{"id":"W6967930118","doi":"10.5281/zenodo.15747700","title":"Data Herding: Keeping your Research Ducks in a Row","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":false,"ca_institutions":"Queen's University; Ontario Council of University Libraries","funders":"","keywords":"Population; Data collection; Selection (genetic algorithm); Livestock","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":[0.01145162,0.0009754346,0.001017957,0.002566636,0.00355451,0.006827145,0.003193911,0.002337173,0.01191955],"category_scores_gemma":[0.03207837,0.001217496,0.0007709372,0.002849234,0.002161134,0.009086948,0.00590952,0.002955228,0.006506704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001091902,"about_ca_system_score_gemma":0.003591127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007111332,"about_ca_topic_score_gemma":0.0108257,"domain_scores_codex":[0.9924471,0.002371656,0.0007025654,0.001731452,0.0021158,0.0006313465],"domain_scores_gemma":[0.9596242,0.007337173,0.002836779,0.01792117,0.006418265,0.005862345],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009819891,0.0003926827,0.02983925,0.0005219771,0.000259517,0.0006263826,0.00484585,0.002179324,0.02332967,0.01163952,0.1689741,0.7564096],"study_design_scores_gemma":[0.000323766,0.001249385,0.02963792,0.00103891,0.0005638916,0.003149125,0.01715121,0.05891393,0.03988207,0.07085106,0.7768044,0.0004342793],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1597997,0.006699266,0.6552234,0.05350958,0.005884937,0.001124753,0.003004312,0.04988822,0.06486585],"genre_scores_gemma":[0.247327,0.001642708,0.6718711,0.005037276,0.0008980673,0.0003667156,0.00459716,0.005471651,0.06278836],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9885484,"threshold_uncertainty_score":0.06056267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2779497749905405,"score_gpt":0.4000227408206185,"score_spread":0.122072965830078,"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."}}