{"id":"W4200461582","doi":"10.1101/2021.12.23.473883","title":"Scholar Metrics Scraper (SMS): automated retrieval of citation and author data","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; Division of Mathematical Sciences; Fondation Leducq; Fondation Brain Canada; Heart and Stroke Foundation of Canada","keywords":"Citation; Computer science; Scraper site; Citation database; Scalability; Information retrieval; Measure (data warehouse); Data science; World Wide Web; Database","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":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.007760907,0.00197785,0.001549796,0.02127555,0.001117925,0.004823219,0.001812429,0.00100901,0.01592411],"category_scores_gemma":[0.04807338,0.001173707,0.001087899,0.01534088,0.0004965613,0.004299625,0.004478305,0.001363179,0.02015528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001173168,"about_ca_system_score_gemma":0.003579308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007663016,"about_ca_topic_score_gemma":0.01116376,"domain_scores_codex":[0.9923184,0.001691366,0.0008734753,0.001248669,0.003478821,0.0003893591],"domain_scores_gemma":[0.9628468,0.01353305,0.004469065,0.008185183,0.00886347,0.002102445],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004720845,0.0002301854,0.009291013,0.001114529,0.0002847747,0.0003898646,0.001309147,0.001602057,0.008960367,0.004004743,0.5755414,0.3967998],"study_design_scores_gemma":[0.0008487556,0.0004075177,0.05563275,0.0006845791,0.000228115,0.0007827643,0.002150608,0.09754242,0.08245324,0.02314978,0.7354629,0.0006565434],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.05666335,0.001531261,0.1748762,0.003409267,0.0009144804,0.001298411,0.1936951,0.5434663,0.02414571],"genre_scores_gemma":[0.1536514,0.001241775,0.4962829,0.00095758,0.0008877795,0.001835721,0.2784966,0.03683879,0.02980749],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.9922391,"threshold_uncertainty_score":0.05327153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08156628490478837,"score_gpt":0.2883319686352884,"score_spread":0.2067656837305,"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."}}