{"id":"W3115487106","doi":"10.1145/3437963.3441751","title":"Unbiased Learning to Rank in Feeds Recommendation","year":2021,"lang":"en","type":"article","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"National Natural Science Foundation of China","keywords":"Learning to rank; Ranking (information retrieval); Computer science; Context (archaeology); Rank (graph theory); Set (abstract data type); Information retrieval; Recommender system; Mean reciprocal rank; Position (finance); Machine learning; Focus (optics); Product (mathematics); Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003563272,0.00006262992,0.000104921,0.0001136121,0.00004061446,0.0001350874,0.0002003044,0.00003363853,0.0001140905],"category_scores_gemma":[0.0000440192,0.00005986907,0.00002595226,0.0005505172,0.000001997816,0.0002378605,0.0001528792,0.00009816271,0.00004961072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004369874,"about_ca_system_score_gemma":0.00003458426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001768162,"about_ca_topic_score_gemma":0.0001908346,"domain_scores_codex":[0.9992371,0.0001247757,0.0001791022,0.0002359952,0.0000779781,0.0001450657],"domain_scores_gemma":[0.9996153,0.00005455814,0.00002759503,0.0002053531,0.00004749009,0.00004972493],"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":[0.000003324846,0.00009397785,0.00849684,0.00001651547,0.000009955756,0.00003683625,0.001668918,0.00007859451,0.004462356,0.04892806,0.02294536,0.9132593],"study_design_scores_gemma":[0.0009081822,0.0001939795,0.01583564,0.0001256226,0.000002213995,0.00005254742,0.0005856614,0.0435646,0.1023861,0.003965252,0.8317987,0.0005815048],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007948749,0.00001348942,0.930698,0.01120376,0.000329272,0.0001099932,1.408965e-7,0.0002991242,0.0493974],"genre_scores_gemma":[0.9128714,0.000009230683,0.08245988,0.001402517,0.00002813933,0.0000253017,0.000004983782,0.000005611953,0.003192966],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9126778,"threshold_uncertainty_score":0.244139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0232428136652147,"score_gpt":0.2752439355285293,"score_spread":0.2520011218633146,"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."}}