{"id":"W4388367992","doi":"10.1145/3616855.3635787","title":"Collaboration and Transition: Distilling Item Transitions into Multi-Query Self-Attention for Sequential Recommendation","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Collaborative filtering; Embedding; Leverage (statistics); Transition (genetics); Recommender system; Query optimization; Information retrieval; Data mining; Theoretical computer science; Machine learning; Artificial intelligence","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":[0.001547551,0.001157902,0.001322184,0.0009067921,0.0003957511,0.00073881,0.002452128,0.001236387,0.001805197],"category_scores_gemma":[0.005438308,0.0006408102,0.0009475956,0.001383896,0.0006159557,0.003215896,0.001682432,0.001760874,0.0007818099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009043653,"about_ca_system_score_gemma":0.0009123334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01088887,"about_ca_topic_score_gemma":0.01855285,"domain_scores_codex":[0.9989455,0.0002812037,0.00005878436,0.0004187842,0.0001896634,0.000105962],"domain_scores_gemma":[0.9976224,0.001173607,0.0001916256,0.0005657389,0.0003018819,0.0001447782],"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":[0.000950844,0.0006828514,0.01085733,0.0003387663,0.0003809582,0.0002126873,0.0007845967,0.2165072,0.02144645,0.009079302,0.008011566,0.7307475],"study_design_scores_gemma":[0.00002154053,0.0001253242,0.001200246,0.000007917382,0.0000326438,0.00005574647,0.00002122346,0.9916442,0.002566046,0.003482926,0.0008243935,0.00001768624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06797959,0.001456099,0.9260393,0.0003296421,0.00008724906,0.0001076421,0.0002621108,0.002707171,0.001031118],"genre_scores_gemma":[0.7995376,0.0005183748,0.1933528,0.0004458862,0.0001759154,0.0001715811,0.0007989609,0.0001907558,0.004808061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01088887,"threshold_uncertainty_score":0.02165097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03076690016593541,"score_gpt":0.3100484322918563,"score_spread":0.2792815321259209,"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."}}