{"id":"W4412887130","doi":"10.18653/v1/2025.acl-demo.36","title":"FORG3D: Flexible Object Rendering for Generating Vision-Language Spatial Reasoning Data from 3D Scenes","year":2025,"lang":"en","type":"article","venue":"","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Rendering (computer graphics); Artificial intelligence; Computer vision; Computer graphics (images); Spatial intelligence; Image-based modeling and rendering; Object based; Object (grammar)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002370518,0.000108588,0.0001231536,0.0001046033,0.000272425,0.000358773,0.0005601601,0.00004982619,0.0001033602],"category_scores_gemma":[0.000198233,0.0001043729,0.00003134585,0.0002273124,0.00001509497,0.0006630619,0.0004746712,0.0000649297,0.000006233272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003328593,"about_ca_system_score_gemma":0.000120937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007691866,"about_ca_topic_score_gemma":0.001022105,"domain_scores_codex":[0.9989511,0.00003047459,0.0002230339,0.0004848455,0.0001284442,0.0001821003],"domain_scores_gemma":[0.9989445,0.0001804603,0.00006557853,0.0007169328,0.00005271528,0.00003980111],"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":[0.00001131486,0.00002104033,0.001102112,0.00001812581,0.00003801672,0.00000237967,0.0004350535,0.008673875,0.006764793,0.007954971,0.002818397,0.9721599],"study_design_scores_gemma":[0.0003528984,0.00001355954,0.0008684379,0.00005296149,0.000008090015,0.000001354479,0.0001222339,0.9922208,0.004983232,0.0001879717,0.001067508,0.0001209408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002134809,0.0001132067,0.992645,0.0003952642,0.0006014439,0.0001866704,0.00002356303,0.0003120798,0.003588017],"genre_scores_gemma":[0.2123317,0.00000978711,0.7861642,0.0004065885,0.0001223954,0.00001177312,0.0001457405,0.000006869134,0.0008008911],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9835469,"threshold_uncertainty_score":0.4256202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02668598038903537,"score_gpt":0.3208259843642277,"score_spread":0.2941400039751923,"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."}}