{"id":"W4406091633","doi":"10.7717/peerj-cs.2553","title":"GAN inversion and shifting: recommending product modifications to sellers for better user preference","year":2025,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Waterloo","funders":"","keywords":"Computer science; Recommender system; Preference; Bridging (networking); Product (mathematics); Similarity (geometry); Customer needs; Human–computer interaction; Information retrieval; Artificial intelligence; Marketing; Business; Image (mathematics)","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":[0.0007984784,0.0001555346,0.0001591208,0.0003177252,0.0007383323,0.0006713938,0.001285798,0.00002583442,0.000002105056],"category_scores_gemma":[0.0001285865,0.0001417437,0.0000381335,0.001286932,0.0001466552,0.0009320399,0.00067769,0.00008684991,0.000007472544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006543976,"about_ca_system_score_gemma":0.0001424337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001581273,"about_ca_topic_score_gemma":0.00000592998,"domain_scores_codex":[0.9981719,0.00004964506,0.000207312,0.000927871,0.0002380442,0.0004052606],"domain_scores_gemma":[0.9987253,0.0001771099,0.000062627,0.0006081442,0.0002737498,0.0001530595],"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":[0.00002163667,0.0001550241,0.005489865,0.00007697061,0.00004442098,0.000001822953,0.004894927,0.04097932,0.02654067,0.03393434,0.09150873,0.7963523],"study_design_scores_gemma":[0.0001939932,0.00006553181,0.006566003,0.00005709685,0.0000075586,0.000001412785,0.00001694517,0.9474314,0.02550156,0.001559047,0.01836861,0.0002308766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01608984,0.00002994501,0.9609633,0.02110302,0.0009285964,0.0004615314,0.000002163427,0.00008930502,0.0003322987],"genre_scores_gemma":[0.5668636,0.000003761486,0.4310334,0.001781294,0.0000890616,0.00002987845,7.879081e-7,0.000003393323,0.0001948714],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9064521,"threshold_uncertainty_score":0.6474266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03963277696433789,"score_gpt":0.270945931785924,"score_spread":0.2313131548215861,"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."}}