{"id":"W4409671330","doi":"10.1145/3696410.3714701","title":"MixedSAND: Semantic Annotation of Mixed-unit Numeric Data","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Annotation; Natural language processing; Unit (ring theory); Information retrieval; Semantic annotation; Artificial intelligence; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.00317505,0.00006817146,0.0001840569,0.0002849603,0.0000620307,0.0001244924,0.001676922,0.00002581614,0.0007142498],"category_scores_gemma":[0.001768855,0.00004960001,0.00003147335,0.001152024,0.00006592667,0.0005706929,0.0009672937,0.00004167155,0.0003903929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004655367,"about_ca_system_score_gemma":0.00005508189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003081851,"about_ca_topic_score_gemma":0.0003079298,"domain_scores_codex":[0.99815,0.0001793568,0.000534813,0.0003726958,0.0006458602,0.0001172796],"domain_scores_gemma":[0.9972503,0.0007076544,0.0001368817,0.001740911,0.0001353238,0.00002898251],"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":[0.00001750399,0.0001165511,0.003325664,0.00003529195,0.00003981254,0.000001694699,0.00008970637,0.00003445294,0.0001444144,0.1376641,0.5451947,0.3133361],"study_design_scores_gemma":[0.0003950164,0.00003138147,0.04468546,0.0000300684,0.00004418642,4.808998e-7,0.003106451,0.008120248,0.000903519,0.06693112,0.8756254,0.0001266614],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06789463,0.000207719,0.716452,0.007505423,0.001369195,0.0003911501,0.0002781604,0.00008201728,0.2058197],"genre_scores_gemma":[0.967308,0.00002758111,0.003527205,0.0008229215,0.00001519944,0.0000031247,0.0001777952,0.000002829438,0.02811529],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8994134,"threshold_uncertainty_score":0.7820534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3282300458693544,"score_gpt":0.491568531296563,"score_spread":0.1633384854272086,"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."}}