{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001298615,0.00009916993,0.0001299963,0.0003945851,0.0005843221,0.001043,0.0002899083,0.00004271729,0.000003027138],"category_scores_gemma":[0.00007441709,0.0000752108,0.00002930343,0.0009998144,0.0001017764,0.006290242,0.00008737789,0.00003763235,0.000006021851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002055027,"about_ca_system_score_gemma":0.00003407819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000590338,"about_ca_topic_score_gemma":0.000004466215,"domain_scores_codex":[0.9990609,0.00002583359,0.0002954903,0.0002032161,0.0002286827,0.0001858984],"domain_scores_gemma":[0.9990685,0.0001172841,0.0001130308,0.0001776069,0.0004211848,0.0001023756],"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":[0.00001642408,0.000007047917,0.0003327065,0.0001063611,0.00002058324,1.245704e-8,0.0107633,0.001431842,0.0002893669,0.0747835,0.0004068569,0.911842],"study_design_scores_gemma":[0.0003149662,0.0001503361,0.01373526,0.00001565589,0.00002078552,0.000005171962,0.00005909748,0.9671715,0.002770859,0.002852919,0.01278108,0.0001223178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02335754,0.000007185281,0.9745152,0.0008749139,0.0001012874,0.0007636055,0.00001153026,0.00006696104,0.0003017778],"genre_scores_gemma":[0.8770046,0.00001072343,0.1212914,0.001497374,0.00003760197,0.00008999976,0.0000501281,0.000002105177,0.00001606834],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9657397,"threshold_uncertainty_score":0.999994,"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."}}