{"id":"W4396723194","doi":"10.1145/3589334.3645603","title":"Multimodal Relation Extraction via a Mixture of Hierarchical Visual Context Learners","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Universitas Brawijaya","keywords":"Computer science; Relation (database); Relationship extraction; Context (archaeology); Extraction (chemistry); Artificial intelligence; Context model; Natural language processing; Data mining; Chromatography; Chemistry","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":[0.0002480056,0.0001125518,0.0001216281,0.0001799054,0.00007636056,0.00009139564,0.000289945,0.0001101636,0.00008621279],"category_scores_gemma":[0.0000691654,0.0001006269,0.00008625048,0.0004827755,0.00005393909,0.0004234102,0.00008575993,0.0004523641,0.000228867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004605431,"about_ca_system_score_gemma":0.00006034183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005794591,"about_ca_topic_score_gemma":0.00001866169,"domain_scores_codex":[0.9988344,0.00009476686,0.0002580868,0.000392079,0.0002622628,0.0001584019],"domain_scores_gemma":[0.999216,0.0003095912,0.00005801015,0.0002881971,0.00005305381,0.00007518262],"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":[0.00001510396,0.0001435861,0.002104388,0.00005662875,0.00003936336,0.000007462132,0.001552077,0.002889794,0.05210512,0.2845518,0.000388101,0.6561465],"study_design_scores_gemma":[0.0001391489,0.00006429038,0.02159779,0.00002245608,0.000006851947,0.00002300498,0.00002057122,0.9707075,0.00170991,0.003277219,0.002316653,0.0001145783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1002975,0.00008816315,0.8932747,0.002550151,0.0002080962,0.000170595,9.78503e-7,0.0004744253,0.002935444],"genre_scores_gemma":[0.9420259,0.000003495539,0.05734766,0.00008799107,0.00006753659,0.00002253139,0.000008843053,0.00001209388,0.0004239258],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9678177,"threshold_uncertainty_score":0.4103448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009990317320447086,"score_gpt":0.3100381747683123,"score_spread":0.3000478574478652,"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."}}