{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001127422,0.0003108123,0.0003492529,0.0002834495,0.0005375287,0.001430633,0.008220559,0.0001369542,0.00007084672],"category_scores_gemma":[0.0001269892,0.0003290453,0.00005117259,0.0006437501,0.0001133942,0.005602262,0.003473412,0.0003702378,0.0002783852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002509932,"about_ca_system_score_gemma":0.0003892369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001382068,"about_ca_topic_score_gemma":0.001398343,"domain_scores_codex":[0.9970476,0.0001686754,0.0006028746,0.001265796,0.0003718997,0.0005431492],"domain_scores_gemma":[0.9944597,0.00008720661,0.0001408351,0.005001893,0.0001287069,0.0001816655],"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":[0.00003029384,0.0002526767,0.001906416,0.0001054668,0.0001361248,0.0001166533,0.0004406133,0.0002277628,0.00140065,0.1260061,0.8199221,0.04945514],"study_design_scores_gemma":[0.001939028,0.00005410821,0.001313535,0.0004980697,0.00008212213,0.00009640795,0.000557948,0.2256714,0.0008380432,0.01111187,0.7568857,0.0009517373],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00246705,0.0003082673,0.9861329,0.001871117,0.003746479,0.0005780814,0.003864935,0.0002984358,0.0007327771],"genre_scores_gemma":[0.7373711,0.0002164793,0.2340938,0.008685994,0.0004532244,0.0002426908,0.01623808,0.00006574675,0.002632862],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7520391,"threshold_uncertainty_score":0.9999161,"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."}}