{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.008383337,0.00004830986,0.0001038803,0.0006775388,0.0004473838,0.001050005,0.003577238,0.00007445624,4.036875e-7],"category_scores_gemma":[0.06985859,0.00003836026,0.00001682985,0.004085389,0.0003449856,0.04978548,0.002478532,0.0001389084,8.343015e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001028937,"about_ca_system_score_gemma":0.0004317865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001623434,"about_ca_topic_score_gemma":0.000005307366,"domain_scores_codex":[0.9981709,0.000009543668,0.0003137705,0.0002332408,0.001021564,0.0002510257],"domain_scores_gemma":[0.98914,0.0004166362,0.001300675,0.0004473514,0.008668012,0.00002731],"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":[0.000005488157,0.00002220472,0.002238995,0.0001294611,0.00001783107,9.869947e-9,0.0002933018,5.755241e-7,0.009120163,0.9718495,0.002194146,0.01412833],"study_design_scores_gemma":[0.001065562,0.00028238,0.002487316,0.00009601108,0.00005076688,0.00001416307,0.01222699,0.01991845,0.2923009,0.09424993,0.577115,0.0001925603],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1993824,0.0005950638,0.1719006,0.538651,0.002281082,0.009935551,0.001270344,0.0005407777,0.0754432],"genre_scores_gemma":[0.9293969,0.0003523089,0.06931757,0.0000864007,0.00001952217,0.0001052897,0.00001897024,0.000003023968,0.0007000721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8775995,"threshold_uncertainty_score":0.999987,"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."}}