{"id":"W4321175651","doi":"10.48550/arxiv.2302.07738","title":"Alloprof: a new French question-answer education dataset and its use in an information retrieval case study","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Question answering; Relevance (law); Computer science; Context (archaeology); Spelling; Information retrieval; Task (project management); Variety (cybernetics); Comprehension; Baseline (sea); Natural language processing; Artificial intelligence; World Wide Web; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0020659,0.002083448,0.0009382765,0.006387857,0.001822607,0.001732715,0.002410339,0.00336756,0.008095657],"category_scores_gemma":[0.008170144,0.0003031947,0.001468045,0.00453448,0.0006449202,0.001820024,0.001824711,0.001744809,0.006829577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004073305,"about_ca_system_score_gemma":0.002675237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.176844,"about_ca_topic_score_gemma":0.2607608,"domain_scores_codex":[0.9972278,0.000737889,0.0003170253,0.0007061069,0.0007054123,0.0003056386],"domain_scores_gemma":[0.9952153,0.001239398,0.0002192663,0.0008167183,0.002069465,0.0004398916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009002752,0.00184211,0.02025941,0.003435929,0.0002200055,0.001470634,0.001527055,0.006158146,0.007156554,0.003150774,0.8444223,0.1094568],"study_design_scores_gemma":[0.0005430167,0.0005847829,0.0705695,0.0006217262,0.0001303515,0.001562736,0.002446229,0.03126617,0.00978073,0.001923705,0.8803284,0.0002426773],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1328326,0.003464707,0.01154808,0.002391126,0.000422907,0.001757243,0.8168277,0.01481112,0.01594452],"genre_scores_gemma":[0.0419488,0.0003245691,0.02067531,0.0004304086,0.00008315568,0.0009524868,0.9311487,0.0002832973,0.004153257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.176844,"threshold_uncertainty_score":0.3516294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1564633524956761,"score_gpt":0.2549670573157696,"score_spread":0.09850370482009357,"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."}}