{"id":"W4389326172","doi":"10.48550/arxiv.2312.00699","title":"Rethinking Detection Based Table Structure Recognition for Visually Rich Document Images","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Computer science; Cascade; Table (database); Artificial intelligence; Data mining; Pattern recognition (psychology); Task (project management); Limiting; Graph; Machine learning; Theoretical computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0007672934,0.001987152,0.001418806,0.002585344,0.0003225063,0.002334293,0.003049451,0.001216441,0.004478265],"category_scores_gemma":[0.003122958,0.000579878,0.001641002,0.001173401,0.0004649599,0.003742292,0.001167813,0.001445676,0.006369244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00111664,"about_ca_system_score_gemma":0.001301613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0107981,"about_ca_topic_score_gemma":0.0175033,"domain_scores_codex":[0.9990965,0.00007154151,0.00006279182,0.0003801227,0.0002679336,0.0001210912],"domain_scores_gemma":[0.9988163,0.0003427197,0.0001303221,0.0003361559,0.0003039031,0.00007070289],"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":[0.0004233255,0.0002583546,0.005618754,0.0006084129,0.000192509,0.0003907897,0.0001266394,0.0310161,0.06031656,0.002901618,0.03006018,0.8680868],"study_design_scores_gemma":[0.00003020608,0.0002390032,0.003547868,0.0001018904,0.000107393,0.0004851784,0.0001493967,0.9043657,0.07340527,0.003431532,0.01408588,0.00005077193],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1687681,0.00630096,0.7034963,0.001172659,0.001210346,0.0008893512,0.01158919,0.09248925,0.01408391],"genre_scores_gemma":[0.442524,0.002229205,0.5068346,0.001070815,0.0002162566,0.0003254902,0.02741313,0.001503027,0.0178835],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0107981,"threshold_uncertainty_score":0.02147049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07789674347453357,"score_gpt":0.2231321581178949,"score_spread":0.1452354146433614,"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."}}