{"id":"W4402754204","doi":"10.1109/cvpr52733.2024.02118","title":"GlitchBench: Can Large Multimodal Models Detect Video Game Glitches?","year":2024,"lang":"en","type":"article","venue":"","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Science Foundation","keywords":"Computer science; Video game; Artificial intelligence; Real-time computing; Computer vision; Human–computer interaction; Multimedia","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042768,0.0001680192,0.0001926947,0.00019992,0.00009206094,0.0006213606,0.0005909008,0.00008498642,0.0001226874],"category_scores_gemma":[0.00003292276,0.0001344958,0.000157103,0.0009125929,0.00001584243,0.0008901618,0.0002313628,0.000143317,0.0001125519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006932774,"about_ca_system_score_gemma":0.0001258552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003792075,"about_ca_topic_score_gemma":0.0006282508,"domain_scores_codex":[0.998327,0.00006085124,0.0002944845,0.0005840042,0.0003603415,0.000373351],"domain_scores_gemma":[0.9990931,0.00008016325,0.00003119794,0.0005776401,0.00008613295,0.0001317357],"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":[0.000004606358,0.00009299107,0.0003914303,0.00006782918,0.0001737006,0.0001025614,0.002633828,0.01453245,0.002810376,0.8260754,0.004089938,0.1490249],"study_design_scores_gemma":[0.0001158405,0.00002337068,0.0001751622,0.00001833508,0.00001610581,0.000004809267,0.00002551368,0.9678862,0.001263151,0.02462243,0.005661184,0.0001879101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00609405,0.0004960981,0.9855862,0.001284906,0.0003063596,0.000100338,0.000008774436,0.0005438131,0.005579512],"genre_scores_gemma":[0.9837309,0.00003259271,0.01383655,0.0005152969,0.00009307523,0.00001458915,0.0000105985,0.00001322382,0.001753174],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9776369,"threshold_uncertainty_score":0.5991795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0148359313499549,"score_gpt":0.2396708866345827,"score_spread":0.2248349552846279,"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."}}