{"id":"W4409561214","doi":"10.1109/ieeedata.2025.3562173","title":"Descriptor: Open-Domain Long-Form Context-Aware Question-Answering Dataset (DragonVerseQA)","year":2025,"lang":"en","type":"article","venue":"IEEE data descriptions.","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Open domain; Question answering; Computer science; Context (archaeology); Information retrieval; Domain (mathematical analysis); Closed-ended question; Artificial intelligence; Mathematics; Geography; Statistics","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":[0.001534035,0.002224923,0.000963596,0.002740552,0.001396283,0.00186119,0.002252205,0.003498199,0.02553018],"category_scores_gemma":[0.008327253,0.0003799568,0.00111719,0.002804485,0.0006975131,0.002474939,0.003264908,0.002124398,0.03170453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001390311,"about_ca_system_score_gemma":0.001800389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02211106,"about_ca_topic_score_gemma":0.04576639,"domain_scores_codex":[0.9982889,0.0004021543,0.000193049,0.0004922407,0.0004517068,0.0001718596],"domain_scores_gemma":[0.9969733,0.0008770967,0.0002244306,0.0006839153,0.0008565231,0.0003848161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002739825,0.0001552152,0.001570054,0.001505711,0.00004675791,0.0001765724,0.0004145412,0.001096879,0.00227964,0.001314639,0.9711102,0.02005582],"study_design_scores_gemma":[0.0003256128,0.000178512,0.008798587,0.0003925289,0.00004891629,0.000303409,0.001154293,0.008429121,0.00373518,0.003425255,0.9731026,0.0001058961],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.007024798,0.0009675467,0.002641851,0.0007568296,0.0003305084,0.0004695394,0.9743667,0.00710024,0.006342126],"genre_scores_gemma":[0.00640512,0.0001050408,0.004774791,0.0002357332,0.00004240874,0.0003985284,0.985827,0.0001787695,0.002032588],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02553018,"threshold_uncertainty_score":0.08540702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08150532100520148,"score_gpt":0.3335827149188032,"score_spread":0.2520773939136017,"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."}}