{"id":"W2933271723","doi":"10.1002/asi.24226","title":"Data objects and documenting scientific processes: An analysis of data events in biodiversity data papers","year":2019,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Research Data Management Practices","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"British Antarctic Survey; Alfred P. Sloan Foundation","keywords":"Computer science; Data science; Data set; Set (abstract data type); Information retrieval; Bridge (graph theory); Sentence; Research data; Data curation; World Wide Web","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":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01469224,0.0000448898,0.0001373819,0.001666565,0.0002431148,0.0009333631,0.009443884,0.0000381056,7.189188e-7],"category_scores_gemma":[0.007935259,0.0000327859,0.000007838978,0.005684215,0.0001337237,0.1280355,0.007082053,0.0001117614,8.810343e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008101511,"about_ca_system_score_gemma":0.0003846114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000240161,"about_ca_topic_score_gemma":0.0001669126,"domain_scores_codex":[0.9982415,0.00004082947,0.0003656377,0.0002545399,0.0009379351,0.0001594857],"domain_scores_gemma":[0.9957472,0.0001820321,0.00137718,0.001873526,0.0007898576,0.00003020165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001851276,0.00008663482,0.9633381,0.000124432,0.0002637442,2.777579e-7,0.001138473,0.0001171642,0.0006849536,0.00952122,0.0006872156,0.02401924],"study_design_scores_gemma":[0.002286059,0.0002636556,0.3771614,0.0001122799,0.0005086813,0.00001193409,0.009696214,0.4985085,0.0006908831,0.001725971,0.108711,0.0003234514],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9845496,0.00006042999,0.005038305,0.008535194,0.000340998,0.0005360107,0.0005970001,0.0000184719,0.000324003],"genre_scores_gemma":[0.9961414,0.0001406291,0.003497119,0.00006509074,0.000002977236,5.142361e-7,0.0001229996,5.730224e-7,0.00002870583],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5861767,"threshold_uncertainty_score":0.9959155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07773567746935987,"score_gpt":0.3633635898466321,"score_spread":0.2856279123772722,"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."}}