{"id":"W4389520321","doi":"10.18653/v1/2023.emnlp-main.735","title":"Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Situated; Natural park; Reading (process); Natural language; Natural language processing; Linguistics; Artificial intelligence; Philosophy; Ecology","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":[0.0002654155,0.0001635395,0.0001674615,0.000175666,0.0002360403,0.0001730864,0.0003140667,0.00005076826,0.000005826639],"category_scores_gemma":[0.0000371267,0.0001299089,0.00002496843,0.0005823907,0.00003693116,0.0004705037,0.0002453278,0.000242803,0.00003046133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007144401,"about_ca_system_score_gemma":0.00003162429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003522163,"about_ca_topic_score_gemma":0.0001438005,"domain_scores_codex":[0.9987625,0.000044685,0.0001359335,0.0004469518,0.000235257,0.0003746624],"domain_scores_gemma":[0.9993025,0.0002099813,0.00006119694,0.000285745,0.00003657348,0.0001040168],"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":[0.00005352487,0.00008025633,0.001540319,0.00004145389,0.0001323953,0.000101477,0.04919908,0.08574125,0.015161,0.842696,0.0003487685,0.004904465],"study_design_scores_gemma":[0.0006635759,0.00002410604,0.001534742,0.0000305944,0.000009363061,0.000009130003,0.002918931,0.9919784,0.0001664677,0.0024714,9.505965e-7,0.0001923205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3140481,0.00004300604,0.6821197,0.0004304385,0.00001620912,0.0001817188,0.000007603127,0.0007882437,0.002364968],"genre_scores_gemma":[0.9798061,0.000004108706,0.01910827,0.000215846,0.00001751963,0.00002516818,0.00003116366,0.00002127456,0.0007705177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9062372,"threshold_uncertainty_score":0.5297531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02192735941460207,"score_gpt":0.2936765613624693,"score_spread":0.2717492019478672,"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."}}