{"id":"W6893019505","doi":"10.5281/zenodo.13827956","title":"How Discovery Systems Use DataCite Metadata: Harvester Roundtable","year":2024,"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":"OpenAlex","funders":"","keywords":"Metadata; Key (lock); Public access; Information technology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["scholarly_communication"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"},{"model":"gpt","categories":["scholarly_communication"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001872859,0.0001944842,0.0001716136,0.0005024098,0.001335678,0.9014776,0.004914045,0.00004689536,0.00001808416],"category_scores_gemma":[0.001299225,0.0001786819,0.00005605788,0.001327224,0.00009675534,0.9267924,0.006393457,0.0003983424,0.0002980498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002474709,"about_ca_system_score_gemma":0.000009789842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000965186,"about_ca_topic_score_gemma":9.213702e-7,"domain_scores_codex":[0.9965692,0.0007171809,0.0002495136,0.0009873657,0.0008921229,0.0005846242],"domain_scores_gemma":[0.9972945,0.0001392126,0.00008996856,0.001962796,0.0003035567,0.0002099437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009857545,0.00005034334,0.000001381263,0.0001833119,0.0001080216,0.0001274086,0.00004689716,0.00004751468,0.0009600763,0.9547246,0.04087016,0.002870483],"study_design_scores_gemma":[0.0001428728,0.00009171292,0.00007785152,0.00006744391,0.00001815774,0.0001260706,0.000114856,0.001114863,0.00009074924,0.0001042071,0.9978451,0.0002060812],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0006109335,0.0004919906,0.9907472,0.002881277,0.0004454169,0.0005040915,0.0005865936,0.001090566,0.002641951],"genre_scores_gemma":[0.03877474,0.0006453713,0.001599802,0.0001111626,0.0001958132,1.757366e-7,0.002286256,0.0007181626,0.9556685],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9891474,"threshold_uncertainty_score":0.9999645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1499344929597019,"score_gpt":0.3023084831372117,"score_spread":0.1523739901775098,"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."}}