{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009462829,0.001013583,0.0006067774,0.005946299,0.001031578,0.001231321,0.001099317,0.0009140779,0.008767792],"category_scores_gemma":[0.005891817,0.0002604436,0.000658419,0.004037126,0.0002929949,0.001516939,0.001015119,0.0006202015,0.004681647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007205259,"about_ca_system_score_gemma":0.0009890049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006521841,"about_ca_topic_score_gemma":0.01584067,"domain_scores_codex":[0.9991249,0.0001485418,0.00007511684,0.0003069835,0.0002798755,0.00006449297],"domain_scores_gemma":[0.9965464,0.00155489,0.0001787758,0.0005191553,0.001039292,0.0001615119],"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":[0.00130249,0.0006644445,0.01213049,0.001156724,0.0001813145,0.0009288308,0.001408558,0.02093931,0.03688588,0.00630237,0.1131095,0.8049901],"study_design_scores_gemma":[0.000111699,0.0001761282,0.01250878,0.00009296265,0.0001058004,0.0004911462,0.0008016844,0.856596,0.04326424,0.01347557,0.07224385,0.0001320791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2380017,0.0008916503,0.50752,0.000854451,0.001035988,0.001070785,0.0540631,0.1814596,0.0151027],"genre_scores_gemma":[0.3169282,0.0002639541,0.6100978,0.0001451334,0.0001625053,0.0005513955,0.05507698,0.003419159,0.01335493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008767792,"threshold_uncertainty_score":0.02933115,"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."}}