{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001828413,0.0001146946,0.0001441722,0.00004229708,0.00007531925,0.0001966345,0.001630508,0.00003413517,0.0000724095],"category_scores_gemma":[0.00004039932,0.00008956512,0.00002118512,0.0004655604,0.00001749519,0.0006494708,0.0007178474,0.0001403778,0.00005620914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008296576,"about_ca_system_score_gemma":0.00008074316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006064475,"about_ca_topic_score_gemma":0.00002729167,"domain_scores_codex":[0.9986885,0.0000255517,0.0001618867,0.0005999184,0.0002681719,0.0002560316],"domain_scores_gemma":[0.9986902,0.00005557883,0.00004622658,0.001047438,0.00003058249,0.0001299108],"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":[0.0001066717,0.0001506322,0.009597825,0.000147809,0.0002927041,0.0003976277,0.1541997,0.00372966,0.002595203,0.05379312,0.01365555,0.7613335],"study_design_scores_gemma":[0.0003863591,0.00004607373,0.0001705753,0.00003351418,0.0000068931,0.00001156556,0.0002632201,0.9919968,0.0002807434,0.0001543199,0.006477134,0.0001728645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01972807,0.00004599446,0.9638638,0.01126814,0.00007061449,0.00009816832,0.000003080829,0.000326733,0.004595318],"genre_scores_gemma":[0.7174842,0.000002919697,0.2778507,0.004333171,0.0001230519,0.000002462638,0.000005070637,0.000009362124,0.0001889741],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9882671,"threshold_uncertainty_score":0.365236,"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."}}