{"id":"W4404893151","doi":"10.1007/978-3-031-72897-6_19","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence","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":[0.001254309,0.00298985,0.001016084,0.003380964,0.0008282922,0.001613388,0.003430527,0.003121255,0.01483277],"category_scores_gemma":[0.007533285,0.0006145686,0.001859474,0.002486565,0.0006322297,0.001896906,0.001709089,0.002693183,0.01220017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001836894,"about_ca_system_score_gemma":0.002453742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03034848,"about_ca_topic_score_gemma":0.04313808,"domain_scores_codex":[0.9990029,0.0001909557,0.00009485232,0.0003288474,0.0002769265,0.0001056789],"domain_scores_gemma":[0.9974146,0.001108724,0.0001489868,0.0006234108,0.0004590656,0.0002452475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001465992,0.001218706,0.005835962,0.00226133,0.0004642171,0.0009404557,0.0002843961,0.01798747,0.01417953,0.004046672,0.7580483,0.193267],"study_design_scores_gemma":[0.001979563,0.001329585,0.0246431,0.0007771599,0.0006381109,0.002495553,0.001335602,0.364022,0.0537208,0.01977264,0.528804,0.0004819654],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0646027,0.002371958,0.04396762,0.0008433686,0.0006596195,0.001405378,0.8329862,0.04501923,0.008143941],"genre_scores_gemma":[0.03810112,0.0004031098,0.03644799,0.0002226923,0.00005353072,0.0007084,0.9197385,0.0007647236,0.003559928],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03034848,"threshold_uncertainty_score":0.06034368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03741656571281926,"score_gpt":0.3051162996673086,"score_spread":0.2676997339544893,"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."}}