{"id":"W3092009239","doi":"10.1007/s11192-020-03718-9","title":"Navigation-based candidate expansion and pretrained language models for citation recommendation","year":2020,"lang":"en","type":"article","venue":"Scientometrics","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research; University of Waterloo","funders":"","keywords":"Computer science; Benchmark (surveying); Citation; Ranking (information retrieval); Vocabulary; Domain (mathematical analysis); Task (project management); Information retrieval; Artificial intelligence; Language model; Machine learning; Natural language processing; World Wide Web; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005930914,0.00007234412,0.00008019621,0.000525869,0.0001161532,0.0002035741,0.0002451489,0.00003753448,0.00000339541],"category_scores_gemma":[0.0004694295,0.00007163172,0.00002355396,0.00330145,0.00001497653,0.0005997351,0.0000599403,0.00005289676,0.000002214574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004411755,"about_ca_system_score_gemma":0.00006448996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001501454,"about_ca_topic_score_gemma":0.000001579724,"domain_scores_codex":[0.9989907,0.00002774239,0.0001629495,0.000353535,0.0003033163,0.0001617284],"domain_scores_gemma":[0.9992968,0.0001722611,0.00008036725,0.0001582124,0.000163771,0.0001286008],"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":[0.00003289048,0.00007036536,0.001000391,0.0002614147,0.00001357071,0.000003016525,0.02249643,0.05438607,0.01238903,0.0265204,0.00111719,0.8817092],"study_design_scores_gemma":[0.0004251568,0.00006069683,0.000150766,0.000008393489,0.000002977767,3.412212e-7,0.00007919788,0.9954609,0.00219711,0.001329466,0.0001982426,0.00008678118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09517525,0.00004579433,0.9010119,0.00312161,0.0001771187,0.0002490737,0.00001339741,0.00009639718,0.0001094015],"genre_scores_gemma":[0.8274258,0.000002323818,0.1717019,0.0007484847,0.00003425665,0.00001496567,0.00005169328,0.000004784515,0.00001574561],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9410748,"threshold_uncertainty_score":0.2921057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06364737314638658,"score_gpt":0.3116875286416323,"score_spread":0.2480401554952458,"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."}}