{"id":"W4387842356","doi":"10.1016/j.datak.2023.102238","title":"User-generated short-text classification using cograph editing-based network clustering with an application in invoice categorization","year":2023,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"Ontario Ministry of Research and Innovation; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Foundation for Innovation","keywords":"Computer science; Categorization; Cluster analysis; Invoice; Information retrieval; Product (mathematics); Natural language processing; Data mining; Artificial intelligence; World Wide Web","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":[0.0004294922,0.0002161351,0.0002180712,0.0003179272,0.0001039003,0.0001070001,0.0004192852,0.00005477976,0.00000864954],"category_scores_gemma":[0.000007270851,0.0002388418,0.0000270463,0.002565399,0.0000176107,0.000444344,0.0001498386,0.0001866461,0.000008932822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006777749,"about_ca_system_score_gemma":0.0000476323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001983561,"about_ca_topic_score_gemma":0.0007040629,"domain_scores_codex":[0.9986285,0.00005311791,0.0003367128,0.0005059029,0.0001281178,0.0003476409],"domain_scores_gemma":[0.9989326,0.00005922742,0.00009000693,0.0007477261,0.00009489142,0.00007556527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001500087,0.0001067182,0.08540051,0.00005273158,0.00006493308,0.000001355608,0.0001486188,0.8631446,0.00877,0.001454289,0.0004267107,0.04041455],"study_design_scores_gemma":[0.0001533808,0.00001363088,0.007102872,0.00007639873,0.00004178211,2.465187e-7,0.00006493321,0.9900123,0.0003791896,0.00002562295,0.001884474,0.000245201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1486487,0.00003410666,0.8504485,0.000008973858,0.00008235434,0.0002820742,0.00003766047,0.0003980153,0.00005955367],"genre_scores_gemma":[0.9744105,0.000002594292,0.01388515,0.000003597253,0.0009449064,0.0001065471,0.01057982,0.0000615047,0.000005417891],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8365634,"threshold_uncertainty_score":0.9739686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04509888621521016,"score_gpt":0.2994695044326596,"score_spread":0.2543706182174494,"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."}}