{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009297759,0.001539733,0.0008751075,0.0009914633,0.0006370777,0.002814562,0.003193092,0.001143841,0.01784444],"category_scores_gemma":[0.00308224,0.001092121,0.002109904,0.0006681936,0.001176203,0.002169123,0.003202812,0.002490295,0.004848439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008528083,"about_ca_system_score_gemma":0.001055815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003480663,"about_ca_topic_score_gemma":0.006778291,"domain_scores_codex":[0.9993772,0.00008267083,0.00003774392,0.00009920556,0.0003456462,0.00005763159],"domain_scores_gemma":[0.9993107,0.0002909049,0.00003514339,0.0002002575,0.0001055802,0.00005736817],"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":[0.000647333,0.0002625416,0.002133645,0.001861548,0.0002670708,0.000857399,0.001881378,0.2734286,0.08165673,0.2050955,0.1427111,0.2891972],"study_design_scores_gemma":[0.0001406944,0.00004782452,0.0003382421,0.0001113487,0.00002945543,0.0003251264,0.0001456291,0.7530746,0.0534762,0.06168989,0.130502,0.0001189676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002315413,0.00007040779,0.9556186,0.0001063467,0.00006519585,0.00008166918,0.001665985,0.03527922,0.004797232],"genre_scores_gemma":[0.0895378,0.0002700748,0.8766799,0.0002512069,0.00002873934,0.0003528324,0.005702872,0.02326404,0.00391243],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01784444,"threshold_uncertainty_score":0.0596956,"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."}}