{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.00356909,0.001519791,0.002557183,0.005853218,0.001192613,0.002147307,0.002914227,0.002911504,0.004579556],"category_scores_gemma":[0.01608689,0.0007526428,0.002365638,0.006114601,0.0006495112,0.00400384,0.001766677,0.003028463,0.004379843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001183542,"about_ca_system_score_gemma":0.002812168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02100849,"about_ca_topic_score_gemma":0.03116752,"domain_scores_codex":[0.9980808,0.0007723055,0.0001891472,0.0004341067,0.0003044661,0.0002191291],"domain_scores_gemma":[0.9907673,0.006827734,0.000337206,0.0006187906,0.001159414,0.000289421],"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":[0.00128599,0.00113383,0.008003539,0.0005970355,0.0005444727,0.0003927727,0.0003462853,0.2679984,0.006363961,0.0146177,0.03346499,0.665251],"study_design_scores_gemma":[0.00002753474,0.00003445992,0.0003705437,0.0000159341,0.00005387814,0.00004195413,0.00001968411,0.9927453,0.0006637817,0.005297133,0.000711868,0.0000179703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1111503,0.005878877,0.8642191,0.002619663,0.0005992675,0.0002569851,0.003628862,0.007662918,0.003983981],"genre_scores_gemma":[0.7348387,0.002676646,0.2326228,0.000845573,0.001455892,0.0006943666,0.01181539,0.0006853797,0.01436531],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9941468,"threshold_uncertainty_score":0.04177243,"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."}}