{"id":"W4412944217","doi":"10.18653/v1/2025.trl-1.14","title":"OrQA – Open Data Retrieval for Question Answering dataset generation","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Question answering; Information retrieval","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":[0.004352254,0.001973546,0.0008710693,0.003893287,0.001045904,0.002627586,0.003661652,0.001679819,0.01673088],"category_scores_gemma":[0.01843076,0.000599601,0.002229046,0.003028749,0.0008285468,0.003416566,0.004061831,0.002630475,0.01098701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001523543,"about_ca_system_score_gemma":0.002542564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0113698,"about_ca_topic_score_gemma":0.01649501,"domain_scores_codex":[0.9961116,0.001130417,0.0004208353,0.001159484,0.0009417947,0.0002359286],"domain_scores_gemma":[0.9940943,0.002311366,0.0002603182,0.00200009,0.001048362,0.0002854601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007760475,0.0006910809,0.006713685,0.003198321,0.0002952563,0.0004803267,0.00160917,0.02295367,0.01641484,0.0287641,0.7061117,0.2119918],"study_design_scores_gemma":[0.0006012425,0.0003443366,0.004475196,0.0003233636,0.000102598,0.0004477879,0.001184916,0.3316324,0.03143647,0.06915513,0.5601192,0.0001773707],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.02241898,0.001922908,0.3860208,0.002221471,0.0007604035,0.00301484,0.357056,0.2111836,0.01540098],"genre_scores_gemma":[0.04757511,0.0003508611,0.4406008,0.0007979874,0.00009882829,0.002308596,0.5005195,0.004125536,0.003622818],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01673088,"threshold_uncertainty_score":0.05597037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.162147800632898,"score_gpt":0.3991111183299413,"score_spread":0.2369633176970433,"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."}}