{"id":"W4327644584","doi":"10.1007/978-3-031-28238-6_51","title":"Learning Query-Space Document Representations for High-Recall Retrieval","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; University of Waterloo; Toronto Metropolitan University","funders":"","keywords":"Computer science; Information retrieval; Set (abstract data type); Recall; Representation (politics); Space (punctuation); Range (aeronautics); Precision and recall; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001431632,0.0004586228,0.0004996695,0.0007811508,0.0004412696,0.0007432061,0.002835288,0.0003155555,0.00001193668],"category_scores_gemma":[0.0004890739,0.0004548231,0.0001647001,0.000720658,0.0002948299,0.0005945049,0.001559806,0.0009150182,0.00006709295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003785347,"about_ca_system_score_gemma":0.0005253343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007854403,"about_ca_topic_score_gemma":0.0000660092,"domain_scores_codex":[0.9954671,0.00005044149,0.0006094631,0.001993833,0.001107371,0.0007718421],"domain_scores_gemma":[0.996352,0.001337245,0.0003300766,0.001461316,0.0003396914,0.0001797357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001372238,0.00001491888,0.00003754828,0.00006742449,0.00002467367,0.0000609849,0.001508842,0.4426526,0.0002709094,0.2644647,0.00008886487,0.2907947],"study_design_scores_gemma":[0.0003105585,0.0001751367,0.00005295759,0.0002346255,0.000009711127,0.00001631136,5.369139e-7,0.5818459,0.000942742,0.4147399,0.001157714,0.0005139097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001255892,0.00008515984,0.9904273,0.004072155,0.003226329,0.0006907624,0.000004126403,0.0004630164,0.0009055239],"genre_scores_gemma":[0.07454652,0.00006919023,0.9146274,0.0007342217,0.001079836,0.00003691826,0.00001833656,0.0000827324,0.008804822],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2902808,"threshold_uncertainty_score":0.9997904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02723612666037623,"score_gpt":0.2840207212977938,"score_spread":0.2567845946374176,"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."}}