{"id":"W4384827425","doi":"10.1145/3539618.3591804","title":"One Stop Shop for Question-Answering Dataset Selection","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Question answering; Visualization; Point (geometry); Selection (genetic algorithm); Information retrieval; Field (mathematics); Domain (mathematical analysis); World Wide Web; Data science; Artificial intelligence","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":[0.01409315,0.002333558,0.002108495,0.007886069,0.0017014,0.005783731,0.002656999,0.002452062,0.0382294],"category_scores_gemma":[0.05338353,0.001228059,0.002202918,0.006341208,0.0007223919,0.007026525,0.008776367,0.002738228,0.02764514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001134313,"about_ca_system_score_gemma":0.0023567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002988681,"about_ca_topic_score_gemma":0.006782582,"domain_scores_codex":[0.9906096,0.003093441,0.001208052,0.002357627,0.002190191,0.0005410259],"domain_scores_gemma":[0.9671414,0.0151167,0.001141513,0.01040616,0.004522666,0.001671599],"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":[0.0008077122,0.0001931403,0.005914826,0.001440962,0.0002134997,0.0003542366,0.0009564489,0.0008227255,0.00975718,0.008694173,0.7129406,0.2579044],"study_design_scores_gemma":[0.0006036567,0.0003552829,0.01086019,0.0004923206,0.0001237764,0.001100724,0.001732164,0.05959316,0.02355165,0.04046356,0.8608342,0.0002893902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.01284728,0.002082612,0.3498353,0.003479758,0.001303344,0.001792388,0.149927,0.4652908,0.01344151],"genre_scores_gemma":[0.07087901,0.0005222812,0.6236321,0.002156754,0.0004481128,0.003380416,0.2541925,0.03686121,0.007927574],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0382294,"threshold_uncertainty_score":0.1278901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06248357797921539,"score_gpt":0.3178259029697293,"score_spread":0.2553423249905139,"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."}}