{"id":"W4392869771","doi":"10.1007/978-3-031-56060-6_18","title":"LaQuE: Enabling Entity Search at Scale","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"Computer science; Scale (ratio); Information retrieval; Data science; Cartography","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007991929,0.000374843,0.0005136773,0.001427645,0.0003807615,0.001962829,0.003935627,0.0002370237,0.000820884],"category_scores_gemma":[0.0004443103,0.0002861687,0.0001909316,0.001129898,0.001100461,0.0005747884,0.005956199,0.0008058933,0.003118415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004327182,"about_ca_system_score_gemma":0.0002649306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008493935,"about_ca_topic_score_gemma":0.001179732,"domain_scores_codex":[0.9925898,0.00007135806,0.0007804162,0.002110149,0.003808564,0.0006396662],"domain_scores_gemma":[0.9961747,0.001310468,0.0001705723,0.00184805,0.0002957363,0.0002004843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001564214,0.00003495247,0.0001209865,0.00009554261,0.00001957826,0.0002012183,0.001516777,0.01174295,0.0001171061,0.04329756,0.002439468,0.9403982],"study_design_scores_gemma":[0.0001467082,0.00008186293,0.0001047976,0.0003474083,0.00001684987,0.0000259656,0.000002627414,0.0475149,0.001108689,0.6809699,0.2690881,0.0005922269],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0005536362,0.0007515449,0.9481142,0.002405854,0.003653604,0.0004011595,0.00006892048,0.0001125625,0.04393854],"genre_scores_gemma":[0.3728437,0.0007163431,0.1751854,0.01479042,0.005183234,0.00004154981,0.0001465749,0.0002469082,0.4308459],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.939806,"threshold_uncertainty_score":0.9999591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1165270300492635,"score_gpt":0.3810499936203446,"score_spread":0.2645229635710812,"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."}}