{"id":"W3213111926","doi":"10.48550/arxiv.2012.02339","title":"Understanding Guided Image Captioning Performance across Domains","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Closed captioning; Computer science; Readability; Transformer; Artificial intelligence; Natural language processing; Image (mathematics); Domain (mathematical analysis); Key (lock); Information retrieval; Programming language","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":[0.0001490649,0.0001292346,0.0001171106,0.00004705587,0.000509341,0.0001261317,0.0008852807,0.00004926784,0.00002439138],"category_scores_gemma":[0.00004280735,0.0001533177,0.0000620949,0.0008807579,0.00008808537,0.000740041,0.000379692,0.0002257799,0.0003055678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001868705,"about_ca_system_score_gemma":0.00003890651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008692856,"about_ca_topic_score_gemma":0.000007067195,"domain_scores_codex":[0.9989167,0.00005195788,0.0001193243,0.0005328147,0.00007245877,0.0003066709],"domain_scores_gemma":[0.9991808,0.00006497469,0.00009623962,0.0004261578,0.00005275371,0.0001790751],"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":[0.00001807373,0.00004445846,0.04886437,0.00003704091,0.00003837187,0.00008595796,0.003147081,0.3247344,0.00317086,0.6189135,0.0004686847,0.0004772406],"study_design_scores_gemma":[0.0004484979,0.00003464034,0.01157877,0.000009249927,0.000007085116,0.000005224833,0.0002143431,0.9848822,0.0002132435,0.002106761,0.0003046786,0.0001953497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4284883,0.000001856538,0.5683011,0.0006437115,0.00002886519,0.00006792488,0.000001509677,0.0002452769,0.002221476],"genre_scores_gemma":[0.9902726,0.00001030645,0.009199295,0.0003300843,0.00004197346,5.717566e-7,0.000002832993,0.00001075977,0.0001315512],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6601478,"threshold_uncertainty_score":0.6252114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2005041772895836,"score_gpt":0.2319281612384972,"score_spread":0.0314239839489136,"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."}}