{"id":"W4393148525","doi":"10.1609/aaai.v38i5.28272","title":"SeTformer Is What You Need for Vision and Language","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Vetenskapsrådet; Knut och Alice Wallenbergs Stiftelse","keywords":"Computer science; Linguistics; Philosophy","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":[0.001564142,0.002413531,0.001156379,0.0009604467,0.0008997554,0.004401116,0.002532833,0.002338321,0.09233],"category_scores_gemma":[0.008125362,0.001269553,0.001557196,0.001025612,0.001435475,0.01124825,0.003761439,0.004365063,0.07900098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001238093,"about_ca_system_score_gemma":0.001697249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004127287,"about_ca_topic_score_gemma":0.006467925,"domain_scores_codex":[0.9989989,0.0001810544,0.00006349768,0.0002459217,0.0003843116,0.0001262963],"domain_scores_gemma":[0.9977427,0.0005092188,0.00009158777,0.0009038027,0.0005332197,0.0002195776],"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":[0.000433214,0.0001238016,0.0009841636,0.0004796012,0.0001067619,0.0003033371,0.000317419,0.005000246,0.02706334,0.03852879,0.2826566,0.6440027],"study_design_scores_gemma":[0.0001270207,0.0002654798,0.001284062,0.0002806968,0.0001206698,0.001014649,0.0003694567,0.08380991,0.04852415,0.1434576,0.7205676,0.0001786697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005132234,0.002525477,0.8307467,0.01794017,0.002692987,0.0002411427,0.003468794,0.09138823,0.04586418],"genre_scores_gemma":[0.1162513,0.003631979,0.7336235,0.01416593,0.001395552,0.0005350653,0.00850285,0.01683339,0.1050603],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09233,"threshold_uncertainty_score":0.3088747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05020884113658372,"score_gpt":0.3140827375632839,"score_spread":0.2638738964267002,"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."}}