{"id":"W4404783635","doi":"10.18653/v1/2024.findings-emnlp.83","title":"EchoSight: Advancing Visual-Language Models with Wiki Knowledge","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Visual language; Human–computer interaction; Natural language processing; Knowledge management; World Wide Web; Linguistics","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":[0.003068587,0.001652705,0.001010393,0.002422878,0.0005427724,0.00244464,0.003315199,0.001762507,0.004420634],"category_scores_gemma":[0.01346453,0.0005620209,0.001758991,0.001038848,0.0009740963,0.005862141,0.003338928,0.002608087,0.003070132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027907,"about_ca_system_score_gemma":0.001797606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01206893,"about_ca_topic_score_gemma":0.01597716,"domain_scores_codex":[0.9979387,0.0008235199,0.0001203892,0.0006133933,0.0003973079,0.0001066639],"domain_scores_gemma":[0.9932504,0.004445122,0.0002631589,0.001075843,0.0007492574,0.0002161767],"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":[0.0004505274,0.0007325913,0.003363813,0.001188136,0.0003557877,0.0003535229,0.0007968768,0.1200743,0.01188673,0.02533487,0.04245795,0.7930049],"study_design_scores_gemma":[0.00009469484,0.0001569056,0.000387216,0.00008673947,0.00007324334,0.00019006,0.0001849681,0.9349813,0.005647495,0.04230615,0.01583632,0.00005478751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01668368,0.00215308,0.9478341,0.0007805675,0.0002341557,0.0003385143,0.002111967,0.02517597,0.004687894],"genre_scores_gemma":[0.2957205,0.001306077,0.6807813,0.001428982,0.0002538059,0.0005879616,0.0113989,0.001203362,0.007319035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01206893,"threshold_uncertainty_score":0.02399737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007573520661421284,"score_gpt":0.3036279570150422,"score_spread":0.2960544363536209,"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."}}