{"id":"W2967813257","doi":"10.1007/s10791-019-09361-0","title":"Evaluating sentence-level relevance feedback for high-recall information retrieval","year":2019,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Relevance feedback; Relevance (law); Recall; Computer science; Sentence; Baseline (sea); Information retrieval; Precision and recall; Natural language processing; Artificial intelligence; Cognitive psychology; Psychology; Image retrieval","routes":{"ca_aff":true,"ca_fund":true,"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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001657817,0.0002508897,0.0002852199,0.0002941217,0.0002080377,0.0006004287,0.0009571533,0.0002063052,0.00005302965],"category_scores_gemma":[0.001572526,0.0002481626,0.0001180916,0.0007286257,0.00003004411,0.01238474,0.0002618658,0.0002828366,0.001411036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002531035,"about_ca_system_score_gemma":0.0003034283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002212436,"about_ca_topic_score_gemma":8.695101e-7,"domain_scores_codex":[0.9968733,0.00005611903,0.001159055,0.0002631182,0.001142315,0.0005061578],"domain_scores_gemma":[0.9969814,0.0003514196,0.0006795368,0.0008184863,0.001038762,0.0001304048],"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":[0.001563148,0.00008240072,0.001056261,0.001158182,0.000130585,0.000001375229,0.01184533,0.06378419,0.003649749,0.2340185,0.004764323,0.677946],"study_design_scores_gemma":[0.002623551,0.0004065951,0.001867975,0.00009905322,0.00001260513,0.00001740322,0.0002236504,0.9673481,0.005361234,0.003641358,0.01793341,0.0004650866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2182396,0.0000160242,0.7757292,0.0009311115,0.001946559,0.001145741,0.00004261674,0.000292135,0.001656957],"genre_scores_gemma":[0.7672732,0.00001493538,0.2295872,0.002108195,0.000190516,0.00002071892,0.0001948523,0.00001396311,0.0005964512],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9035639,"threshold_uncertainty_score":0.9999971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04688903707632153,"score_gpt":0.292025163440755,"score_spread":0.2451361263644335,"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."}}