{"id":"W4402670803","doi":"10.18653/v1/2024.findings-acl.66","title":"CoLLaVO: Crayon Large Language and Vision mOdel","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Defense Acquisition Program Administration; Ministry of Science and ICT, South Korea","keywords":"Computer science; Artificial intelligence; Human–computer interaction; Computer vision","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":[],"consensus_categories":[],"category_scores_codex":[0.0001367544,0.00007022473,0.00006671459,0.00006496692,0.00004594652,0.0002143068,0.0001777456,0.00003291709,0.00001928534],"category_scores_gemma":[0.00001475724,0.00005321307,0.00002264604,0.0002264714,0.00001317938,0.0007110519,0.0002191931,0.00007199187,0.00003615567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001310671,"about_ca_system_score_gemma":0.00001951002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002953421,"about_ca_topic_score_gemma":0.000002093905,"domain_scores_codex":[0.9994168,0.000009479213,0.00007802183,0.0002460464,0.0001082531,0.0001414196],"domain_scores_gemma":[0.9996801,0.00003512934,0.000007909564,0.0002126396,0.00001842254,0.00004581185],"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":[0.000004578453,0.00004032056,0.00001557879,0.00007962954,0.000008517822,0.0001295238,0.001353467,0.00001664323,0.0306105,0.5424622,0.02388035,0.4013986],"study_design_scores_gemma":[0.00008046789,0.00007610543,0.00002434993,0.00004449891,0.000002360712,0.00001465131,0.00003575478,0.9018574,0.05833897,0.01787394,0.02151766,0.0001338004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001768848,0.001708448,0.9822574,0.0004645876,0.00004730469,0.00007558057,0.000002521591,0.0008563235,0.01281899],"genre_scores_gemma":[0.7109726,0.0002604053,0.2796052,0.0006805108,0.00003094512,0.00000590432,0.000001012863,0.00001033556,0.008433071],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9018408,"threshold_uncertainty_score":0.2169966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00914918910983499,"score_gpt":0.3375273162868338,"score_spread":0.3283781271769988,"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."}}