{"id":"W7115568583","doi":"10.1109/cvprw63382.2024.11301672","title":"Retraction Notice: T2VBench: Benchmarking Temporal Dynamics for Text-to-Video Generation","year":2024,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Benchmarking; Benchmark (surveying); Dynamics (music); Generative grammar; Temporal database; Temporal scales","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":["research_integrity"],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01011242,0.001930983,0.0009966514,0.001856515,0.000980289,0.003423261,0.00244471,0.002154151,0.02179698],"category_scores_gemma":[0.07521517,0.0003929913,0.0009251526,0.001316712,0.0007927548,0.003146171,0.002765204,0.003006026,0.01115184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001917663,"about_ca_system_score_gemma":0.002369227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01274395,"about_ca_topic_score_gemma":0.01535643,"domain_scores_codex":[0.9919436,0.002658004,0.0006598058,0.001090911,0.003279973,0.0003676909],"domain_scores_gemma":[0.9694486,0.0133203,0.0008823162,0.003628892,0.01088447,0.001835397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009174799,0.0002216318,0.003513595,0.001100912,0.000141912,0.0003526123,0.0003920489,0.01747105,0.009945882,0.005686881,0.7694079,0.1908481],"study_design_scores_gemma":[0.0008172343,0.002179115,0.0110235,0.0007356874,0.000192327,0.001194581,0.0007521008,0.3081098,0.04090619,0.01210723,0.6215861,0.0003961207],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"editorial","genre_scores_codex":[0.1120553,0.008466326,0.4289454,0.01937973,0.05733198,0.003615625,0.1299258,0.1620539,0.07822585],"genre_scores_gemma":[0.3291404,0.002087516,0.3090693,0.005453517,0.003231717,0.002725074,0.2591023,0.02435466,0.06483542],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.9978458,"threshold_uncertainty_score":0.07291812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03208427690256058,"score_gpt":0.3291478281031487,"score_spread":0.2970635512005881,"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."}}