{"id":"W4411270537","doi":"10.1109/tcomm.2025.3579703","title":"Mobile Traffic Prediction Using LLMs With Efficient In-Context Demonstration Selection","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); University of Ottawa","funders":"Mitacs","keywords":"Selection (genetic algorithm); Context (archaeology); Computer science; Mobile telephony; Mobile radio; Telecommunications; Artificial intelligence; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001109945,0.001267816,0.001005879,0.001122983,0.0004174331,0.0008694615,0.001485193,0.0007905798,0.00149391],"category_scores_gemma":[0.004614695,0.0004088596,0.0007909103,0.0006668284,0.000349338,0.001740799,0.001251766,0.001366754,0.0006323478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006221756,"about_ca_system_score_gemma":0.0009757822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006753839,"about_ca_topic_score_gemma":0.01207913,"domain_scores_codex":[0.9992199,0.0002816533,0.00004302868,0.0002328894,0.0001526256,0.00006990768],"domain_scores_gemma":[0.9985153,0.0008329662,0.0001256994,0.0001856054,0.0002486486,0.00009170845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005733859,0.0005935566,0.02488857,0.0001841029,0.0001543759,0.0003604402,0.000286441,0.5363345,0.01014481,0.004820153,0.00722789,0.4144318],"study_design_scores_gemma":[0.000008275827,0.00002698188,0.0004128269,0.000004859256,0.000008307741,0.00001457151,0.00001673524,0.9968651,0.001015578,0.001290435,0.0003299663,0.000006265668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1818658,0.0009123258,0.8024676,0.000777152,0.0001478425,0.0002229448,0.001379865,0.009174798,0.003051795],"genre_scores_gemma":[0.8523791,0.000162378,0.1443357,0.0001978277,0.00007860379,0.0001965512,0.001378629,0.0001285088,0.00114262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006753839,"threshold_uncertainty_score":0.01342905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01321321780818193,"score_gpt":0.2452422607304136,"score_spread":0.2320290429222316,"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."}}