{"id":"W6949705662","doi":"10.5281/zenodo.15634431","title":"The Beginner's Guide to Data Curation","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Data curation; Digital curation; Work (physics); Data archive; Research data","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02402504,0.002086875,0.002213581,0.008763557,0.004636623,0.009500635,0.004141063,0.004136851,0.1011994],"category_scores_gemma":[0.05271839,0.003512934,0.001567466,0.0113707,0.004064557,0.009514987,0.008166608,0.009512673,0.1427107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005004284,"about_ca_system_score_gemma":0.03242065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04255404,"about_ca_topic_score_gemma":0.08602441,"domain_scores_codex":[0.9857334,0.005801722,0.002155326,0.001146894,0.004630318,0.0005323601],"domain_scores_gemma":[0.9490157,0.0180195,0.001636842,0.008472935,0.01976717,0.003087946],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001255317,0.00001583186,0.0001252079,0.0003682796,0.000007948856,0.00007031019,0.0005998756,0.0001005449,0.00038567,0.007523716,0.9106265,0.08016361],"study_design_scores_gemma":[0.000002738559,0.000002096013,0.0001162319,0.0002370303,0.000001540907,0.00004624978,0.000126644,0.00003366017,0.00004976126,0.002949236,0.9964274,0.000007474757],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007241449,0.05046649,0.4028399,0.1367429,0.01576879,0.004600775,0.04476655,0.04449314,0.2995973],"genre_scores_gemma":[0.004408592,0.05121557,0.4806327,0.04522608,0.00395944,0.005640776,0.03784664,0.01494591,0.3561242],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.975975,"threshold_uncertainty_score":0.3385458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09535802209298047,"score_gpt":0.3528864714512202,"score_spread":0.2575284493582397,"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."}}