{"id":"W4405766356","doi":"10.48550/arxiv.2412.16694","title":"DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Context (archaeology); Open domain; Question answering; Domain (mathematical analysis); Computer science; Information retrieval; History; Mathematics; Archaeology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005002515,0.0004706376,0.0004436017,0.0003622521,0.0003386834,0.0007495511,0.004904113,0.0003557276,0.00009450823],"category_scores_gemma":[0.00004065593,0.0005535295,0.0002465766,0.0008578605,0.0001417813,0.000495701,0.01119184,0.001590167,0.001178534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005418169,"about_ca_system_score_gemma":0.0004289758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003813689,"about_ca_topic_score_gemma":0.0004834409,"domain_scores_codex":[0.9970592,0.0001869359,0.0003061135,0.00183851,0.0001434147,0.0004658801],"domain_scores_gemma":[0.9970488,0.000150144,0.0002689098,0.002077657,0.0001804892,0.0002740159],"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":[0.00001780391,0.0001124661,0.004972294,0.0002272012,0.000166975,0.0005438603,0.0008138181,0.08619419,0.00002463443,0.9023209,0.0006567686,0.003949111],"study_design_scores_gemma":[0.0005202135,0.00004203673,0.005471767,0.000358099,0.00007490974,0.00001969858,0.0001402545,0.7799385,0.00005399424,0.2093211,0.003254376,0.0008050906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2027698,0.00008973023,0.785351,0.001329179,0.0009867975,0.0008677298,0.00004239221,0.0009724893,0.007590829],"genre_scores_gemma":[0.9909739,0.00004417672,0.004693712,0.000186227,0.0001116335,0.00001269327,0.00004127395,0.00004811547,0.003888213],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7882041,"threshold_uncertainty_score":0.9996916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05469037283173667,"score_gpt":0.2341087230419267,"score_spread":0.17941835021019,"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."}}