{"id":"W4412030713","doi":"10.26599/tst.2024.9010216","title":"Learning Fine-Grained User Preference for Personalized Recommendation","year":2025,"lang":"en","type":"article","venue":"Tsinghua Science & Technology","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Preference; Computer science; Information retrieval; Human–computer interaction; Statistics; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001325866,0.0001797357,0.0002559516,0.001507334,0.0007262476,0.00029547,0.001910986,0.0001661452,0.00001196563],"category_scores_gemma":[0.0005126502,0.0001654618,0.00006448004,0.003624643,0.0005347658,0.0007123028,0.0005592887,0.0002632856,0.000009702594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001935119,"about_ca_system_score_gemma":0.000337062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002205532,"about_ca_topic_score_gemma":0.0000117569,"domain_scores_codex":[0.9980843,0.000046243,0.0003348821,0.0007720282,0.0001933196,0.0005692095],"domain_scores_gemma":[0.9987684,0.000118856,0.0001749833,0.0005853774,0.0002998924,0.00005245786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007009774,0.00004212229,0.001101644,0.00002343995,0.000009455078,7.962896e-7,0.0004441641,0.000006021739,0.01973536,0.7498035,0.002229343,0.2265972],"study_design_scores_gemma":[0.000880627,0.000471064,0.0003207375,0.000159832,0.00001226956,0.00002423625,0.0003791321,0.03495053,0.08524838,0.1050577,0.7720385,0.0004569892],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007281811,0.00007843921,0.9681864,0.01345488,0.0005312984,0.0005279831,0.000001232529,0.001539776,0.008398166],"genre_scores_gemma":[0.8666819,0.00001254244,0.127823,0.0002129341,0.00001930295,0.0002305687,0.000002883373,0.000008269245,0.005008589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8594001,"threshold_uncertainty_score":0.6747338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03092815123050258,"score_gpt":0.3062304388535652,"score_spread":0.2753022876230626,"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."}}