{"id":"W2963299217","doi":"","title":"A Neural Compositional Paradigm for Image Captioning","year":2018,"lang":"en","type":"article","venue":"The HKU Scholars Hub (University of Hong Kong)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Closed captioning; Computer science; Semantics (computer science); Generalization; Natural language processing; Artificial intelligence; Syntax; Representation (politics); Image (mathematics); Programming language; Mathematics","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":[0.0003445662,0.00009104906,0.0001139149,0.00008456656,0.001033472,0.00009680158,0.001212353,0.00003965409,0.0000439338],"category_scores_gemma":[0.00003015173,0.00009249859,0.00009521424,0.0002738655,0.0003019018,0.0007188755,0.0002656123,0.0002114204,0.00009930932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003540327,"about_ca_system_score_gemma":0.00003967282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003155461,"about_ca_topic_score_gemma":0.00002911687,"domain_scores_codex":[0.9991811,0.00009086001,0.00008789243,0.0002561096,0.0001925828,0.0001914357],"domain_scores_gemma":[0.9990137,0.0001612017,0.0001265472,0.0004764594,0.0001577064,0.00006442293],"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":[0.0003004192,0.0005614875,0.017178,0.00009183645,0.0003236448,0.00003050836,0.01533623,0.004582933,0.1244782,0.7916766,0.009643005,0.03579711],"study_design_scores_gemma":[0.001288448,0.0002328572,0.3882141,0.00003624249,0.00005134158,0.00005210001,0.0003140042,0.5917244,0.0007911708,0.01436503,0.002607813,0.0003225382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5770375,0.0000149788,0.4160992,0.005820717,0.00007117462,0.0001905625,0.00001183349,0.00009707839,0.0006569696],"genre_scores_gemma":[0.8925865,0.000001197036,0.1070685,0.0001266089,0.00005587523,0.000001094575,0.000009545963,0.00000603643,0.0001445715],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7773116,"threshold_uncertainty_score":0.7948737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01437617044879723,"score_gpt":0.2468396403155849,"score_spread":0.2324634698667877,"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."}}