{"id":"W2004109264","doi":"10.1109/tpami.2014.2306414","title":"A Hybrid Loss for Multiclass and Structured Prediction","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Northwest A and F University; University of Adelaide; University of Alberta","keywords":"Hinge loss; CRFS; Conditional random field; Artificial intelligence; Computer science; Machine learning; Support vector machine; Structured prediction; Margin (machine learning); Probabilistic logic; Consistency (knowledge bases); Multiclass classification; Parametric statistics; Pattern recognition (psychology); Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000266847,0.0001561607,0.0002142165,0.0003065499,0.0002481902,0.00016367,0.0001890031,0.00003955772,0.00001915291],"category_scores_gemma":[0.00001192673,0.0001381729,0.0001261308,0.0003052034,0.00005908774,0.000199425,0.000003730595,0.000150777,0.000003635613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001554395,"about_ca_system_score_gemma":0.000007740836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001389656,"about_ca_topic_score_gemma":0.0002591288,"domain_scores_codex":[0.9988781,0.0000752292,0.0002599413,0.0004433689,0.0001666945,0.000176681],"domain_scores_gemma":[0.999258,0.0002021021,0.00008356667,0.0002695453,0.00006536244,0.0001213664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001428444,0.00004065935,0.0005573583,0.00001633747,0.0001914642,0.000001157187,0.0003750905,0.02670923,0.0003308799,0.0004252987,0.000004440655,0.9713338],"study_design_scores_gemma":[0.0001970051,0.0001330267,0.002368843,0.000009177672,0.0001822005,0.00001238468,0.00002722969,0.9725739,0.02313559,0.0007547145,0.0004550957,0.0001507674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01091405,0.0000319341,0.9882617,0.000330718,0.000172543,0.0001393139,0.00003710758,0.00008373904,0.00002887552],"genre_scores_gemma":[0.991799,0.00008179828,0.007545679,0.0003795211,0.00002165416,0.00002527534,0.00000627305,0.000008417579,0.0001323838],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.980885,"threshold_uncertainty_score":0.5634528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0158254362966248,"score_gpt":0.2564596120722665,"score_spread":0.2406341757756417,"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."}}