{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003490358,0.003382521,0.002328224,0.01311523,0.001647112,0.003919171,0.003543005,0.003891437,0.009118656],"category_scores_gemma":[0.007249852,0.0006278884,0.002789849,0.007243581,0.0006627331,0.003205786,0.002335697,0.002799039,0.01116205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002326642,"about_ca_system_score_gemma":0.002728698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01061566,"about_ca_topic_score_gemma":0.0154242,"domain_scores_codex":[0.9964393,0.0005350935,0.0004433239,0.001129285,0.0009800594,0.0004729191],"domain_scores_gemma":[0.9961655,0.001369113,0.000279427,0.000804959,0.001135736,0.0002452719],"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":[0.0009215528,0.0006978292,0.005714769,0.0009821682,0.0003937634,0.0003132996,0.0001871,0.01168859,0.01091459,0.001054878,0.1187111,0.8484204],"study_design_scores_gemma":[0.0005522106,0.001192599,0.01055626,0.0003536455,0.0002764304,0.001345616,0.0010694,0.8395951,0.06155132,0.007421607,0.07582462,0.0002611529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1519805,0.01535582,0.3944287,0.002454226,0.003909369,0.003109185,0.09467889,0.3167604,0.01732293],"genre_scores_gemma":[0.2669663,0.001597058,0.5742811,0.0009080277,0.0006201096,0.001875201,0.1385208,0.002988035,0.01224346],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01311523,"threshold_uncertainty_score":0.03050488,"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."}}