{"id":"W2140565904","doi":"10.5539/cis.v7n1p162","title":"Layout Analysis for Scanned PDF and Transformation to the Structured PDF Suitable for Vocalization and Navigation","year":2014,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Optical character recognition; Software; Graphics; Reading (process); Section (typography); Information retrieval; Transformation (genetics); Font; ASCII; Representation (politics); Artificial intelligence; Computer graphics (images); Image (mathematics); Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"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":[0.0007768773,0.001016328,0.0004946108,0.004218325,0.0008188526,0.002806357,0.0008420612,0.0007255199,0.05683539],"category_scores_gemma":[0.00575794,0.0004166784,0.0007298135,0.003916499,0.0006734206,0.002079333,0.0006996875,0.001121256,0.0233708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006023535,"about_ca_system_score_gemma":0.001211338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001767232,"about_ca_topic_score_gemma":0.002537989,"domain_scores_codex":[0.998677,0.000156361,0.0001217544,0.0002701637,0.0006995265,0.00007513559],"domain_scores_gemma":[0.9970295,0.0008032433,0.000290613,0.0006018783,0.001211686,0.00006294522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001955321,0.00006371043,0.001204035,0.00113006,0.00003544319,0.0008639555,0.0005980879,0.002733256,0.08746888,0.01215001,0.05438426,0.8391729],"study_design_scores_gemma":[0.00006679672,0.0003331028,0.01259166,0.0004489319,0.0001128019,0.005657077,0.001318251,0.04954242,0.2577194,0.01071601,0.6612319,0.000261634],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0160944,0.001874599,0.9133123,0.0006810494,0.001280046,0.0005808219,0.00581662,0.0249439,0.03541626],"genre_scores_gemma":[0.1005779,0.003169661,0.8280641,0.0003050677,0.0003150306,0.0005831713,0.008731027,0.006030993,0.05222305],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05683539,"threshold_uncertainty_score":0.1901333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009019937935547423,"score_gpt":0.2487820889044696,"score_spread":0.2397621509689221,"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."}}