{"id":"W4415345326","doi":"10.48550/arxiv.2507.03922","title":"Dynamic Injection of Entity Knowledge into Dense Retrievers","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Code (set theory); Layer (electronics); Labrador Retriever; Set (abstract data type)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004828474,0.0002187309,0.0003924888,0.000408119,0.000106629,0.00007770697,0.001454386,0.0002487138,0.00001413826],"category_scores_gemma":[0.0002561093,0.0002292534,0.0002368036,0.0008810328,0.00007436846,0.0002178494,0.002505681,0.0004979714,0.00008572998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001733318,"about_ca_system_score_gemma":0.0003761848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000918533,"about_ca_topic_score_gemma":0.0005738333,"domain_scores_codex":[0.998317,0.0001389035,0.0004027393,0.0007387437,0.0002027977,0.0001998125],"domain_scores_gemma":[0.9978557,0.00009546831,0.0002817841,0.001473892,0.0002259295,0.00006718599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004450456,0.0007568304,0.8954905,0.001836848,0.001338615,0.00004400799,0.01197272,0.002751141,0.002265347,0.002448949,0.0100815,0.07096902],"study_design_scores_gemma":[0.0008820386,0.0002104748,0.3678392,0.001631437,0.0006633034,0.00001461895,0.0003474131,0.6094633,0.005987192,0.005303366,0.006059138,0.001598472],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7901207,0.0003688261,0.2066773,0.0001793928,0.001425781,0.00009380118,0.00002692088,0.0001567007,0.0009505037],"genre_scores_gemma":[0.9901085,0.0001189057,0.006056935,0.00003705762,0.00004046245,0.000008997898,0.00006640993,0.000006997197,0.0035557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6067122,"threshold_uncertainty_score":0.9348683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02382128318680259,"score_gpt":0.2891982362677081,"score_spread":0.2653769530809055,"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."}}