{"id":"W4408980177","doi":"10.1007/978-981-96-0143-1_7","title":"Automatic Table Detection and Tabular Data Extraction from Scanned Documents","year":2025,"lang":"en","type":"book-chapter","venue":"Smart innovation, systems and technologies","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Table (database); Computer science; Extraction (chemistry); Information retrieval; Artificial intelligence; Pattern recognition (psychology); Database; Chromatography; Chemistry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005335874,0.0003559622,0.0004634697,0.001083028,0.000289863,0.0006276518,0.0008155311,0.0006926874,0.00001095697],"category_scores_gemma":[0.0001972994,0.0003467352,0.00001912559,0.000530418,0.0001383975,0.001224997,0.001044632,0.0004001382,0.00001106461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009246494,"about_ca_system_score_gemma":0.00008860383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004079389,"about_ca_topic_score_gemma":0.00007414031,"domain_scores_codex":[0.9978098,0.0000247009,0.0007453045,0.0009056794,0.0003045247,0.0002100508],"domain_scores_gemma":[0.997427,0.0001055511,0.0005977674,0.001433425,0.0004167853,0.00001944782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003002801,0.00001451539,0.0001343169,0.0003084627,0.0001554723,0.000009231514,0.00002109404,1.585577e-7,0.0009337701,0.2354245,0.007334053,0.7556614],"study_design_scores_gemma":[0.0006949919,0.0002193672,0.0003354249,0.003278301,0.0001480313,0.0001025151,0.0002957597,0.02590168,0.01015654,0.4149238,0.5425775,0.001366131],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003611927,0.01039456,0.9227052,0.001597565,0.00256239,0.003030893,0.000583884,0.01254094,0.04297261],"genre_scores_gemma":[0.7025368,0.01002681,0.1157268,0.0003745799,0.0005010006,0.001124907,0.002692464,0.0002248425,0.1667918],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8069784,"threshold_uncertainty_score":0.9998985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02523845195628567,"score_gpt":0.2619397415263762,"score_spread":0.2367012895700906,"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."}}