{"id":"W2895601233","doi":"10.1145/3209280.3209532","title":"Active High-Recall Information Retrieval from Domain-Specific Text Corpora based on Query Documents","year":2018,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Ranking (information retrieval); Domain (mathematical analysis); Document retrieval; Class (philosophy); Artificial intelligence; Precision and recall; Active learning (machine learning); Natural language processing","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002448981,0.0001620933,0.0001455954,0.0001439694,0.0002034563,0.0003141301,0.000568968,0.00008117178,0.0005548887],"category_scores_gemma":[0.00002421252,0.0001308187,0.00004995889,0.0003545787,0.00006482264,0.001014782,0.0001204098,0.0002256853,0.002175937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008481769,"about_ca_system_score_gemma":0.00005542402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003175952,"about_ca_topic_score_gemma":0.000004953723,"domain_scores_codex":[0.9986252,0.0001045829,0.0002417426,0.0002983848,0.0004900969,0.0002400477],"domain_scores_gemma":[0.9988937,0.0001558137,0.0001655085,0.0005488539,0.0001261464,0.0001099107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009492965,0.0004365864,0.001405629,0.00001611013,0.00008977273,0.00003221859,0.003934789,0.0009593553,0.001595358,0.1778956,0.05691664,0.7557687],"study_design_scores_gemma":[0.004430848,0.00175798,0.0468186,0.0001128062,0.000009333838,0.000004908743,0.0001698822,0.4497036,0.01843189,0.02375066,0.4537692,0.001040344],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1124117,0.000003601387,0.8577278,0.001393295,0.001113279,0.0001540881,0.00001099428,0.0003085171,0.02687668],"genre_scores_gemma":[0.8603807,0.000003004869,0.1360424,0.00232997,0.0004203919,0.000004465626,0.00006946515,0.000009274533,0.0007403083],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7547283,"threshold_uncertainty_score":0.998601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007305110214433513,"score_gpt":0.2241554571873962,"score_spread":0.2168503469729627,"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."}}