{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004487468,0.001813179,0.002342687,0.002898043,0.001358214,0.001714454,0.003637709,0.003359212,0.009164668],"category_scores_gemma":[0.01112063,0.0009540825,0.001514781,0.002648868,0.001254568,0.002814495,0.002251045,0.002998259,0.007330564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007124066,"about_ca_system_score_gemma":0.001721146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003722501,"about_ca_topic_score_gemma":0.008352203,"domain_scores_codex":[0.9966938,0.0009819056,0.0002595008,0.0008287918,0.001028677,0.000207257],"domain_scores_gemma":[0.991764,0.003244099,0.0003252036,0.002044336,0.002298754,0.0003236238],"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":[0.0002846347,0.0003447203,0.001145562,0.0001809938,0.0001387876,0.00008220894,0.00007963755,0.04175915,0.01019125,0.005528332,0.02566864,0.9145961],"study_design_scores_gemma":[0.00005527697,0.0001410975,0.0003918545,0.00002342553,0.00003993863,0.0001603793,0.00002507679,0.9754683,0.009235983,0.009262608,0.005164475,0.00003155696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004782136,0.0003173109,0.9901304,0.0001622737,0.0001844112,0.0001051613,0.0002810292,0.003203569,0.0008338671],"genre_scores_gemma":[0.07639628,0.0002655588,0.9040539,0.0004704988,0.0005642361,0.000409561,0.002517174,0.0005340096,0.01478878],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009164668,"threshold_uncertainty_score":0.03065884,"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."}}