{"id":"W4417456948","doi":"10.1007/s11192-025-05508-7","title":"Data as scholarly output: addressing challenges in data citation tracking through natural language processing automation","year":2025,"lang":"en","type":"article","venue":"Scientometrics","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Concordia University","keywords":"Citation; Python (programming language); Tracking (education); Automation; Citation analysis; Bibliometrics","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":[0.05651845,0.0009950858,0.00260628,0.0126211,0.003138259,0.02987031,0.004359353,0.00253916,0.002349882],"category_scores_gemma":[0.2992386,0.001202729,0.001439656,0.02729866,0.004290226,0.02934875,0.007442734,0.006610857,0.002670928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002907524,"about_ca_system_score_gemma":0.01025857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007100855,"about_ca_topic_score_gemma":0.006756663,"domain_scores_codex":[0.927911,0.03783482,0.008225976,0.007470728,0.01773802,0.0008195374],"domain_scores_gemma":[0.5430458,0.3314296,0.02406457,0.05996063,0.03985238,0.001646966],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002815397,0.00035993,0.01696445,0.001681335,0.0002187076,0.0002346406,0.004231796,0.01391051,0.003933373,0.1983134,0.02203492,0.7378354],"study_design_scores_gemma":[0.0000649834,0.00009484605,0.005095651,0.0007145594,0.00016537,0.0002882619,0.00215597,0.2410439,0.01586092,0.635487,0.09884537,0.0001832452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01933642,0.002509552,0.9407412,0.01684649,0.0006060281,0.0002685594,0.003078204,0.00853762,0.008076045],"genre_scores_gemma":[0.2811778,0.003595075,0.7025041,0.001776486,0.00109418,0.0004581976,0.005250464,0.001665849,0.002477768],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9873789,"threshold_uncertainty_score":0.2989017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5489135483319633,"score_gpt":0.5066334825260266,"score_spread":0.04228006580593668,"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."}}