{"id":"W2901806206","doi":"10.2166/wqrj.2018.013","title":"Towards a water quality database for raw and validated data with emphasis on structured metadata","year":2018,"lang":"en","type":"article","venue":"Water Quality Research Journal","topic":"Environmental Monitoring and Data Management","field":"Earth and Planetary Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Metadata; Database; Documentation; Raw data; Computer science; Data quality; Quality (philosophy); Data mining; Information retrieval; World Wide Web; Engineering","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01221901,0.0002078601,0.0002790877,0.0001662206,0.001008833,0.001053827,0.001139034,0.00006084061,0.001338737],"category_scores_gemma":[0.0001998712,0.000101695,0.00004009521,0.0001028625,0.0005343533,0.001665154,0.0004807556,0.0004712908,0.0001290586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002155801,"about_ca_system_score_gemma":0.00003846532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00495165,"about_ca_topic_score_gemma":0.001314211,"domain_scores_codex":[0.9954006,0.001232232,0.000449049,0.0006982671,0.001341498,0.000878373],"domain_scores_gemma":[0.9978713,0.0001955833,0.00006335138,0.001350876,0.0001139283,0.000405007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.02342958,0.0009836352,0.4369516,0.001327228,0.003154139,0.0004818557,0.006985255,0.0002307074,0.04630496,0.0006993946,0.04526498,0.4341867],"study_design_scores_gemma":[0.00660018,0.004392835,0.4981183,0.0002066782,0.0002019804,0.0002171987,0.003099517,0.001029702,0.1853149,0.00397099,0.2955457,0.001301933],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903676,0.00009371056,0.00248532,0.002370713,0.0003000163,0.0004606847,0.003534491,0.00002547756,0.0003620227],"genre_scores_gemma":[0.9868231,0.0001198193,0.005284062,0.0001795159,0.0006365188,0.000003480211,0.006333959,0.00001060811,0.0006089095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4328847,"threshold_uncertainty_score":0.9999832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3127212060043523,"score_gpt":0.4385814531661647,"score_spread":0.1258602471618124,"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."}}