{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001951683,0.001419193,0.001935346,0.003286739,0.0005626069,0.002108599,0.002096284,0.002144953,0.00539972],"category_scores_gemma":[0.006581736,0.0005767967,0.001413217,0.003868878,0.0006431782,0.004024752,0.001566834,0.002350664,0.004276519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001294247,"about_ca_system_score_gemma":0.001303678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004597288,"about_ca_topic_score_gemma":0.005463167,"domain_scores_codex":[0.9987062,0.0003780319,0.0001225151,0.0003062126,0.0003195774,0.0001675273],"domain_scores_gemma":[0.9977638,0.001134491,0.000167126,0.0004649805,0.0003837738,0.00008578404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006936803,0.0003856798,0.001233567,0.0003296702,0.0001291917,0.0000926178,0.0001502239,0.03593347,0.01691003,0.006727853,0.02309486,0.9143191],"study_design_scores_gemma":[0.00009497979,0.0003325412,0.000836988,0.00006168934,0.0001247446,0.0002810393,0.0001310234,0.959829,0.009719145,0.02331355,0.005227149,0.00004812456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04401847,0.004138328,0.9396754,0.0006539817,0.0002272285,0.0001948488,0.001761657,0.007499811,0.00183024],"genre_scores_gemma":[0.3811697,0.003446969,0.5912277,0.0005455036,0.0006616867,0.0004982542,0.01228863,0.000628626,0.009532911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00539972,"threshold_uncertainty_score":0.0180639,"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."}}