{"id":"W4412387458","doi":"10.1145/3733567.3735571","title":"Mitigating Class Imbalance in Fact-Checking Datasets Through LLM-Based Synthetic Data Generation","year":2025,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Class (philosophy); Synthetic data; Data mining; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"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":[0.005319603,0.001035539,0.0008760142,0.002890738,0.0007901614,0.001591275,0.002274224,0.001452486,0.002503978],"category_scores_gemma":[0.02629931,0.0004428709,0.0008973351,0.002026959,0.0007414727,0.002045566,0.002383459,0.002334681,0.001156022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008997635,"about_ca_system_score_gemma":0.001927059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002849933,"about_ca_topic_score_gemma":0.006027265,"domain_scores_codex":[0.9970777,0.0008790749,0.0002126184,0.000688077,0.0009295295,0.0002130105],"domain_scores_gemma":[0.9812087,0.009489041,0.001100255,0.004542402,0.003212698,0.0004470484],"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":[0.002506837,0.001566465,0.05697732,0.0007470498,0.0003209717,0.001114903,0.0008456417,0.2276714,0.03145491,0.01400509,0.09018252,0.5726069],"study_design_scores_gemma":[0.00008054987,0.000104508,0.002390177,0.00003731142,0.00004029712,0.0001806719,0.0001379147,0.9732864,0.009509923,0.007372428,0.006842542,0.00001717359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2952535,0.0009141863,0.659126,0.00283625,0.001160051,0.0008670787,0.01325581,0.02098673,0.005600374],"genre_scores_gemma":[0.6033243,0.0001464047,0.3700371,0.0006365543,0.0001748521,0.0004331381,0.02270903,0.0006641065,0.001874532],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005319603,"threshold_uncertainty_score":0.02813315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07088414799895912,"score_gpt":0.3394362157914215,"score_spread":0.2685520677924624,"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."}}