{"id":"W6891602650","doi":"10.48448/4xrw-rg22","title":"MagiCapture: High-Resolution Multi-Concept Portrait Customization","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Personalization; Portrait; Artifact (error); Pipeline (software); Identity (music); Task (project management); Quality (philosophy); Ground truth","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":[0.0006082924,0.001486487,0.0006165836,0.0006476701,0.0002540663,0.0009977074,0.002285398,0.001348284,0.01503149],"category_scores_gemma":[0.001962282,0.0007106372,0.00168066,0.0003803384,0.0005284922,0.001611014,0.001528638,0.00202304,0.005031924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006294771,"about_ca_system_score_gemma":0.0003318157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001819381,"about_ca_topic_score_gemma":0.003428275,"domain_scores_codex":[0.9997057,0.0000453363,0.00001081291,0.0001201229,0.00009021549,0.00002771281],"domain_scores_gemma":[0.9995191,0.0001831661,0.00002909787,0.0001705995,0.00005827063,0.00003984302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003724651,0.0002727665,0.001144403,0.0009122877,0.000287917,0.0006722016,0.0004201164,0.2562607,0.1105948,0.00873786,0.04264132,0.5776833],"study_design_scores_gemma":[0.00005828324,0.0001311881,0.0004353114,0.00004131963,0.00003070939,0.0004510049,0.00005301888,0.9363681,0.03587445,0.006776248,0.019736,0.00004441485],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02628003,0.00107356,0.9326736,0.0003773824,0.0002872332,0.0003060405,0.001272203,0.03003186,0.007698142],"genre_scores_gemma":[0.2835428,0.0008610561,0.6859916,0.0007168642,0.0001060529,0.0004391593,0.004743045,0.005232124,0.01836732],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01503149,"threshold_uncertainty_score":0.05028534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0215709962695352,"score_gpt":0.2934809337421486,"score_spread":0.2719099374726134,"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."}}