{"id":"W4411549495","doi":"10.1145/3701716.3715311","title":"SynDL: A Large-Scale Synthetic Test Collection for Passage Retrieval","year":2025,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"Engineering and Physical Sciences Research Council; Universitas Brawijaya","keywords":"Computer science; Scale (ratio); Test (biology); Artificial intelligence; Information retrieval; Geology; Cartography; Geography","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":[0.00407954,0.001374373,0.001008519,0.003296156,0.001567862,0.001639075,0.002704468,0.001730426,0.007365456],"category_scores_gemma":[0.01807017,0.0004916063,0.001085392,0.003012952,0.00128822,0.00211243,0.00220797,0.001936206,0.007788407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001453578,"about_ca_system_score_gemma":0.001878017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01129091,"about_ca_topic_score_gemma":0.02038352,"domain_scores_codex":[0.9956512,0.002063768,0.0004678745,0.0005661777,0.001031122,0.0002199233],"domain_scores_gemma":[0.9832578,0.006389667,0.0007352838,0.003954795,0.004348043,0.001314366],"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":[0.002891805,0.005311732,0.03815646,0.004229195,0.0007031205,0.003038387,0.002797287,0.03371422,0.04964837,0.005542655,0.6151437,0.238823],"study_design_scores_gemma":[0.002369855,0.006677653,0.08518419,0.0003980067,0.0004778092,0.004713597,0.004542576,0.2236423,0.09559187,0.008879029,0.5667101,0.000813001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5600635,0.002485394,0.1092221,0.002279424,0.002153842,0.006081808,0.2524364,0.03639179,0.02888575],"genre_scores_gemma":[0.3206375,0.0004796821,0.09173924,0.0009646693,0.0002986546,0.003665152,0.5684138,0.001853881,0.01194736],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01129091,"threshold_uncertainty_score":0.02463996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007113296214746126,"score_gpt":0.2683040401957007,"score_spread":0.2611907439809546,"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."}}