{"id":"W2189749715","doi":"","title":"Embedding inference for structured multilabel prediction","year":2015,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Inference; Computer science; Structured prediction; Scalability; Embedding; Machine learning; Margin (machine learning); Representation (politics); Artificial intelligence; Bottleneck; Key (lock); Theoretical computer science","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":[0.00214861,0.001128076,0.001231514,0.0008571808,0.0006075025,0.001179465,0.001936431,0.001283231,0.00422256],"category_scores_gemma":[0.01402051,0.0006367074,0.0008266644,0.001036912,0.001057198,0.003859664,0.002134207,0.003104691,0.001335698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009440248,"about_ca_system_score_gemma":0.0009794146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002410541,"about_ca_topic_score_gemma":0.005600625,"domain_scores_codex":[0.99841,0.0006588838,0.00006700948,0.0004849038,0.0002636658,0.0001156057],"domain_scores_gemma":[0.9936651,0.004162259,0.0003628836,0.001106035,0.0005468098,0.000157078],"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":[0.0003137404,0.0002269303,0.002240356,0.0002461713,0.0001295072,0.0001764337,0.0002811796,0.6887457,0.004543927,0.0594897,0.009608219,0.2339982],"study_design_scores_gemma":[0.000007820779,0.00001350496,0.0000907307,0.000007041961,0.000005798363,0.000008049914,0.000009199228,0.9508408,0.0006490156,0.04803531,0.0003268976,0.000005806629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01010621,0.0001393701,0.987566,0.0002174163,0.00002802218,0.00002810611,0.0001828922,0.001025776,0.0007060915],"genre_scores_gemma":[0.670287,0.000228862,0.3225003,0.000401565,0.0001776015,0.0002099598,0.002352024,0.0004724694,0.003370249],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00422256,"threshold_uncertainty_score":0.01412588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05642435896109493,"score_gpt":0.3103287019881856,"score_spread":0.2539043430270906,"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."}}