{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002692248,0.00004521767,0.00005502742,0.00007126749,0.00008416353,0.00007326718,0.0002626452,0.00002490109,0.00001226265],"category_scores_gemma":[0.00003820993,0.00004803131,0.00001608771,0.0002631631,0.000004006028,0.0003001335,0.0001030213,0.00003941541,0.00008409657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002311938,"about_ca_system_score_gemma":0.00002280471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006123634,"about_ca_topic_score_gemma":0.00004080802,"domain_scores_codex":[0.9993967,0.00001197148,0.00009969219,0.0002288126,0.0001050674,0.0001577804],"domain_scores_gemma":[0.9996256,0.00005344087,0.00001732363,0.0002404479,0.00002988622,0.00003331839],"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":[0.000007970035,0.00005834901,0.0006742398,0.00007851556,0.00003481867,0.000003025875,0.0005823608,0.02937691,0.01019821,0.6328418,0.06638393,0.2597598],"study_design_scores_gemma":[0.0001013608,0.00002123069,0.000289805,0.000006659846,0.000002014195,0.000001512098,0.00001024293,0.9806949,0.001848794,0.003822791,0.01312477,0.00007594882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004413584,0.000004343087,0.9933143,0.001180673,0.0002354109,0.0001152464,0.00001752165,0.0004710623,0.0002478475],"genre_scores_gemma":[0.3682006,0.00001190708,0.6275719,0.0005969083,0.0003550184,0.0001018938,0.0003858178,0.00001616102,0.002759706],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.951318,"threshold_uncertainty_score":0.195866,"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."}}