{"id":"W6958462973","doi":"10.60692/bzw3c-ctp50","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","year":2018,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Question answering; Natural language; Natural (archaeology); Empirical research","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":[0.00195489,0.002911137,0.001757451,0.004362098,0.001866013,0.001858077,0.00438606,0.004959098,0.01473633],"category_scores_gemma":[0.0106696,0.0006748308,0.001997516,0.003342035,0.0007125075,0.003678318,0.003992102,0.002338303,0.01210609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001849086,"about_ca_system_score_gemma":0.002356967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03201551,"about_ca_topic_score_gemma":0.06417438,"domain_scores_codex":[0.9977349,0.0006412258,0.0002909618,0.0006221236,0.0005030457,0.0002078351],"domain_scores_gemma":[0.9955974,0.001926542,0.0002419213,0.0009414904,0.0008599926,0.0004326822],"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":[0.0006267013,0.0004708035,0.005840034,0.002205541,0.0002624864,0.0004989635,0.0004777852,0.002763537,0.003390818,0.002308218,0.9414163,0.03973884],"study_design_scores_gemma":[0.001680586,0.0006213274,0.03694228,0.0007825656,0.0004335794,0.00135964,0.002565175,0.07901051,0.008418934,0.01839904,0.8494439,0.000342464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.02726297,0.003687947,0.009488702,0.001967398,0.000407583,0.0007503754,0.9372596,0.01299933,0.006176222],"genre_scores_gemma":[0.02011235,0.0002553142,0.01151096,0.0003507395,0.00006263593,0.0004663982,0.9647473,0.0002023187,0.002292062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03201551,"threshold_uncertainty_score":0.0636583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06763872202132244,"score_gpt":0.2565929837434248,"score_spread":0.1889542617221024,"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."}}