{"id":"W4415065478","doi":"10.48550/arxiv.2504.16264","title":"CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents","year":2025,"lang":"en","type":"preprint","venue":"Conicet","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Benchmark (surveying); Key (lock); Machine translation; Document retrieval; Query expansion","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":[0.003411378,0.002631185,0.001467464,0.01634805,0.003110645,0.003914554,0.003104393,0.002033987,0.007515132],"category_scores_gemma":[0.01397716,0.0004690261,0.001986419,0.01545933,0.001410944,0.004112407,0.005490493,0.002070633,0.0114742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005168594,"about_ca_system_score_gemma":0.01022743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2009229,"about_ca_topic_score_gemma":0.3073825,"domain_scores_codex":[0.9943915,0.001084538,0.0006966705,0.001094918,0.002088748,0.0006435675],"domain_scores_gemma":[0.9932731,0.00112198,0.0005181515,0.001814212,0.002713029,0.0005594743],"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":[0.0007908683,0.0005610926,0.008609362,0.005148018,0.0004559182,0.0006409725,0.001097419,0.004255668,0.01615793,0.00652819,0.8390637,0.1166909],"study_design_scores_gemma":[0.0005455018,0.0003746906,0.02456033,0.0005749963,0.000265731,0.001197806,0.001921365,0.02982551,0.02266421,0.005947862,0.9117995,0.0003226305],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.07148388,0.00873671,0.02628102,0.002033491,0.0008325836,0.001798489,0.8096663,0.04250392,0.03666356],"genre_scores_gemma":[0.03466117,0.0009414678,0.03206436,0.0003469483,0.00009446141,0.0005473351,0.9244905,0.001008246,0.005845603],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2009229,"threshold_uncertainty_score":0.3995068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0255777633171702,"score_gpt":0.3318747589393084,"score_spread":0.3062969956221382,"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."}}