{"id":"W4415881427","doi":"10.1519/jsc.0000000000005253","title":"Scraping the Surface: A Guide to Data Collection Using Web Scraping in Sports Medicine","year":2025,"lang":"en","type":"article","venue":"The Journal of Strength and Conditioning Research","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Provincial Laboratory of Public Health; University of Alberta","funders":"","keywords":"Data collection; Operationalization; Popularity; Data extraction; Strengths and weaknesses; Transparency (behavior); Data sharing; Code (set theory)","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0641541,0.00278677,0.002991977,0.01249107,0.003411179,0.007005102,0.005408403,0.003309683,0.09436374],"category_scores_gemma":[0.1524614,0.003705628,0.00349993,0.009518776,0.003701127,0.006285492,0.007293077,0.008623542,0.09964697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002871453,"about_ca_system_score_gemma":0.01808913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006955227,"about_ca_topic_score_gemma":0.0160542,"domain_scores_codex":[0.9394643,0.03393735,0.01214296,0.00184895,0.01174736,0.0008591218],"domain_scores_gemma":[0.7737393,0.1362632,0.007950364,0.02576642,0.05131438,0.004966435],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001975482,0.0003534522,0.0008860304,0.00349398,0.00008467952,0.0004541493,0.003896298,0.0004715845,0.002456972,0.005044577,0.6713534,0.3113073],"study_design_scores_gemma":[0.0001311591,0.0001310288,0.002634009,0.004644317,0.00002991745,0.0004647551,0.002115606,0.0009448554,0.001229738,0.01062706,0.9768843,0.0001631869],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003966244,0.009729728,0.6645583,0.03012695,0.007368606,0.07585032,0.06772717,0.05599038,0.08468231],"genre_scores_gemma":[0.004424943,0.006393083,0.8653466,0.006859154,0.0009934732,0.05927496,0.01197492,0.009060969,0.03567194],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9358459,"threshold_uncertainty_score":0.3392833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1508436943774424,"score_gpt":0.4567894811032112,"score_spread":0.3059457867257688,"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."}}