{"id":"W4392057301","doi":"10.3389/frma.2024.1335454","title":"Scholar Metrics Scraper (SMS): automated retrieval of citation and author data","year":2024,"lang":"en","type":"article","venue":"Frontiers in Research Metrics and Analytics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Vancouver Coastal Health","funders":"Division of Mathematical Sciences; Canadian Institutes of Health Research; Deutsches Krebsforschungszentrum; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Heart and Stroke Foundation of Canada","keywords":"Citation; Computer science; Scraper site; Information retrieval; Visualization; Data science; Graph; Citation database; Data retrieval; Data visualization; World Wide Web; Data mining; Scopus","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":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.1256891,0.0002332937,0.0006821924,0.2001942,0.0003718243,0.005100957,0.002899451,0.0003344001,0.00004199164],"category_scores_gemma":[0.2216733,0.0001782101,0.0000935121,0.4398936,0.0007787796,0.001603759,0.002654542,0.001585181,0.00001949863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002448821,"about_ca_system_score_gemma":0.0006230528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001178095,"about_ca_topic_score_gemma":0.00000851989,"domain_scores_codex":[0.9810916,0.001118511,0.001356774,0.001600689,0.01379506,0.001037371],"domain_scores_gemma":[0.9793847,0.01303803,0.0002104558,0.001686229,0.004879891,0.0008007408],"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":[0.0001211123,0.0002981288,0.23074,0.0002889912,0.0002039302,0.0002008099,0.0003893585,0.00008171761,0.0006617937,0.004686619,0.270911,0.4914165],"study_design_scores_gemma":[0.0004492563,0.0002584532,0.02777652,0.00006432899,0.0000279177,0.000006533945,0.001630906,0.9065436,0.0002423133,0.01514201,0.04763302,0.0002251893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6699031,0.1915167,0.1218567,0.005427917,0.003755843,0.001607928,0.001493957,0.0002508943,0.004186959],"genre_scores_gemma":[0.9483922,0.0161517,0.03341378,0.00002921991,0.00008893478,0.000003555357,0.00004783743,0.00003357018,0.001839195],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9064618,"threshold_uncertainty_score":0.9959319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7988117842642299,"score_gpt":0.6516311723059829,"score_spread":0.1471806119582471,"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."}}