{"id":"W7106813719","doi":"10.48448/vcb3-yg37","title":"Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scalability; Task (project management); Labrador Retriever; Collaborative editing; Recall; Precision and recall","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001650833,0.001680432,0.001329271,0.0007670555,0.0006104105,0.002146216,0.003362272,0.002039906,0.01633916],"category_scores_gemma":[0.01038013,0.0006001464,0.000970723,0.0005581644,0.0008677916,0.003982001,0.003489892,0.00254491,0.00806764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008956971,"about_ca_system_score_gemma":0.00188774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004246966,"about_ca_topic_score_gemma":0.008876819,"domain_scores_codex":[0.9983808,0.0003712987,0.0001034953,0.0005458034,0.0004196626,0.0001789676],"domain_scores_gemma":[0.9968587,0.001362217,0.0001856405,0.001071922,0.0003193566,0.0002022412],"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":[0.0009342282,0.0007096022,0.001896482,0.000805182,0.0001380858,0.0005719265,0.0004989146,0.1247231,0.0319257,0.02606554,0.06995609,0.7417752],"study_design_scores_gemma":[0.0000823231,0.0000994531,0.0001932912,0.00002557541,0.00003262078,0.0001549545,0.00007337186,0.9493305,0.01547862,0.02071103,0.01377392,0.00004439182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02573095,0.001016751,0.8266056,0.000847264,0.0003136921,0.0002212204,0.001169974,0.1341416,0.009952848],"genre_scores_gemma":[0.437892,0.0004825603,0.5286772,0.001041265,0.0001833374,0.0003150748,0.002723333,0.008942198,0.01974317],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01633916,"threshold_uncertainty_score":0.0546599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02321768382216558,"score_gpt":0.3453363469885539,"score_spread":0.3221186631663883,"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."}}