024,0.006526555,0.004538637,0.00002576992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03247029,0.0001538079,0.9600998,0.0001034985,0.00005647387,0.00008226527,0.00006353949,0.003294604,0.003675678],"genre_scores_gemma":[0.4834112,0.000200648,0.5016071,0.0003648152,0.00006448573,0.000220387,0.0004700916,0.0009355693,0.01272569],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003248725,"threshold_uncertainty_score":0.008271217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04033418163011707,"score_gpt":0.3016133730694952,"score_spread":0.2612791914393781,"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."}}