{"id":"W3194211952","doi":"10.1002/pra2.458","title":"Toward Best Practices for Unstructured Descriptions of Research Data","year":2021,"lang":"en","type":"article","venue":"Proceedings of the Association for Information Science and Technology","topic":"Research Data Management Practices","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Canada First Research Excellence Fund; Ocean Frontier Institute; Dalhousie University; Mitacs; Marine Environmental Observation Prediction and Response Network","keywords":"Computer science; Data science; Documentation; Best practice; Unstructured data; Set (abstract data type); Data sharing; Search engine indexing; Point (geometry); Conversation; Information retrieval; World Wide Web; Big data; Data mining; Sociology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4393086,0.002021411,0.002475686,0.03671246,0.0124582,0.05334707,0.01430858,0.009571135,0.002800448],"category_scores_gemma":[0.5394526,0.004854811,0.002883567,0.02471658,0.03775746,0.05470284,0.02987606,0.01636589,0.003407671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02176965,"about_ca_system_score_gemma":0.05175675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01461663,"about_ca_topic_score_gemma":0.01319992,"domain_scores_codex":[0.4771119,0.3717484,0.07433945,0.01348231,0.05900289,0.004315162],"domain_scores_gemma":[0.2101998,0.3779662,0.04246869,0.219975,0.1429881,0.00640223],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001264896,0.0003864038,0.005856847,0.005865517,0.0001736983,0.001178155,0.2139786,0.003972183,0.004373587,0.5072699,0.02834416,0.2284745],"study_design_scores_gemma":[0.00007996278,0.0001517357,0.001562015,0.02183813,0.000146277,0.001368046,0.106853,0.007616525,0.00763155,0.4782352,0.3741448,0.0003726626],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01292831,0.00440317,0.8941486,0.06440429,0.0007862554,0.002766632,0.000647748,0.002468296,0.01744678],"genre_scores_gemma":[0.04844054,0.002068299,0.9413691,0.002249194,0.0001938014,0.001991147,0.000747257,0.0007127112,0.002227906],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5606915,"threshold_uncertainty_score":0.6914324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2853651277475985,"score_gpt":0.443741816901022,"score_spread":0.1583766891534235,"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."}}