{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00965426,0.000153297,0.000166585,0.004683469,0.0003175905,0.01577495,0.01117426,0.0000678391,0.00000232662],"category_scores_gemma":[0.02352634,0.000148717,0.00001468328,0.02075647,0.0000713031,0.1955046,0.007535483,0.0005026867,0.0000250364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001811463,"about_ca_system_score_gemma":0.0003494503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009892069,"about_ca_topic_score_gemma":0.0001577349,"domain_scores_codex":[0.9955098,0.0002961193,0.0003900125,0.001394745,0.00190352,0.0005058176],"domain_scores_gemma":[0.9950242,0.000612246,0.000267707,0.00371026,0.0003206882,0.00006488798],"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":[0.000004617935,0.0001018385,0.0005767958,0.0002271755,0.00001311624,0.00003234542,0.001741184,0.00003891687,0.0001509013,0.01426143,0.0007226224,0.982129],"study_design_scores_gemma":[0.0007446575,0.00002951573,0.06284849,0.0005426595,0.00002090468,0.000006675366,0.003121665,0.8887345,0.0001875032,0.00118839,0.04221455,0.0003605518],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02095882,0.07295966,0.8615018,0.01918238,0.001857406,0.0009937583,0.0001179086,0.0006302567,0.02179801],"genre_scores_gemma":[0.8927805,0.001786273,0.1036934,0.0003255274,0.00006176101,0.000009469851,0.0005740477,0.00001159189,0.0007574348],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9817685,"threshold_uncertainty_score":0.9972798,"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."}}