{"id":"W760598031","doi":"10.1007/s00778-015-0389-y","title":"Profiling relational data: a survey","year":2015,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":273,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Metadata; Computer science; Data mining; Data type; Information retrieval; Data science; 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":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05177788,0.0000584324,0.0001057201,0.00008779347,0.0002647905,0.0005620382,0.002124306,0.0000212411,0.0002132176],"category_scores_gemma":[0.01092482,0.00002940482,0.00002786537,0.0003772489,0.00007365708,0.0009252531,0.0007525229,0.0002489306,0.0009997596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002482647,"about_ca_system_score_gemma":0.0001817656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000394526,"about_ca_topic_score_gemma":0.00009459696,"domain_scores_codex":[0.9964501,0.001076383,0.0004557821,0.0001861964,0.001677312,0.0001541984],"domain_scores_gemma":[0.9971984,0.001150703,0.0002507955,0.0009383176,0.0003282107,0.000133551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008279585,0.00004889921,0.02160096,7.102893e-7,0.00003862204,0.0000145812,0.0004793146,0.0007371026,0.000007779039,0.02283371,0.9319591,0.02219645],"study_design_scores_gemma":[0.0006290396,0.00005144617,0.08757444,0.000009612902,0.00001879511,0.0001690034,0.00230548,0.006690034,0.00001282652,0.1558823,0.7465175,0.0001395253],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.352442,0.001669338,0.5112038,0.05794158,0.009467906,0.0007046077,0.001088508,0.0001032462,0.065379],"genre_scores_gemma":[0.9670879,0.00005673001,0.01336891,0.002534217,0.001571264,0.000002907286,0.0002372622,0.00001702415,0.01512381],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6146459,"threshold_uncertainty_score":0.9997781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8844173631534311,"score_gpt":0.5434835487839118,"score_spread":0.3409338143695193,"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."}}