{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004698418,0.0001106852,0.000136671,0.00008951892,0.0002069679,0.0003790218,0.0007516109,0.00005367287,0.00002390071],"category_scores_gemma":[0.0002375218,0.00007279893,0.0001035595,0.0002056093,0.00007615865,0.0001506433,0.00004019609,0.00006014905,0.000007256249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002793223,"about_ca_system_score_gemma":0.00007999818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000143863,"about_ca_topic_score_gemma":0.00001430172,"domain_scores_codex":[0.9990227,0.00004498184,0.0002552527,0.000244495,0.0002700136,0.0001625994],"domain_scores_gemma":[0.9984598,0.0004255173,0.0001248791,0.0007187062,0.0002291725,0.00004197194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002730199,0.0002020327,0.000005904607,0.0000064716,0.0000070879,0.000001177112,0.0001126893,0.0008526604,0.01649237,0.1626255,0.01399293,0.8056738],"study_design_scores_gemma":[0.0006090776,0.000556581,0.0001945575,0.00001873587,0.000006404843,0.000001543249,0.000009155317,0.5674775,0.422056,0.006723581,0.002235941,0.0001109069],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003457207,0.00002365265,0.9901858,0.004225951,0.0001220126,0.0007326878,0.00001079087,0.0001741601,0.001067729],"genre_scores_gemma":[0.8955761,0.000001671972,0.1009727,0.00320383,0.000046982,0.00006608911,0.000009925134,0.000004696152,0.0001180227],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8921189,"threshold_uncertainty_score":0.3654916,"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."}}