{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002722518,0.00184039,0.001035795,0.005463701,0.001539536,0.003048003,0.002784572,0.002821083,0.008375232],"category_scores_gemma":[0.01595555,0.0005384997,0.001371918,0.003008094,0.000862047,0.005657969,0.005694775,0.002893389,0.008257809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001532116,"about_ca_system_score_gemma":0.002053053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01008313,"about_ca_topic_score_gemma":0.02575349,"domain_scores_codex":[0.9958567,0.001535391,0.0003808737,0.001245008,0.0007468996,0.0002351028],"domain_scores_gemma":[0.9928565,0.003195872,0.0004689823,0.001712778,0.001213075,0.0005528231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001283194,0.001134871,0.01286126,0.009017779,0.0004066097,0.0009290332,0.007282797,0.01390712,0.02845239,0.02625649,0.6182753,0.2801932],"study_design_scores_gemma":[0.0002189518,0.0003598632,0.01199354,0.0005981526,0.0001160994,0.0006184432,0.00389553,0.07206289,0.01188776,0.02326828,0.8747893,0.0001912449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.07185718,0.01104697,0.2244534,0.005603889,0.001515591,0.003766316,0.560334,0.0859258,0.03549683],"genre_scores_gemma":[0.09211794,0.001030521,0.2414854,0.001836575,0.0003641264,0.002824645,0.6508088,0.001333524,0.008198582],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01008313,"threshold_uncertainty_score":0.02801794,"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."}}