{"id":"W2082489355","doi":"10.1145/1572741.1572763","title":"Tools for the efficient generation of hand-drawn corpora based on context-free grammars","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sketch; Computer science; Natural language processing; Grammar; Context (archaeology); Rule-based machine translation; Artificial intelligence; Ground truth; Symbol (formal); Domain (mathematical analysis); Sketch recognition; Context-free grammar; Theoretical computer science; Algorithm; Programming language; Linguistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005691482,0.002384716,0.002113019,0.005267954,0.001722818,0.003706043,0.004420676,0.001867728,0.02130993],"category_scores_gemma":[0.04558353,0.002617324,0.001829108,0.00505233,0.002518145,0.005738612,0.006184075,0.004300086,0.01420363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001292383,"about_ca_system_score_gemma":0.002282674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001965717,"about_ca_topic_score_gemma":0.003654636,"domain_scores_codex":[0.9930145,0.002491693,0.000855257,0.001904387,0.001549496,0.0001846026],"domain_scores_gemma":[0.9639018,0.02283974,0.001282869,0.008556146,0.002986804,0.0004326764],"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":[0.0004450612,0.0005101562,0.002397327,0.003029619,0.0002721069,0.001540322,0.003756578,0.06136712,0.05243056,0.07958794,0.07279918,0.7218642],"study_design_scores_gemma":[0.00041347,0.0002531882,0.002542216,0.000457162,0.0001178628,0.00140892,0.001122562,0.5690055,0.07722363,0.1607215,0.1863675,0.0003665192],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005181525,0.0002413399,0.9479306,0.0001804626,0.0001593473,0.0005563173,0.004697512,0.03840937,0.002643529],"genre_scores_gemma":[0.03999248,0.0002397886,0.9294977,0.0001158569,0.00007138404,0.001850771,0.0209258,0.005868261,0.001437976],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02130993,"threshold_uncertainty_score":0.07128888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05454921578927355,"score_gpt":0.268285942490044,"score_spread":0.2137367267007705,"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."}}