{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007469812,0.0004251751,0.0003541169,0.001119619,0.0003240305,0.0009183667,0.001713272,0.0002926553,0.00001269911],"category_scores_gemma":[0.00009252292,0.0004236036,0.00008165185,0.0007879056,0.0005269156,0.001411288,0.001293973,0.001244877,0.00005751297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003442554,"about_ca_system_score_gemma":0.0004479715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001629645,"about_ca_topic_score_gemma":0.00002895542,"domain_scores_codex":[0.9973132,0.0000220487,0.0004361527,0.001018701,0.0007155314,0.000494367],"domain_scores_gemma":[0.9981763,0.0004521956,0.0002302876,0.0008062607,0.0001520331,0.0001828853],"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":[0.000002608266,0.000005037327,0.00006941816,0.0000427331,0.00001148534,0.00002131227,0.004466603,0.03882652,0.00003346474,0.09429175,0.000007739723,0.8622213],"study_design_scores_gemma":[0.0001919382,0.00008219004,0.0004607524,0.0002707087,0.000009705698,0.0000565213,0.00000137154,0.9428531,0.00004311948,0.05099243,0.004580496,0.0004576939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004902272,0.0001390202,0.9904026,0.001356915,0.0009933759,0.0003378051,0.000008208249,0.0003307101,0.005941177],"genre_scores_gemma":[0.5437327,0.00003063612,0.4551463,0.0006130256,0.0002788795,0.000006625528,0.0000168161,0.00002586265,0.0001491133],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9040266,"threshold_uncertainty_score":0.9998216,"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."}}