{"id":"W4385573653","doi":"10.18653/v1/2022.emnlp-main.696","title":"Dictionary-Assisted Supervised Contrastive Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; Charles Koch Foundation; Craig Newmark Philanthropies; John S. and James L. Knight Foundation; William and Flora Hewlett Foundation; Bill and Melinda Gates Foundation","keywords":"Computer science; Leverage (statistics); Natural language processing; Artificial intelligence; Entropy (arrow of time); Word (group theory); Cross entropy; Security token; Principle of maximum entropy; Linguistics","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":[0.000173457,0.00005441075,0.00006775451,0.00005199327,0.0003669604,0.00004237522,0.0003838108,0.00001102694,0.0005013456],"category_scores_gemma":[0.000018667,0.00005459814,0.0000338541,0.0002012471,0.000008371862,0.0001611493,0.0003800187,0.0001884577,0.000020542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006036817,"about_ca_system_score_gemma":0.00004247626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004842089,"about_ca_topic_score_gemma":0.000001980203,"domain_scores_codex":[0.999188,0.00009488441,0.0001073627,0.0002320016,0.0002329008,0.0001448565],"domain_scores_gemma":[0.9996616,0.00006645937,0.00002454621,0.000178776,0.00002759998,0.00004102919],"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":[0.00002508275,0.0002476028,0.01543113,0.000008936977,0.00007403916,0.0001110256,0.004431356,0.09924436,0.00616128,0.49411,0.002999846,0.3771553],"study_design_scores_gemma":[0.0003181118,0.00006578911,0.005530311,0.000001104155,0.000001841778,0.00003147438,0.0003073904,0.979274,0.0000926056,0.000859011,0.01341823,0.0001000891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02948941,0.00003692019,0.9521679,0.001258472,0.000324715,0.00006973776,5.912941e-7,0.0003492719,0.016303],"genre_scores_gemma":[0.9749726,8.664703e-7,0.02138529,0.000439609,0.00002869739,0.00002765961,0.00000241364,0.000003924983,0.003138936],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9454832,"threshold_uncertainty_score":0.5489382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02082510238209005,"score_gpt":0.2238134163181582,"score_spread":0.2029883139360682,"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."}}