{"id":"W7082258247","doi":"10.48448/zv8b-3h49","title":"SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spatial intelligence; Bridge (graph theory); Construct (python library); Closed captioning; Key (lock); Spatial relation; Spatial analysis; Robotics; Synthetic data","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":[0.002140994,0.002221933,0.0007325941,0.001485946,0.0006135239,0.002231663,0.003683628,0.00210629,0.009423231],"category_scores_gemma":[0.01158871,0.0005593296,0.002163264,0.001294861,0.0007649186,0.00365143,0.001888256,0.002711401,0.005200371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001956234,"about_ca_system_score_gemma":0.001727528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03055418,"about_ca_topic_score_gemma":0.04651712,"domain_scores_codex":[0.9984453,0.0005058462,0.00009723591,0.000603434,0.0002475837,0.000100629],"domain_scores_gemma":[0.9968348,0.001678463,0.0001234725,0.0007936238,0.0004344049,0.0001352341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009948378,0.001084768,0.007639186,0.001843298,0.0006062705,0.0004991879,0.0005505209,0.2689234,0.008134228,0.01205685,0.2514386,0.446229],"study_design_scores_gemma":[0.0002081252,0.0001791238,0.001055305,0.0001288402,0.00006913362,0.0001686684,0.0003032643,0.9467941,0.006038849,0.01695869,0.02804692,0.00004895562],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1650815,0.006992712,0.5253846,0.005141987,0.001888691,0.001210815,0.09658664,0.16926,0.02845299],"genre_scores_gemma":[0.413767,0.0008556835,0.4062878,0.002368788,0.0001919841,0.0006998524,0.1659011,0.00203826,0.007889516],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03055418,"threshold_uncertainty_score":0.06075269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.015895039186548,"score_gpt":0.2721519323356744,"score_spread":0.2562568931491264,"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."}}