{"id":"W4366598314","doi":"10.1145/3591109","title":"A Framework and Toolkit for Testing the Correctness of Recommendation Algorithms","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Recommender Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Test suite; Correctness; Unit testing; Python (programming language); Algorithm; Recommender system; Suite; White-box testing; Implementation; Surprise; Regression testing; Code coverage; Integration testing; Test case; Software engineering; Software; Programming language; Machine learning; Software system; Software construction","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":[0.00139476,0.0002207525,0.0003430132,0.0002678496,0.0004642026,0.0002286997,0.0008521737,0.0001486686,0.000005698324],"category_scores_gemma":[0.0001607739,0.0001670127,0.0001083283,0.001043169,0.00003786248,0.0003288381,0.00004442964,0.0002604044,0.000007694377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005276499,"about_ca_system_score_gemma":0.00004071408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002157387,"about_ca_topic_score_gemma":0.00001062523,"domain_scores_codex":[0.9981928,0.0002319572,0.0005794253,0.0004602483,0.0001977141,0.0003378224],"domain_scores_gemma":[0.9951854,0.003364077,0.0002654109,0.0009390975,0.0001720325,0.00007397591],"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":[0.00001501179,0.0001107317,0.0002084147,0.0002559251,0.0001528195,0.00000106067,0.001717247,0.0003460558,0.0001102997,0.00729173,0.009190926,0.9805998],"study_design_scores_gemma":[0.002094925,0.001768638,0.001897107,0.001602092,0.0001390387,0.0002725521,0.006687361,0.7357277,0.004857661,0.04858931,0.1947804,0.001583188],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004971026,0.0000616433,0.9874656,0.00738224,0.002593462,0.001055229,0.00003894775,0.0005633041,0.0003425298],"genre_scores_gemma":[0.880877,0.0001324982,0.1165064,0.0003950536,0.000167216,0.001496433,0.00001620395,0.0000512458,0.000357951],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9790166,"threshold_uncertainty_score":0.681058,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1268538343049634,"score_gpt":0.3261905453913853,"score_spread":0.1993367110864219,"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."}}