{"id":"W4378946015","doi":"10.48550/arxiv.2305.19181","title":"Table Detection 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":"University of Ottawa","funders":"Mitacs","keywords":"Computer science; Information loss; Intersection (aeronautics); Artificial intelligence; Ground truth; Task (project management); Image (mathematics); Data mining; Table (database); Term (time); Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004709071,0.0003007324,0.0003046046,0.000454042,0.000221058,0.0002773823,0.001429726,0.0003013162,0.00002248066],"category_scores_gemma":[0.00007139766,0.0003657746,0.0002099182,0.0007248938,0.00005612632,0.0005688921,0.001621226,0.0003742169,0.0001901977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002381628,"about_ca_system_score_gemma":0.0001580357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001393238,"about_ca_topic_score_gemma":0.00006117648,"domain_scores_codex":[0.9979573,0.0001002307,0.0002324802,0.001193044,0.0001099177,0.0004069833],"domain_scores_gemma":[0.9981718,0.0001763316,0.0002556562,0.0009006673,0.000367159,0.0001283719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007061763,0.002107583,0.00564687,0.004951077,0.002889802,0.00247892,0.002303703,0.1024123,0.02535065,0.5447766,0.07296046,0.2334159],"study_design_scores_gemma":[0.001049677,0.0004247166,0.0008573231,0.0002829299,0.0001702445,0.00001063892,0.00008388334,0.2090419,0.1264472,0.6557444,0.004466816,0.001420277],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01761308,0.00002064663,0.9780014,0.0001191757,0.0006998113,0.0008316864,0.00003559965,0.001866449,0.0008121674],"genre_scores_gemma":[0.97638,0.000235082,0.01550067,0.00008679225,0.0001136506,0.00003204725,0.00003427272,0.00003981113,0.007577687],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9625007,"threshold_uncertainty_score":0.9998794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0660151355830532,"score_gpt":0.2256042815368107,"score_spread":0.1595891459537574,"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."}}