{"id":"W4415289293","doi":"10.1109/iccv51701.2025.02460","title":"NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Canadian Institute for Advanced Research","keywords":"Inpainting; Leverage (statistics); Ranging; Focus (optics); Expansive; Process (computing); Set (abstract data type)","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":[],"consensus_categories":[],"category_scores_codex":[0.0002906892,0.0002636459,0.0003797249,0.0002824579,0.00008068156,0.0001542142,0.001176904,0.0001581696,0.00001077316],"category_scores_gemma":[0.0001108191,0.0002392754,0.0001648178,0.0003707891,0.00004854706,0.0002343067,0.002055957,0.0002930863,0.000005214109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009927669,"about_ca_system_score_gemma":0.0002367431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005887233,"about_ca_topic_score_gemma":0.00000387085,"domain_scores_codex":[0.9981751,0.00006266309,0.0004930603,0.0006780098,0.0003552195,0.0002359201],"domain_scores_gemma":[0.9981681,0.00005850047,0.0002310349,0.001154439,0.0003329042,0.00005507156],"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":[0.00002782319,0.0005023953,0.0002489705,0.001163854,0.0001533524,0.00002136483,0.001458514,0.0304713,0.02735767,0.3046511,0.002712765,0.631231],"study_design_scores_gemma":[0.0001294354,0.00004360457,0.00009858934,0.0002755076,0.00001447604,0.000001143073,0.00001444968,0.1180652,0.8723453,0.007031436,0.001666076,0.0003147518],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004904767,0.0005607013,0.9889435,0.0002271454,0.001109252,0.0004077751,0.000008099772,0.0005336854,0.003305055],"genre_scores_gemma":[0.3193559,0.0007606434,0.6776199,0.000192404,0.0002071651,0.0001556053,0.00001986082,0.0000150283,0.001673483],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8449876,"threshold_uncertainty_score":0.9757369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1514160570516142,"score_gpt":0.3400950745186135,"score_spread":0.1886790174669993,"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."}}