{"id":"W3035931148","doi":"10.48550/arxiv.2006.10923","title":"Hyperparameter Analysis for Image Captioning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Closed captioning; Hyperparameter; Computer science; Transformer; Baseline (sea); Encoder; Artificial intelligence; Image (mathematics); Sensitivity (control systems); Preprocessor; Machine learning; Speech recognition; Pattern recognition (psychology); Natural language processing; Engineering","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":[0.005320746,0.001911039,0.0009325316,0.002019023,0.0005985969,0.001985485,0.00137271,0.001976563,0.006455848],"category_scores_gemma":[0.04991529,0.0006317911,0.001283305,0.001287427,0.001018879,0.003053768,0.001912038,0.002690295,0.001715597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001845595,"about_ca_system_score_gemma":0.0005379044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002839025,"about_ca_topic_score_gemma":0.001943523,"domain_scores_codex":[0.9954934,0.00212723,0.0002216604,0.0007668228,0.001124591,0.0002662564],"domain_scores_gemma":[0.9829623,0.01244641,0.0006852963,0.002381193,0.00139146,0.0001334076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007429285,0.0001712606,0.00421969,0.001143437,0.0005839842,0.0004534742,0.0002567503,0.6358668,0.0483781,0.009944201,0.01146783,0.2867716],"study_design_scores_gemma":[0.00002199124,0.0001773183,0.003533392,0.0001347644,0.0001170084,0.0005124919,0.0000856554,0.9450209,0.0275683,0.01639758,0.00635834,0.00007230132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1330563,0.01119082,0.8260044,0.001961679,0.0005963835,0.0005309307,0.002138183,0.008462936,0.01605825],"genre_scores_gemma":[0.9015853,0.00215223,0.08596893,0.0009427543,0.0002877818,0.0003732906,0.003091465,0.001873341,0.003724858],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006455848,"threshold_uncertainty_score":0.02813911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09702672678732742,"score_gpt":0.2241226351722768,"score_spread":0.1270959083849494,"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."}}