{"id":"W4410636570","doi":"10.1007/s10032-025-00527-9","title":"Revisiting Table Detection Datasets for Visually Rich Documents","year":2025,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Defence Research and Development Canada; University of Ottawa","funders":"Mitacs","keywords":"Table (database); Information retrieval; Computer science; Data mining","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001174564,0.0002110827,0.000303608,0.001595565,0.0003750279,0.001539182,0.0006269617,0.00009180177,0.0002044],"category_scores_gemma":[0.0002012133,0.0001892199,0.000256576,0.0009100451,0.00002896664,0.001271312,0.0001737874,0.0002494538,0.00002886403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002054577,"about_ca_system_score_gemma":0.00006020232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002359866,"about_ca_topic_score_gemma":0.00001323942,"domain_scores_codex":[0.997826,0.0001379995,0.0006997041,0.0004780691,0.0006053358,0.0002529117],"domain_scores_gemma":[0.9981875,0.0002289545,0.000455608,0.0002117745,0.0007965381,0.0001195768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001024041,0.0001432601,0.0009831645,0.00002001282,0.002377592,0.00002409408,0.00005397723,0.00002553768,0.001251073,0.002235489,0.002381221,0.9904022],"study_design_scores_gemma":[0.01076615,0.001483161,0.01355762,0.002338195,0.004422061,0.0004534999,0.0003494421,0.04718193,0.3167491,0.4216775,0.1783355,0.002685717],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02985997,0.0001383673,0.9648899,0.00233519,0.0008253967,0.0003076635,0.0001052892,0.0001269085,0.001411322],"genre_scores_gemma":[0.9606711,0.001485908,0.03209068,0.003152651,0.0005717847,0.0001390467,0.0006336328,0.00001760184,0.001237633],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9877164,"threshold_uncertainty_score":0.9994973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01224472622766342,"score_gpt":0.3188094202265064,"score_spread":0.306564693998843,"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."}}