{"id":"W4404545360","doi":"10.1007/978-3-031-73021-4_23","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmarking; Computer science; Training (meteorology); Artificial intelligence; Human–computer interaction; Geography","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":[0.006528571,0.002881408,0.001856621,0.003137984,0.001367463,0.002191655,0.004154308,0.002933038,0.0122441],"category_scores_gemma":[0.01208699,0.001082303,0.001406699,0.002221855,0.0009597282,0.004986966,0.003682235,0.002155768,0.009733526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001600446,"about_ca_system_score_gemma":0.001734637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008926051,"about_ca_topic_score_gemma":0.01202074,"domain_scores_codex":[0.9955918,0.001350391,0.0003605655,0.001509428,0.000749341,0.000438393],"domain_scores_gemma":[0.9953511,0.002296779,0.0001693222,0.00107401,0.0008527973,0.0002559899],"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":[0.001837269,0.001283767,0.004070815,0.001008419,0.0005464348,0.000208391,0.0003137338,0.03175222,0.02002373,0.001722146,0.0667436,0.8704895],"study_design_scores_gemma":[0.000575398,0.002485386,0.007268573,0.000269183,0.0005318032,0.0006634914,0.0008742216,0.8594416,0.08982854,0.005244032,0.03262924,0.0001885755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.434063,0.01532241,0.3665792,0.0007802686,0.001760679,0.00157096,0.01327656,0.1455089,0.02113783],"genre_scores_gemma":[0.4937029,0.001734542,0.4196579,0.0008500927,0.000358782,0.001570662,0.04773988,0.005120001,0.02926527],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0122441,"threshold_uncertainty_score":0.04096061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01190080356280129,"score_gpt":0.2410022629830654,"score_spread":0.2291014594202641,"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."}}