{"id":"W4318185157","doi":"10.1109/bigdata55660.2022.10020564","title":"A Novel Rigorous Measurement Model for Big Data Quality Characteristics","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Big data; Computer science; Data modeling; Quality (philosophy); Data mining; Database; Physics","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003808621,0.0005230819,0.0005241804,0.0004306049,0.0006925223,0.001165245,0.01558162,0.0001077835,0.0006162717],"category_scores_gemma":[0.001687976,0.0005366653,0.00006724057,0.0005040185,0.0001508142,0.003019417,0.01423682,0.0006236541,0.00021407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002138077,"about_ca_system_score_gemma":0.0005341115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001791008,"about_ca_topic_score_gemma":0.002560489,"domain_scores_codex":[0.9933088,0.00005003914,0.001074828,0.002262869,0.002695192,0.0006082271],"domain_scores_gemma":[0.9908994,0.0001312753,0.0009334378,0.007001189,0.0009757305,0.00005893692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001191419,0.002063079,0.0006978903,0.0003821337,0.0004788555,0.00002837353,0.00005136909,0.0003042303,0.007977203,0.03119813,0.4345047,0.5211226],"study_design_scores_gemma":[0.0007286242,0.00001880804,0.0005257921,0.00007358225,0.0001081833,0.000008436114,0.0001184559,0.5060958,0.00002868474,0.001105564,0.4906168,0.0005712986],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002940909,0.00008346818,0.6129281,0.007544855,0.03040891,0.001241568,0.3410549,0.0002534418,0.003543884],"genre_scores_gemma":[0.6710271,0.0001511794,0.0009029489,0.003928367,0.009516309,0.0001935718,0.3133636,0.00008316475,0.0008338011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6680862,"threshold_uncertainty_score":0.9998716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7505477363862263,"score_gpt":0.4080711581157322,"score_spread":0.3424765782704941,"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."}}