{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005930148,0.0003910958,0.0003581325,0.0006417783,0.0003427375,0.0003823954,0.001199775,0.000534824,0.00004777688],"category_scores_gemma":[0.0001494279,0.0004752924,0.0002287814,0.0008888745,0.00006260375,0.000711485,0.0008619362,0.0006731048,0.00004684857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003519016,"about_ca_system_score_gemma":0.0002396867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001217748,"about_ca_topic_score_gemma":0.0001172604,"domain_scores_codex":[0.9974551,0.0002041575,0.0003093464,0.001416879,0.0001694403,0.0004450287],"domain_scores_gemma":[0.9976633,0.000299432,0.000429313,0.0008659335,0.0006128039,0.0001292723],"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":[0.001674393,0.001539344,0.004016043,0.008512159,0.002740549,0.002319583,0.004910473,0.2471552,0.06454381,0.0543717,0.02373191,0.5844849],"study_design_scores_gemma":[0.0006330624,0.0001744777,0.0001933329,0.0003210332,0.00011355,0.00000449603,0.000028331,0.2121011,0.1255027,0.6599958,0.0002298245,0.0007023055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05374078,0.00001400033,0.9420549,0.000131983,0.0007945009,0.001044287,0.0001520621,0.001873511,0.0001940126],"genre_scores_gemma":[0.952583,0.00007093441,0.04607049,0.0001718861,0.0001345178,0.00002341126,0.0002307031,0.00005050948,0.0006646191],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8988422,"threshold_uncertainty_score":0.9997699,"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."}}