{"id":"W4407450044","doi":"10.1109/tcyb.2025.3536165","title":"Personalizing Vision-Language Models With Hybrid Prompts for Zero-Shot Anomaly Detection","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"South University of Science and Technology of China; Ministry of Industry and Information Technology of the People's Republic of China; China Scholarship Council","keywords":"Zero (linguistics); Anomaly detection; Shot (pellet); Computer science; Ground zero; Anomaly (physics); Artificial intelligence; Natural language processing; Physics; Linguistics; Chemistry","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":[0.001371012,0.001761472,0.001104697,0.0009870713,0.0003140129,0.00126292,0.002555193,0.001372472,0.002905849],"category_scores_gemma":[0.006963238,0.000620805,0.001224528,0.0005113171,0.0006572031,0.003394581,0.002329505,0.002504211,0.001625154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009292035,"about_ca_system_score_gemma":0.001358512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004368846,"about_ca_topic_score_gemma":0.006540687,"domain_scores_codex":[0.9989729,0.0001865711,0.00004798172,0.0004992142,0.0001923566,0.0001010471],"domain_scores_gemma":[0.9982564,0.000829538,0.0001383874,0.0003381401,0.0003356582,0.0001018213],"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":[0.0008775656,0.0006287138,0.007819748,0.0003850063,0.0001437151,0.0005160864,0.0007139217,0.1611527,0.03626075,0.007496577,0.01534182,0.7686634],"study_design_scores_gemma":[0.00003550401,0.0001385075,0.000527669,0.00001587753,0.00002581319,0.00009194622,0.00009390448,0.9755951,0.009520968,0.01189059,0.002034341,0.00002980352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06970185,0.0004691662,0.8862759,0.0004951917,0.0001505973,0.0001844828,0.0009612647,0.04035613,0.001405398],"genre_scores_gemma":[0.6277494,0.0002126691,0.3641554,0.0008512862,0.0000710302,0.0003198553,0.002684945,0.0009932759,0.002961975],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004368846,"threshold_uncertainty_score":0.009721041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01531708000535554,"score_gpt":0.2699115341578634,"score_spread":0.2545944541525079,"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."}}