{"id":"W2967688951","doi":"10.5220/0007978403770384","title":"Data Quality in Secondary Data Analysis: A Case Study of Ecological Data using a Semiotic-based Approach","year":2019,"lang":"en","type":"article","venue":"","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Semiotics; Data quality; Computer science; Data warehouse; Data science; Data collection; Quality (philosophy); Process (computing); Data modeling; Data model (GIS); Domain (mathematical analysis); Data analysis; Multidimensional analysis; Information retrieval; Data mining; Database; Artificial intelligence; Engineering; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07018854,0.0006807175,0.001185785,0.00507559,0.005853106,0.01474533,0.003153519,0.003351312,0.002070965],"category_scores_gemma":[0.1279719,0.0007135491,0.001933947,0.01195612,0.01085561,0.009917129,0.00813638,0.004141891,0.0005162536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00662138,"about_ca_system_score_gemma":0.00811639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009803436,"about_ca_topic_score_gemma":0.007861558,"domain_scores_codex":[0.9054728,0.06530081,0.006131475,0.002781683,0.01860763,0.001705631],"domain_scores_gemma":[0.7304802,0.2150192,0.007115946,0.02190996,0.0227935,0.002681252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001022122,0.001218203,0.03809026,0.003427382,0.0002989643,0.02361282,0.2515809,0.02261739,0.01051603,0.4313119,0.01297009,0.203334],"study_design_scores_gemma":[0.0003234714,0.000914299,0.01649658,0.002580774,0.0003820662,0.01558844,0.1340302,0.1105594,0.03834666,0.2933611,0.3870201,0.0003969928],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2093556,0.0009132407,0.7514539,0.01243414,0.0001774168,0.001647251,0.0008669301,0.0008357596,0.02231576],"genre_scores_gemma":[0.6830108,0.0007053476,0.309648,0.0007348324,0.0000927947,0.0006795395,0.0007898095,0.000459885,0.003879098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07018854,"threshold_uncertainty_score":0.3711969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3458250035053249,"score_gpt":0.4033727382815156,"score_spread":0.05754773477619074,"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."}}