{"id":"W4382282153","doi":"10.21203/rs.3.rs-3090614/v1","title":"Estimating serendipity in content-based recommender systems","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Serendipity; Recommender system; Relevance (law); Computer science; Surprise; Domain (mathematical analysis); Information retrieval; Collaborative filtering; World Wide Web; Measure (data warehouse); Data mining; Psychology; 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":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008127058,0.000383224,0.0007121592,0.001419612,0.0002448671,0.001319726,0.002767053,0.0005179055,0.00001105415],"category_scores_gemma":[0.000479272,0.0003582137,0.0001962476,0.001091892,0.0000653329,0.0002670739,0.003684295,0.002576915,0.0001271916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007710295,"about_ca_system_score_gemma":0.0006055612,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01094249,"about_ca_topic_score_gemma":0.0005661409,"domain_scores_codex":[0.9931875,0.002003973,0.0008881653,0.001327546,0.001465254,0.001127492],"domain_scores_gemma":[0.9956574,0.00105671,0.0002599576,0.002192346,0.0005932346,0.0002403835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001450946,0.002912844,0.2018372,0.06013597,0.000802353,0.002991318,0.009423432,0.05405358,0.0006620089,0.1536106,0.3459739,0.1674517],"study_design_scores_gemma":[0.0005944608,0.0001953103,0.007853842,0.0073614,0.000003432562,0.000007972999,0.0005447298,0.97158,0.0003684172,0.008181207,0.002592639,0.0007166376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01008442,0.0009407976,0.9664552,0.00734438,0.005247351,0.004477924,0.0001010531,0.002605801,0.002743127],"genre_scores_gemma":[0.9376292,0.000056779,0.05851836,0.00006358521,0.000401037,0.002295706,0.0001031219,0.00009532202,0.0008369031],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9275448,"threshold_uncertainty_score":0.999887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3741743428969209,"score_gpt":0.446292249745643,"score_spread":0.07211790684872205,"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."}}