{"id":"W21569900","doi":"","title":"A self-training method for learning to rank with unlabeled data","year":2009,"lang":"en","type":"preprint","venue":"NPARC","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Ranking (information retrieval); Rank (graph theory); Artificial intelligence; Machine learning; Learning to rank; Extension (predicate logic); Scalability; Process (computing); Labeled data; Training set; Pattern recognition (psychology); Bipartite graph; Co-training; Data mining; Semi-supervised learning; Mathematics; Theoretical computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.00101651,0.0002519457,0.0003587664,0.0002310538,0.0001598951,0.0004322498,0.00402799,0.0002012056,0.0000099923],"category_scores_gemma":[0.0003012475,0.0002170822,0.00004995682,0.000339715,0.00001934358,0.0002727128,0.002449668,0.0005262744,0.00001682654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006163857,"about_ca_system_score_gemma":0.0002592222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003527895,"about_ca_topic_score_gemma":0.000005017574,"domain_scores_codex":[0.997858,0.00008967383,0.0002692784,0.001112438,0.0002994193,0.0003711882],"domain_scores_gemma":[0.997055,0.000249594,0.0002284739,0.002260386,0.0001227089,0.00008386001],"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":[0.00002377657,0.00004793149,0.00002570551,0.00008348645,0.00008107956,0.000004208659,0.001949088,0.0005033213,0.001250333,0.08957051,0.005182337,0.9012782],"study_design_scores_gemma":[0.001042298,0.0004896141,0.0001529103,0.0002218904,0.0000796742,0.00001335694,0.0004414445,0.5249144,0.002827574,0.2048635,0.264033,0.0009203213],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002284992,0.00004789882,0.9821171,0.01070895,0.0001420517,0.000806773,0.00001070757,0.001989778,0.003948259],"genre_scores_gemma":[0.02413282,0.00002312869,0.9747425,0.0003158605,0.00006316036,0.0002006584,0.00006155407,0.00001836477,0.0004419082],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9003579,"threshold_uncertainty_score":0.8852354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08011453989954655,"score_gpt":0.3464085744124789,"score_spread":0.2662940345129323,"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."}}