{"id":"W4388195444","doi":"10.1016/j.knosys.2023.111080","title":"Table detection for visually rich document images","year":2023,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Mitacs","keywords":"Computer science; Information loss; Intersection (aeronautics); Artificial intelligence; Task (project management); Ground truth; Image (mathematics); Table (database); Data mining; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001340421,0.0002187887,0.0002839422,0.0004920104,0.0002811883,0.0004445513,0.0006385573,0.0001267161,0.00001035705],"category_scores_gemma":[0.0001308531,0.0002099071,0.0001173782,0.001391385,0.00003158697,0.000428874,0.0001127676,0.0001087614,0.0008954201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001450159,"about_ca_system_score_gemma":0.0001786279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000397617,"about_ca_topic_score_gemma":0.00002610279,"domain_scores_codex":[0.9980622,0.0001891789,0.00043279,0.0005570909,0.0002763299,0.0004824416],"domain_scores_gemma":[0.9982631,0.0003787233,0.0001524567,0.0005597475,0.0005190432,0.0001269929],"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":[0.0001109821,0.0008898899,0.0009782126,0.003984672,0.0002625231,0.00006520704,0.001807551,0.000800239,0.2678422,0.01748181,0.223381,0.4823957],"study_design_scores_gemma":[0.001287336,0.0005871277,0.0002616673,0.0003297681,0.00002444564,0.00001491855,0.00009080258,0.1708526,0.7163481,0.002386451,0.1071793,0.0006375592],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003203279,0.0003372508,0.9874573,0.0001486006,0.00163854,0.001293118,0.0000189904,0.002923953,0.002978914],"genre_scores_gemma":[0.9856825,0.00001166161,0.006666718,0.00005352468,0.0003401393,0.002162946,0.00003048044,0.00004172828,0.005010253],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9824793,"threshold_uncertainty_score":0.9998825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02134654737885951,"score_gpt":0.2956310126386067,"score_spread":0.2742844652597472,"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."}}