{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006788463,0.000177473,0.0001977591,0.0001597801,0.000135322,0.0003476273,0.002793172,0.00009236385,0.00001756295],"category_scores_gemma":[0.00038993,0.0001761091,0.00002151463,0.0007900518,0.00006420424,0.002106241,0.0008318814,0.0002063544,0.00002546691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001245658,"about_ca_system_score_gemma":0.0002012036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001364755,"about_ca_topic_score_gemma":0.0001460413,"domain_scores_codex":[0.997848,0.0001419972,0.000465941,0.000964326,0.0002658415,0.0003139288],"domain_scores_gemma":[0.9961437,0.00018761,0.0001459775,0.003431073,0.00005866837,0.00003299465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001234728,0.0006256395,0.008722381,0.0002082738,0.00003960864,0.00003703387,0.0002962364,0.000846789,0.1890135,0.4897824,0.2193365,0.09107931],"study_design_scores_gemma":[0.0002517222,0.00001280528,0.001407977,0.000117178,0.000003911302,0.000001684257,0.00001761689,0.8445541,0.1355944,0.001772279,0.01605436,0.0002120211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001257987,0.0000744175,0.9902102,0.003174116,0.0002017734,0.0002922772,0.0002620746,0.0004775266,0.004049583],"genre_scores_gemma":[0.6733354,0.00001604431,0.3225268,0.00205213,0.00002576562,0.00004481724,0.00192216,0.000007786771,0.00006913343],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8437073,"threshold_uncertainty_score":0.7181519,"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."}}