{"id":"W3214266825","doi":"","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Autoregressive model; Transformer; Texture synthesis; Minimum bounding box; Permutation (music); Floor plan; Architecture; Artificial intelligence; Embedding; Computer vision; Algorithm; Image (mathematics); Engineering drawing; Image processing; Engineering; 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":[0.0002645388,0.0001423397,0.0002002814,0.00005103462,0.0003871659,0.0004949366,0.0001029529,0.00009149294,0.0001396655],"category_scores_gemma":[0.0002055317,0.0001069906,0.00006854277,0.0001981586,0.00003496138,0.002079809,0.000002845134,0.00009418272,0.00007510761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009749598,"about_ca_system_score_gemma":0.0001083378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001710964,"about_ca_topic_score_gemma":0.0001244351,"domain_scores_codex":[0.9988564,0.00006689484,0.0004114422,0.000132673,0.0002620472,0.0002705754],"domain_scores_gemma":[0.9992278,0.0001466942,0.0001865042,0.00006913296,0.0002695874,0.000100283],"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":[0.00005693498,0.000008482414,0.01449203,0.001087576,0.00002217161,0.000004939181,0.001872425,0.002720682,0.00009618526,0.00003638611,0.001470547,0.9781317],"study_design_scores_gemma":[0.0009875438,0.0001728878,0.07156441,0.001146205,0.00007625289,0.0003033799,0.01214366,0.8302652,0.003944431,0.00004141729,0.07842078,0.0009338308],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8988741,0.01024006,0.02021952,0.002344365,0.006042069,0.002503307,0.001951579,0.001170181,0.05665479],"genre_scores_gemma":[0.9985248,0.00001560044,0.0003835347,0.0002007317,0.0001004605,0.00002269681,0.0003362201,0.000003460565,0.0004124282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9771978,"threshold_uncertainty_score":0.4772685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02360552716175293,"score_gpt":0.2305080485321016,"score_spread":0.2069025213703486,"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."}}