{"id":"W4409183264","doi":"10.1007/978-3-031-88714-7_14","title":"The Impact of Incidental Multilingual Text on Cross-Lingual Transfer in Monolingual Retrieval","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Transfer (computing); Information retrieval; Speech recognition","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":[0.004017074,0.0005510143,0.0008354532,0.001164284,0.001081203,0.003638162,0.0007431474,0.0009606233,0.01001811],"category_scores_gemma":[0.05301557,0.0004632313,0.0004181129,0.001472189,0.00124045,0.008215994,0.003483419,0.001551501,0.004549302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007655188,"about_ca_system_score_gemma":0.001000973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002838645,"about_ca_topic_score_gemma":0.002516118,"domain_scores_codex":[0.9964585,0.001873471,0.000249821,0.0005222143,0.0005599892,0.0003361112],"domain_scores_gemma":[0.941327,0.05153335,0.0008092811,0.002549009,0.003004255,0.0007772081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007888349,0.001351614,0.02603441,0.001396596,0.000374033,0.001150628,0.004769458,0.01410261,0.1439874,0.008049108,0.01053792,0.7803578],"study_design_scores_gemma":[0.0006995565,0.004531024,0.2798054,0.0005264149,0.003015256,0.005267534,0.0140793,0.2840583,0.317684,0.06774653,0.02195861,0.0006281891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9327972,0.002612602,0.01747546,0.0006377086,0.0003388546,0.00008210031,0.0005105805,0.001117104,0.04442839],"genre_scores_gemma":[0.9913244,0.0006478552,0.00289805,0.000117848,0.0001883639,0.00003402569,0.0004831227,0.0003886808,0.003917678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01001811,"threshold_uncertainty_score":0.0335139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01936076133707259,"score_gpt":0.3130104121299656,"score_spread":0.293649650792893,"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."}}