{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001237756,0.0003199584,0.0003581493,0.000524314,0.0001728518,0.0003254056,0.004884118,0.0001737119,0.0001866762],"category_scores_gemma":[0.0004719733,0.000263621,0.00002120686,0.001352997,0.000424754,0.0006335952,0.002445115,0.0004071534,0.00002578999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009108995,"about_ca_system_score_gemma":0.001202088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002162096,"about_ca_topic_score_gemma":0.003295389,"domain_scores_codex":[0.9966872,0.00005204479,0.0003119005,0.001613767,0.0007078462,0.0006272583],"domain_scores_gemma":[0.9967991,0.0001110975,0.0002316137,0.002634011,0.0001013463,0.0001228645],"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":[0.0000792126,0.001330931,0.0006480567,0.001832103,0.0002027007,0.002513607,0.006351901,0.06532488,0.006738205,0.2237461,0.1014898,0.5897425],"study_design_scores_gemma":[0.0002639934,0.0000457993,0.00002062979,0.001721085,0.00001129621,0.00003184846,0.0001784456,0.9831669,0.0007351831,0.002331087,0.01102395,0.0004697531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00001922073,0.0002611972,0.5992929,0.0006346932,0.0002215518,0.0001807534,0.00001571581,0.0001949391,0.399179],"genre_scores_gemma":[0.4355879,0.0000740188,0.3214798,0.0004724202,0.0003239811,0.00002514519,0.0001173032,0.00006525437,0.2418541],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.917842,"threshold_uncertainty_score":0.9999816,"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."}}