{"id":"W3176655069","doi":"10.1609/aaai.v35i5.16539","title":"PREMERE: Meta-Reweighting via Self-Ensembling for Point-of-Interest Recommendation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Weighting; Computer science; Benchmark (surveying); Recommender system; Scheme (mathematics); Meta learning (computer science); Artificial intelligence; Point of interest; Data mining; Point (geometry); Metamodeling; Machine learning; Metadata; Information retrieval; World Wide Web; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003233735,0.001489263,0.002430153,0.00148233,0.0006303269,0.001070524,0.003365445,0.001967486,0.001767961],"category_scores_gemma":[0.009016129,0.0008431311,0.001162983,0.001251665,0.000772515,0.002457586,0.001289238,0.002136471,0.001159644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000837374,"about_ca_system_score_gemma":0.0009321612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006994586,"about_ca_topic_score_gemma":0.01323129,"domain_scores_codex":[0.9988164,0.0004134884,0.00007570066,0.0003417438,0.000257751,0.00009487196],"domain_scores_gemma":[0.9972374,0.001331492,0.0001482649,0.0006219344,0.0005493275,0.0001115103],"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":[0.0004382361,0.0005491523,0.006456726,0.0002728895,0.0005582471,0.0001899137,0.0003336588,0.4160053,0.0115088,0.007277313,0.01243884,0.543971],"study_design_scores_gemma":[0.00002542879,0.00009143237,0.0003164225,0.00001399713,0.00003463838,0.00004724443,0.000009870769,0.9947777,0.001170997,0.002561625,0.0009334835,0.00001716723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03524279,0.001834191,0.9570782,0.0002751453,0.0002135531,0.0001330596,0.0002078622,0.003543758,0.001471456],"genre_scores_gemma":[0.508481,0.0006922054,0.4833772,0.0007697844,0.0002613582,0.0003615478,0.001234799,0.0004748745,0.004347118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006994586,"threshold_uncertainty_score":0.01710182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2633691770941545,"score_gpt":0.3375238780501245,"score_spread":0.07415470095596993,"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."}}