{"id":"W3100038904","doi":"10.18653/v1/2020.sustainlp-1.14","title":"A Little Bit Is Worse Than None: Ranking with Limited Training Data","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Training set; Ranking (information retrieval); Classifier (UML); Relevance (law); Labeled data; Artificial intelligence; Information retrieval; Machine learning; Domain (mathematical analysis); Simple (philosophy); Training (meteorology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0106621,0.001361874,0.002702259,0.001737393,0.001518555,0.00240002,0.002079878,0.002102904,0.002531043],"category_scores_gemma":[0.03786686,0.000512941,0.0009448575,0.001379859,0.00164647,0.006472863,0.001469344,0.003332056,0.002169793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001137652,"about_ca_system_score_gemma":0.001189177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006649637,"about_ca_topic_score_gemma":0.01260546,"domain_scores_codex":[0.993292,0.00430951,0.0002675659,0.001107328,0.0007204583,0.0003031379],"domain_scores_gemma":[0.9772906,0.01564278,0.0006689609,0.004433276,0.001342289,0.0006220617],"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":[0.003056266,0.00183373,0.02167059,0.001176461,0.0007130163,0.0003351274,0.0007550899,0.2177557,0.01188729,0.02657378,0.08271552,0.6315274],"study_design_scores_gemma":[0.0002986358,0.001778062,0.007041223,0.0001682219,0.0001734034,0.0005803488,0.0007537639,0.8814836,0.01016167,0.08585443,0.0115194,0.0001872322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5410271,0.009954116,0.4106563,0.009395684,0.001088993,0.0003502836,0.003445027,0.008144317,0.01593805],"genre_scores_gemma":[0.8603687,0.0007449573,0.1271468,0.001356427,0.0004155619,0.0001032288,0.004558937,0.0004875268,0.004817925],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0106621,"threshold_uncertainty_score":0.05638731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1694170731781986,"score_gpt":0.2713215509351272,"score_spread":0.1019044777569286,"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."}}