{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001999737,0.002146645,0.0007438808,0.00143308,0.0005080706,0.002730843,0.002378658,0.002087326,0.008119853],"category_scores_gemma":[0.01865384,0.0005514646,0.001073957,0.0005252195,0.0008315662,0.003579,0.002853321,0.00200398,0.003310822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028371,"about_ca_system_score_gemma":0.001185274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01545992,"about_ca_topic_score_gemma":0.01853948,"domain_scores_codex":[0.9986475,0.0004570713,0.00007427405,0.0004152872,0.0002607162,0.00014519],"domain_scores_gemma":[0.9956505,0.00271129,0.0002262023,0.0006803831,0.000495484,0.0002360855],"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":[0.003187736,0.0009271079,0.022726,0.002222596,0.0006878163,0.0008908379,0.001652426,0.1347215,0.03189464,0.01276937,0.08747279,0.7008471],"study_design_scores_gemma":[0.0001399437,0.0004863883,0.005886174,0.0001841546,0.00008019733,0.0003151823,0.0005797316,0.9476622,0.01521019,0.01733909,0.01203934,0.00007746846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3010363,0.003556381,0.5610428,0.002607462,0.0008522287,0.001607723,0.01718928,0.08657134,0.02553645],"genre_scores_gemma":[0.6738213,0.0005435657,0.2943281,0.0009038036,0.00007811827,0.0007510903,0.02090783,0.002428959,0.006237233],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01545992,"threshold_uncertainty_score":0.0307399,"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."}}