{"id":"W4403582548","doi":"10.1145/3627673.3679939","title":"How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrieval","year":2024,"lang":"en","type":"article","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Leverage (statistics); Computer science; Information retrieval; World Wide Web; Knowledge management; Artificial intelligence","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004161942,0.0001208962,0.0001227931,0.0002020908,0.0001004402,0.001083491,0.0003155368,0.00006537536,0.00004454603],"category_scores_gemma":[0.00004811365,0.0001001122,0.0001131956,0.0003038605,0.00001642158,0.001757953,0.00009940807,0.00007486284,0.00009836398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001124985,"about_ca_system_score_gemma":0.000161964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001061418,"about_ca_topic_score_gemma":0.000003718969,"domain_scores_codex":[0.9991415,0.0000267266,0.0001759611,0.0002311305,0.0002304276,0.0001942108],"domain_scores_gemma":[0.9994172,0.0001557223,0.00002790801,0.0001409304,0.0001632158,0.00009499142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001444689,0.0000132843,0.00001096281,0.0001229674,0.00003160401,0.000001139762,0.006220595,3.673939e-7,0.0002211442,0.7955189,0.1634323,0.03441228],"study_design_scores_gemma":[0.0002698155,0.0001362966,0.00006772276,0.00004376163,0.000003993168,0.0000226729,0.0004111193,0.09791572,0.001429497,0.001427919,0.8980857,0.0001857653],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000416482,0.0001429421,0.9796743,0.01084606,0.000643052,0.000469066,0.0000217487,0.0005423889,0.007243951],"genre_scores_gemma":[0.9126418,0.000004469215,0.06686984,0.0009812899,0.0003039983,0.00009214717,0.00003379923,0.00001011165,0.01906261],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9128045,"threshold_uncertainty_score":0.9999535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03115555359617272,"score_gpt":0.2796713288968972,"score_spread":0.2485157753007244,"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."}}