{"id":"W7106810235","doi":"10.48448/pfp1-yr71","title":"CAVE : Detecting and Explaining Commonsense Anomalies in Visual Environments","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Commonsense reasoning; Anomaly detection; Cave; Perception; Commonsense knowledge; Cognition; Visualization","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":[0.001805856,0.001272733,0.0004071987,0.001649551,0.0008494128,0.002456222,0.002847122,0.002506231,0.006876997],"category_scores_gemma":[0.0282497,0.0004282917,0.001227044,0.0006285246,0.002211719,0.006165809,0.004087268,0.002176747,0.001151212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001169002,"about_ca_system_score_gemma":0.001704473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008113906,"about_ca_topic_score_gemma":0.01300894,"domain_scores_codex":[0.9983176,0.0006125125,0.00008009413,0.0004487314,0.0004231135,0.0001180119],"domain_scores_gemma":[0.9879941,0.008183231,0.0007088053,0.001911706,0.0008354747,0.0003666831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001174191,0.0006625976,0.02558778,0.002359371,0.0003606344,0.001612513,0.005889318,0.1477927,0.03186324,0.1644529,0.07071942,0.5475254],"study_design_scores_gemma":[0.00009366631,0.0001773204,0.004029233,0.0002747356,0.00008300006,0.0007554997,0.001104829,0.6430591,0.01633449,0.2890586,0.04490476,0.0001247678],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1069252,0.001311011,0.8157765,0.003249598,0.0002577002,0.0003989296,0.004052614,0.04864522,0.01938319],"genre_scores_gemma":[0.5940504,0.0003614415,0.3965375,0.0006955893,0.0000503986,0.0001592846,0.004394409,0.001167783,0.002583341],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008113906,"threshold_uncertainty_score":0.0230059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03644291980475214,"score_gpt":0.323851672177058,"score_spread":0.2874087523723058,"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."}}