{"id":"W4382396965","doi":"10.1145/3606369","title":"Coarse-to-Fine Knowledge-Enhanced Multi-Interest Learning Framework for Multi-Behavior Recommendation","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Purchasing; Preference; Artificial intelligence; Machine learning","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008025672,0.0002493166,0.0003042877,0.0007878325,0.0005139184,0.0005248449,0.0007586097,0.000207203,0.00001139562],"category_scores_gemma":[0.0001566867,0.0002443353,0.0001476358,0.001056615,0.00001357938,0.001833327,0.00003595449,0.0003328408,0.0009666847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001715535,"about_ca_system_score_gemma":0.0000472209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005259097,"about_ca_topic_score_gemma":0.00003951384,"domain_scores_codex":[0.9981433,0.0001345403,0.0008585372,0.0003071901,0.0001825682,0.0003738946],"domain_scores_gemma":[0.9981347,0.0003506196,0.0003060336,0.0007051303,0.0003535648,0.0001499542],"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":[0.00003893637,0.0003053113,0.00006584321,0.0003555902,0.00008619852,7.927553e-7,0.01105886,0.005831367,0.0004879269,0.01137126,0.003413342,0.9669846],"study_design_scores_gemma":[0.002190816,0.0007144259,0.00063488,0.0007649552,0.0000346102,0.00002368055,0.003361192,0.7127901,0.01037627,0.0001982324,0.267969,0.0009418484],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007106952,0.000006431469,0.9917379,0.0006727999,0.002979853,0.001851781,0.00004457816,0.001758804,0.0002371688],"genre_scores_gemma":[0.7552413,0.00001732759,0.2401208,0.0001232484,0.00007342626,0.0033834,0.00009849043,0.00002784877,0.0009141216],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9660427,"threshold_uncertainty_score":0.9998112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.124798766701181,"score_gpt":0.3673304309339685,"score_spread":0.2425316642327875,"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."}}