{"id":"W2949999477","doi":"10.48550/arxiv.1312.7373","title":"Extending Contexts with Ontologies for Multidimensional Data Quality Assessment","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Datalog; Context (archaeology); Quality (philosophy); Data quality; Quality assessment; Database; Information retrieval; Data mining; Data science; Evaluation methods; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005849352,0.000404334,0.000773235,0.0003207031,0.0003488511,0.0003606577,0.004089482,0.0002399811,0.0003360845],"category_scores_gemma":[0.001410907,0.0003236498,0.0001870264,0.0003524753,0.0003543229,0.001117447,0.007865082,0.0004526226,0.0001683068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000209839,"about_ca_system_score_gemma":0.0003196941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008617088,"about_ca_topic_score_gemma":0.001570132,"domain_scores_codex":[0.9950079,0.0006796899,0.0006887612,0.002544089,0.0006086627,0.0004709222],"domain_scores_gemma":[0.990566,0.002973719,0.0009612338,0.004676195,0.0006236804,0.0001991929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003427894,0.0003958881,0.00712718,0.0001480071,0.0004454871,0.00009701784,0.0001442815,0.02658853,0.00001999353,0.9041305,0.04829963,0.01226075],"study_design_scores_gemma":[0.004244261,0.0003451696,0.07914578,0.0003387856,0.0005346342,0.000005012434,0.007256782,0.3106357,0.0000370555,0.3725464,0.2228379,0.002072541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1931467,0.00007697746,0.7980647,0.000830808,0.000869407,0.001532349,0.002534214,0.0001638334,0.00278097],"genre_scores_gemma":[0.9673164,0.00006406779,0.02275558,0.0002831646,0.00007228192,0.000009271948,0.0009602213,0.0000207565,0.008518292],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7753091,"threshold_uncertainty_score":0.9999216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6427823544612737,"score_gpt":0.3972805547871189,"score_spread":0.2455017996741548,"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."}}