{"id":"W1575833922","doi":"10.48550/arxiv.1505.02074","title":"Exploring Models and Data for Image Question Answering","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":390,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Image (mathematics); Question answering; Suite; Artificial intelligence; Segmentation; Image segmentation; Simple (philosophy); Object (grammar); Baseline (sea); Information retrieval; Pattern recognition (psychology); Machine learning; Data mining","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":[0.0002963753,0.00007613286,0.0000737406,0.00007188523,0.0001040817,0.00006881995,0.0007982947,0.00002187119,4.398487e-7],"category_scores_gemma":[0.00006297644,0.00008982278,0.00001393985,0.0002282285,0.00003062182,0.002354234,0.0005721406,0.00007490896,0.000010664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003903787,"about_ca_system_score_gemma":0.00003041515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003135443,"about_ca_topic_score_gemma":0.00001407675,"domain_scores_codex":[0.9992381,0.00003302083,0.00006261292,0.0004899461,0.00003554271,0.000140823],"domain_scores_gemma":[0.9988728,0.00006626145,0.00004293379,0.0008240041,0.00007390001,0.0001201522],"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":[0.000015211,0.00003762898,0.00145771,0.0000176767,0.00001373074,0.00001318548,0.0004711199,0.2112447,0.0003221234,0.7798377,0.0001104361,0.006458814],"study_design_scores_gemma":[0.0002956872,0.00002131546,0.0008913057,0.000007493421,0.000007883396,0.000002769667,0.00005179897,0.9743403,0.00004271058,0.02384051,0.0003950604,0.0001031576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.245121,0.00000989836,0.754043,0.0001578185,0.00004465641,0.000106081,0.000005056726,0.0001459853,0.0003665392],"genre_scores_gemma":[0.9342812,0.00001741808,0.0655719,0.00002017975,0.00002660055,0.000001909434,0.00001071554,0.000006677922,0.00006334646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7630956,"threshold_uncertainty_score":0.3662867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4143372677061843,"score_gpt":0.2670283867265147,"score_spread":0.1473088809796696,"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."}}