{"id":"W4416035530","doi":"10.18653/v1/2025.emnlp-main.1379","title":"CAVE : Detecting and Explaining Commonsense Anomalies in Visual Environments","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Anomaly detection; Cave; Perception; Visual reasoning; Commonsense reasoning; Visualization; Cognition; Resource (disambiguation)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001278102,0.003277378,0.000948921,0.002711822,0.0009108338,0.002371206,0.004501909,0.002908499,0.01670272],"category_scores_gemma":[0.01000988,0.0006964845,0.002417485,0.001783327,0.0009402301,0.003547166,0.003390913,0.002854541,0.01072467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001803226,"about_ca_system_score_gemma":0.001480079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03537323,"about_ca_topic_score_gemma":0.06571553,"domain_scores_codex":[0.9982578,0.0003832936,0.00009786386,0.0006871971,0.0004105855,0.0001633773],"domain_scores_gemma":[0.9962942,0.001658704,0.0002419417,0.001111687,0.0004620346,0.000231443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009215368,0.0004920692,0.008495989,0.002083001,0.0002775039,0.0005357017,0.000439484,0.0160532,0.004742091,0.004243325,0.8583131,0.103403],"study_design_scores_gemma":[0.001231895,0.0007236805,0.0382988,0.001069,0.000254914,0.001809606,0.001580026,0.3844517,0.02282228,0.03994201,0.5074184,0.000397848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.07072517,0.002326245,0.06009723,0.002078975,0.0008261803,0.001577109,0.668897,0.1748951,0.01857705],"genre_scores_gemma":[0.07233521,0.0003315957,0.07550322,0.0005392566,0.00007764499,0.0008601901,0.8420798,0.002779062,0.005494032],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03537323,"threshold_uncertainty_score":0.07033467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007723986487770126,"score_gpt":0.2779768870020778,"score_spread":0.2702529005143077,"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."}}