{"id":"W4409787564","doi":"10.61091/jcmcc127a-401","title":"A study on optimizing deep learning models for creative generation of animated new media advertisements: an application based on improved generative adversarial networks (GANs) and variational autocoders (VAEs)","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Generative grammar; Adversarial system; Computer science; Artificial intelligence; Deep learning; Generative adversarial network; Generative model; Machine learning; Multimedia","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001694043,0.000948874,0.0006629403,0.0003743127,0.0002111001,0.0007306151,0.0009829393,0.0009022661,0.001346338],"category_scores_gemma":[0.003339214,0.0004372627,0.0006990316,0.000312609,0.0006347997,0.001123098,0.0007593152,0.00141249,0.000214334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007847838,"about_ca_system_score_gemma":0.000665814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004169001,"about_ca_topic_score_gemma":0.002634192,"domain_scores_codex":[0.999585,0.0001552111,0.00001721963,0.00011254,0.00008177114,0.00004831681],"domain_scores_gemma":[0.9987636,0.0008880039,0.00007080942,0.00008337606,0.0001440435,0.00005016631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005335295,0.00004981586,0.0007641517,0.00006736146,0.0000444848,0.00005160607,0.0000473877,0.9448397,0.002644582,0.007283296,0.000678759,0.04347546],"study_design_scores_gemma":[0.000002425232,0.00001740583,0.00005200033,0.000002834946,0.000004192016,0.000008148856,0.000002445671,0.9987051,0.0004228265,0.0006394229,0.0001413456,0.000001833018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07030486,0.001476623,0.922233,0.0004990394,0.00009099251,0.00007818697,0.00004589349,0.0004695274,0.004801815],"genre_scores_gemma":[0.8741925,0.0008405659,0.1192312,0.0002751431,0.00005941852,0.0001150341,0.000133524,0.0001118318,0.005040873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004169001,"threshold_uncertainty_score":0.008959055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0424589621275114,"score_gpt":0.3377650313920022,"score_spread":0.2953060692644908,"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."}}