{"id":"W4387846857","doi":"10.1145/3583780.3615046","title":"SAND: Semantic Annotation of Numeric Data in Web Tables","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Semantic Web; Annotation; Semantic Web Stack; Semantic annotation; Graph; Margin (machine learning); Knowledge graph; Social Semantic Web; Schema (genetic algorithms); Natural language processing; Artificial intelligence; Machine learning; Theoretical computer science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004390383,0.00004294744,0.0001315889,0.0003305258,0.00002263945,0.00007382222,0.0009414548,0.00001565001,0.0007316124],"category_scores_gemma":[0.001481505,0.00003110915,0.00001360825,0.001831122,0.00003139734,0.0005915565,0.0006560191,0.00002636167,0.001040648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004329863,"about_ca_system_score_gemma":0.00002519407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004112751,"about_ca_topic_score_gemma":0.001347466,"domain_scores_codex":[0.9984341,0.0001089595,0.0004046939,0.0002803049,0.0006565023,0.0001154779],"domain_scores_gemma":[0.9983678,0.0005309855,0.00008973467,0.0009522237,0.0000384101,0.0000208315],"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":[0.0000214304,0.0001250344,0.01893739,0.00004672525,0.00001650731,0.00001521819,0.0008499478,0.0005548375,0.001236256,0.02281906,0.769596,0.1857816],"study_design_scores_gemma":[0.0009939009,0.00006796263,0.1612023,0.00005421857,0.00001803348,0.000001105293,0.01667353,0.2332104,0.0007031323,0.07689877,0.5098777,0.0002989608],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8893638,0.0001290122,0.02966088,0.008632896,0.0008188969,0.0005784303,0.0008556857,0.0001933054,0.06976709],"genre_scores_gemma":[0.9931678,0.00006327723,0.0007311985,0.0001904189,0.00001148448,0.0000027223,0.0002658122,0.000002726581,0.005564571],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2597183,"threshold_uncertainty_score":0.9997371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3297667459228645,"score_gpt":0.4672587250817268,"score_spread":0.1374919791588622,"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."}}