{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007198239,0.0004466012,0.0005242923,0.0007393411,0.0001904278,0.000390327,0.002910736,0.0002166409,0.00001023732],"category_scores_gemma":[0.0002462082,0.0004147055,0.0001380399,0.0005545322,0.0006927061,0.0005100315,0.001208234,0.0006623841,0.00001906277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003675087,"about_ca_system_score_gemma":0.0003782705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002126836,"about_ca_topic_score_gemma":0.00007110508,"domain_scores_codex":[0.9967456,0.00002468927,0.0005826677,0.001467334,0.0006723732,0.0005072639],"domain_scores_gemma":[0.995375,0.002578619,0.0003152975,0.00147235,0.0001154113,0.0001433514],"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":[0.000008423173,0.00004759813,0.00001994139,0.0002811088,0.00004066575,0.00007818734,0.005029857,0.3841874,0.0002236758,0.5285305,0.0003135163,0.08123912],"study_design_scores_gemma":[0.0001568666,0.00008987411,0.000004120073,0.0003322515,0.00001282074,0.00001782497,0.000001142311,0.6200466,0.0002112628,0.3785673,0.0002717914,0.0002882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00002963461,0.0008044397,0.9952172,0.001068903,0.0006583696,0.0008654764,0.0007161218,0.0001530478,0.000486822],"genre_scores_gemma":[0.6013475,0.00001313936,0.3974792,0.00046021,0.0002063663,0.00005474471,0.0002905715,0.00004856969,0.00009967951],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6013179,"threshold_uncertainty_score":0.9998305,"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."}}