{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001589326,0.0004811402,0.0003434078,0.0005874098,0.0008677238,0.002595266,0.0009299935,0.0004749291,0.0003455245],"category_scores_gemma":[0.0003442476,0.0005073748,0.0002683616,0.001862851,0.00005968146,0.001304277,0.0003417025,0.000986736,0.0006331174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007851725,"about_ca_system_score_gemma":0.0004268738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001506203,"about_ca_topic_score_gemma":0.001300022,"domain_scores_codex":[0.995775,0.0001636959,0.0009214867,0.001760977,0.0006608767,0.0007179031],"domain_scores_gemma":[0.9973112,0.0006449427,0.0002015056,0.001117709,0.0003754325,0.0003492016],"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":[0.00001467044,0.0001410337,0.0008445552,0.0002366672,0.00007238144,0.000005797276,0.001175341,0.04518799,0.002505658,0.1751339,0.01560872,0.7590733],"study_design_scores_gemma":[0.0001893763,0.0003089889,0.003558823,0.0001396588,0.00007285084,0.00002482324,0.00003389596,0.9579786,0.0002240978,0.001010654,0.03587588,0.0005823324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0120619,0.000227539,0.9527007,0.02243727,0.007264636,0.001859443,0.0000510888,0.0006701449,0.002727248],"genre_scores_gemma":[0.7024659,0.00001325982,0.2913362,0.000477295,0.002442728,0.0002797123,0.0002191433,0.00005651652,0.002709222],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9127907,"threshold_uncertainty_score":0.9997378,"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."}}