{"id":"W4413756608","doi":"10.1145/3718958.3750526","title":"Towards User-level QoE: Large-scale Practice in Personalized Optimization of Adaptive Video Streaming","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Beijing National Research Center For Information Science And Technology","keywords":"Computer science; Scale (ratio); Video streaming; Quality of experience; Multimedia; Human–computer interaction; Real-time computing; Computer network; Quality of service","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":[0.002424743,0.0007477661,0.0006586598,0.0003507187,0.0004261229,0.0009517097,0.001107956,0.0007140117,0.0008109728],"category_scores_gemma":[0.008942421,0.0004384046,0.0002879979,0.000344279,0.0009931996,0.001414067,0.001234432,0.001464714,0.0001723402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000762351,"about_ca_system_score_gemma":0.0008865788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004132606,"about_ca_topic_score_gemma":0.004394289,"domain_scores_codex":[0.9989976,0.0004402402,0.00003268433,0.0002084832,0.0002640433,0.00005701427],"domain_scores_gemma":[0.9963707,0.002426013,0.0002922695,0.000424079,0.000365075,0.000121786],"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":[0.0001417504,0.0003486575,0.00612495,0.000112315,0.0000616293,0.00009765023,0.0002390384,0.8772032,0.01532816,0.00608964,0.001193798,0.09305914],"study_design_scores_gemma":[0.000008792828,0.00006674125,0.0007970548,0.000006733638,0.000004444614,0.0000137593,0.00002333495,0.9937244,0.00205886,0.002947894,0.000340526,0.00000745522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0823637,0.000302721,0.9138539,0.0004545447,0.00002392525,0.00008878517,0.00002676993,0.0007390567,0.002146592],"genre_scores_gemma":[0.8783637,0.0001551298,0.1205098,0.000159232,0.00002840203,0.00009859934,0.00004737888,0.00009411044,0.0005435261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004132606,"threshold_uncertainty_score":0.01282346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04799784066488448,"score_gpt":0.3513281742509259,"score_spread":0.3033303335860414,"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."}}