{"id":"W7108315141","doi":"10.1145/3767695.3769494","title":"FalseCoTQA: Adversarial Multi-Hop QA via Knowledge-Grounded False Chains of Thought","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Guelph","funders":"","keywords":"Adversarial system; Inference; Robustness (evolution); Construct (python library); Benchmark (surveying); Knowledge graph; Question answering; Language model","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":[0.005278556,0.001200277,0.0007968522,0.0008247292,0.001046918,0.002177409,0.003399818,0.002865327,0.005863204],"category_scores_gemma":[0.03360367,0.0004666636,0.001148777,0.0006114842,0.002372339,0.004795083,0.004489555,0.003830451,0.001717692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001553101,"about_ca_system_score_gemma":0.002001514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005364001,"about_ca_topic_score_gemma":0.007325039,"domain_scores_codex":[0.9942191,0.002951554,0.000231647,0.001003029,0.001269356,0.0003253812],"domain_scores_gemma":[0.9762211,0.01705888,0.0007952292,0.004250195,0.00123542,0.0004391673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00133164,0.0006302282,0.008014038,0.001479636,0.0004128164,0.0008221477,0.001644716,0.5866715,0.02047898,0.1454455,0.06727143,0.1657973],"study_design_scores_gemma":[0.0000722754,0.0001248031,0.0003017535,0.00004616555,0.00002865413,0.0001527009,0.0001111034,0.9219092,0.005046521,0.06446385,0.007711787,0.00003108757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09251154,0.00210098,0.8627113,0.004892309,0.0005388151,0.0005876268,0.003925903,0.01865611,0.01407532],"genre_scores_gemma":[0.7537865,0.0003983388,0.2317988,0.001928951,0.0001870583,0.0003550603,0.004460916,0.0008426065,0.006241729],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005863204,"threshold_uncertainty_score":0.02791601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03161552785915398,"score_gpt":0.296717215648937,"score_spread":0.265101687789783,"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."}}