{"id":"W4400526284","doi":"10.1145/3626772.3657942","title":"Synthetic Test Collections for Retrieval Evaluation","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"Engineering and Physical Sciences Research Council; Universitas Brawijaya","keywords":"Computer science; Test (biology); Information retrieval; Geology","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":[0.0004617716,0.00003847978,0.00003720075,0.00008102096,0.0001029464,0.0002424799,0.0001559781,0.00002296878,0.0000608098],"category_scores_gemma":[0.0002967837,0.00003329037,0.00003316348,0.000414708,0.000005784298,0.0001609986,0.00003209928,0.000033965,0.00003726158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000646211,"about_ca_system_score_gemma":0.0001377469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004688016,"about_ca_topic_score_gemma":0.000005547121,"domain_scores_codex":[0.9994234,0.00001302962,0.00008975641,0.0002187572,0.0001634446,0.00009160294],"domain_scores_gemma":[0.999365,0.0003119007,0.000007219102,0.0002112876,0.00008160769,0.00002297276],"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":[0.000005449368,0.0001036956,0.00003826432,0.0001105297,0.00004334472,0.000003867215,0.001148538,0.00572993,0.007140397,0.6189812,0.05216755,0.3145273],"study_design_scores_gemma":[0.00005599054,0.00002988376,0.000008733324,0.00001196508,0.000008320672,0.000006567645,0.000006759129,0.9644202,0.001652084,0.0218002,0.01195507,0.00004419777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005732982,0.0001541215,0.9813054,0.002002358,0.000782566,0.000263824,0.000001266746,0.0002734262,0.01464372],"genre_scores_gemma":[0.8639052,0.000003866153,0.1173974,0.000121265,0.0001640095,0.00005980041,0.000001188344,0.000007061862,0.01834019],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9586903,"threshold_uncertainty_score":0.233824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0516350703716649,"score_gpt":0.3152633073841311,"score_spread":0.2636282370124662,"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."}}