{"id":"W4376130046","doi":"10.1016/j.jbi.2023.104386","title":"Learning to rank query expansion terms for COVID-19 scholarly search","year":2023,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Query expansion; Computer science; Ranking (information retrieval); Information retrieval; Web search query; Benchmark (surveying); Learning to rank; Web query classification; Rank (graph theory); Domain (mathematical analysis); Query optimization; Set (abstract data type); Language model; Precision and recall; Search engine; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.004506571,0.000115605,0.0002523624,0.001059586,0.0003069719,0.0006049963,0.001007034,0.0001274318,0.00002453494],"category_scores_gemma":[0.002449007,0.00008317117,0.0001587124,0.001514684,0.00007200728,0.003023675,0.0003233982,0.0005852863,0.0002290916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001571356,"about_ca_system_score_gemma":0.0007150067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003659405,"about_ca_topic_score_gemma":2.190611e-7,"domain_scores_codex":[0.9967748,0.00006561023,0.001141559,0.00006618987,0.00151994,0.000431898],"domain_scores_gemma":[0.9975078,0.000430748,0.0003153135,0.0001986296,0.0005317437,0.00101575],"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":[0.0003569895,0.0002237077,0.000862581,0.001109626,0.0001051897,0.0001625292,0.0957761,0.004807613,0.004199514,0.004872895,0.1307757,0.7567475],"study_design_scores_gemma":[0.003680989,0.003696765,0.001876544,0.0002315531,0.00002212842,0.0004106878,0.007776634,0.3589083,0.001744246,0.00101885,0.6201798,0.0004534478],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1571613,0.000006637877,0.833716,0.008019837,0.0005815547,0.0002837499,0.00000801943,0.0001039646,0.0001189216],"genre_scores_gemma":[0.5978367,0.0003591251,0.373477,0.02431332,0.00119539,0.00005771101,0.0001112117,0.00005086223,0.00259863],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7562941,"threshold_uncertainty_score":0.5833994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0615972581029316,"score_gpt":0.3637558269493393,"score_spread":0.3021585688464077,"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."}}