{"id":"W4393168550","doi":"10.23919/icact60172.2024.10471992","title":"Multi-Class Document Classification using LayoutLMv1 and V2","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Class (philosophy); Computer science; Artificial intelligence; Information retrieval; Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001728507,0.000109455,0.00008397044,0.0001789246,0.00009579355,0.0006930833,0.0003767028,0.00007116129,0.00002761396],"category_scores_gemma":[0.0000199916,0.00008799203,0.00003027022,0.0003677428,0.00006599853,0.0008328498,0.0002103676,0.00009850637,0.0001002268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006995535,"about_ca_system_score_gemma":0.00004217333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001890859,"about_ca_topic_score_gemma":0.000004058772,"domain_scores_codex":[0.9990551,0.00002093776,0.0001824874,0.0004139344,0.0001583701,0.0001691532],"domain_scores_gemma":[0.9994278,0.00005011331,0.00003344084,0.0004117028,0.00003018097,0.0000467399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[7.343399e-7,0.00002348072,0.000286589,0.00002407681,0.00001444851,0.000004572163,0.00023644,0.000009533054,0.02393085,0.8453372,0.00113361,0.1289985],"study_design_scores_gemma":[0.0001769557,0.00002993571,0.003058973,0.00003142702,0.000009237948,0.00001851467,0.0002704312,0.9324946,0.007406766,0.01126956,0.04500169,0.0002319148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02203363,0.0008847893,0.965232,0.007174391,0.0004021347,0.0001782693,9.477448e-7,0.002037656,0.002056176],"genre_scores_gemma":[0.8751454,0.0000865429,0.1226616,0.0001189295,0.00001941295,0.00001664159,0.00000145526,0.000007012516,0.001942983],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.932485,"threshold_uncertainty_score":0.6683418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06226273246793539,"score_gpt":0.3185489801885477,"score_spread":0.2562862477206123,"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."}}