{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005965294,0.001196349,0.001583896,0.001913242,0.0005973083,0.001288273,0.0008333756,0.001868367,0.003316588],"category_scores_gemma":[0.02758873,0.0003225321,0.0006906472,0.0007258973,0.0003188745,0.001566517,0.0007450907,0.0008624804,0.001549442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007001727,"about_ca_system_score_gemma":0.001136423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003736874,"about_ca_topic_score_gemma":0.004950128,"domain_scores_codex":[0.9964738,0.00177839,0.0002779076,0.0003779434,0.0009265538,0.0001653156],"domain_scores_gemma":[0.9842606,0.01257447,0.0004635515,0.0003900566,0.002015383,0.0002958674],"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":[0.01054371,0.002388965,0.009490937,0.002628943,0.0009281894,0.0004327959,0.0005421565,0.04405293,0.1439818,0.001094848,0.01943057,0.7644842],"study_design_scores_gemma":[0.00087746,0.004431417,0.01835079,0.0001107224,0.001201183,0.0005673236,0.0002498139,0.9054238,0.06366134,0.00205599,0.00294272,0.0001273288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7510055,0.0154103,0.2187283,0.0008884288,0.0008114804,0.0008568126,0.001380443,0.005765983,0.005152695],"genre_scores_gemma":[0.9170604,0.001111057,0.07484335,0.0002256332,0.0004723941,0.0001908092,0.002711774,0.0001971688,0.003187427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005965294,"threshold_uncertainty_score":0.03154784,"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."}}