{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.01031834,0.0001534065,0.000180157,0.001507766,0.00232243,0.01335919,0.01524604,0.00006956777,0.0006206536],"category_scores_gemma":[0.00782477,0.0001699992,0.00002922651,0.004275677,0.00021044,0.01772909,0.03098472,0.0009250302,0.002091274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003183879,"about_ca_system_score_gemma":0.00002799895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007504474,"about_ca_topic_score_gemma":0.000005528565,"domain_scores_codex":[0.9945596,0.001785797,0.0003900584,0.001253562,0.001126162,0.0008848606],"domain_scores_gemma":[0.9952474,0.0002328578,0.00009573792,0.0035628,0.000678718,0.0001825408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008470828,0.0004746057,0.00008767384,0.0002478885,0.0001014011,0.0002085983,0.001089034,0.00009835202,0.002175272,0.3180959,0.3955398,0.2817968],"study_design_scores_gemma":[0.0004590488,0.00008454717,0.001248027,0.00009583311,0.000003716118,0.0000185158,0.000546423,0.00877288,0.000119489,0.001256984,0.9872385,0.0001560537],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.00464529,0.0004753935,0.3705738,0.02341197,0.0003057443,0.00152927,0.0001979347,0.001405879,0.5974547],"genre_scores_gemma":[0.9534838,0.00205722,0.01347741,0.001115625,0.0003479383,7.036734e-7,0.003518362,0.001606186,0.02439274],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9488385,"threshold_uncertainty_score":0.9989764,"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."}}