{"id":"W7160112519","doi":"10.1109/iccv51701.2025.00687","title":"Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Canadian Institute for Advanced Research","keywords":"Context (archaeology); Modular design; Automated reasoning; Physical system; Knowledge representation and reasoning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001825971,0.001522917,0.001360372,0.001613773,0.001196755,0.004321139,0.005959105,0.002016958,0.01470597],"category_scores_gemma":[0.006587525,0.001761886,0.00406147,0.001044006,0.001612707,0.007365177,0.005593844,0.004637997,0.004705676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001133788,"about_ca_system_score_gemma":0.00191668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007245014,"about_ca_topic_score_gemma":0.01468185,"domain_scores_codex":[0.9989632,0.0002027125,0.00008322866,0.0002499069,0.0004055744,0.00009523866],"domain_scores_gemma":[0.9985387,0.0005509946,0.00008455991,0.0005199702,0.0002009002,0.000104828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003550218,0.000383574,0.001630797,0.0005781532,0.0003870706,0.0005286276,0.0009252208,0.1372728,0.009866848,0.5484906,0.02502935,0.274552],"study_design_scores_gemma":[0.00003350781,0.0000241583,0.0001595508,0.00005853537,0.00009086494,0.00005784503,0.00006419712,0.6135421,0.005807378,0.3657655,0.01435051,0.0000458361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001652816,0.0000801791,0.988608,0.0001900753,0.00004374462,0.00007750885,0.0003921991,0.007305792,0.001649743],"genre_scores_gemma":[0.140313,0.0003205121,0.8503685,0.0003755575,0.0001090411,0.0003812337,0.001571877,0.002037632,0.004522621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01470597,"threshold_uncertainty_score":0.0491963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01607597050264624,"score_gpt":0.3503052142448334,"score_spread":0.3342292437421871,"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."}}