{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001881023,0.00007073728,0.00008059638,0.0001244711,0.0001187079,0.00006548921,0.0001798653,0.00002827333,0.000003631465],"category_scores_gemma":[0.00005879049,0.00007118916,0.00001049501,0.0002032977,0.00002744122,0.000105449,0.0003006633,0.0001294155,0.0000096792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002868995,"about_ca_system_score_gemma":0.000009707907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006223302,"about_ca_topic_score_gemma":0.0001029465,"domain_scores_codex":[0.999368,0.00006225135,0.0001309011,0.0002379555,0.00006331202,0.0001376548],"domain_scores_gemma":[0.9994799,0.000259831,0.00002875015,0.0002004344,0.000003213376,0.00002782521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004835337,0.00006693651,0.7326713,0.00001119839,0.00001067192,0.000008738917,0.002477165,0.0009791688,0.006703273,0.02789545,0.00001965856,0.2291516],"study_design_scores_gemma":[0.0002153966,0.00001469847,0.5432405,0.00001419006,0.000001233125,0.000003947943,0.0001960019,0.4540408,0.001407459,0.0005478956,0.0002379372,0.00007996975],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7473465,0.00002500351,0.2490016,0.0006066519,0.00002042995,0.00007439255,1.077088e-7,0.00005973464,0.002865602],"genre_scores_gemma":[0.9598317,0.000002503877,0.03974796,0.0001775361,0.000004051477,0.00002046465,3.617084e-7,0.000002896027,0.0002125352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4530616,"threshold_uncertainty_score":0.2903009,"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."}}