{"id":"W4416017175","doi":"10.1145/3746252.3760793","title":"Harnessing Light for Cold-Start Recommendations: Leveraging Epistemic Uncertainty to Enhance Performance in User-Item Interactions","year":2025,"lang":"","type":"article","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Uncertainty quantification; Robustness (evolution); Limiting; Focus (optics); Measure (data warehouse); Uncertainty reduction theory; Estimator; Uncertainty analysis","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001677835,0.000526659,0.0007282922,0.001149237,0.0008553722,0.001135696,0.001364809,0.000174671,0.00007411266],"category_scores_gemma":[0.0001664499,0.0005509099,0.0002128358,0.002215365,0.00003678879,0.002112051,0.0006505408,0.0005275586,0.0000394663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001225356,"about_ca_system_score_gemma":0.0006286422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005827296,"about_ca_topic_score_gemma":0.001487305,"domain_scores_codex":[0.9954615,0.0002819883,0.001722171,0.001366879,0.0002520178,0.0009155056],"domain_scores_gemma":[0.9969448,0.0008319597,0.0003937083,0.001200401,0.0004444868,0.0001846725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001290832,0.0007833727,0.01117554,0.001699668,0.000206721,0.000007782061,0.007543102,0.001218402,0.009240172,0.09619167,0.1138536,0.7579509],"study_design_scores_gemma":[0.0005056963,0.0001805972,0.0007663973,0.006192731,0.00002260379,0.00001126251,0.0006997295,0.2319888,0.0584076,0.0009761279,0.6995011,0.0007473237],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01366167,0.0003437536,0.904115,0.06600644,0.004521412,0.002512883,0.00001301126,0.0003348097,0.00849104],"genre_scores_gemma":[0.9038433,0.0002157362,0.06608719,0.002786108,0.0001353668,0.001081184,0.00001075737,0.00003128071,0.02580903],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8901817,"threshold_uncertainty_score":0.9999012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03068761742079017,"score_gpt":0.3295848590447216,"score_spread":0.2988972416239314,"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."}}