{"id":"W1977202248","doi":"10.1007/s10032-010-0118-4","title":"Grammar-based techniques for creating ground-truthed sketch corpora","year":2010,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sketch; Computer science; Natural language processing; Template; Artificial intelligence; Grammar; Sketch recognition; Annotation; Domain (mathematical analysis); Matching (statistics); Ground truth; Programming language; Linguistics; Algorithm","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":[0.003507208,0.002287152,0.001763391,0.007294407,0.001738445,0.00445846,0.004075534,0.002415252,0.03031227],"category_scores_gemma":[0.02207958,0.00186349,0.00224466,0.00506553,0.001608358,0.005321342,0.004006347,0.003968154,0.01364183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001283363,"about_ca_system_score_gemma":0.002354125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003274394,"about_ca_topic_score_gemma":0.007371611,"domain_scores_codex":[0.9959002,0.0008503592,0.000628454,0.001347268,0.001082173,0.0001914537],"domain_scores_gemma":[0.9822873,0.00796724,0.0008118307,0.004775376,0.003907377,0.0002509459],"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":[0.0002848452,0.0002562991,0.002509868,0.001918648,0.0002041836,0.001013527,0.00114043,0.0378093,0.05047311,0.02896008,0.04396768,0.8314621],"study_design_scores_gemma":[0.00027769,0.0003703806,0.004830775,0.0004447158,0.0003098024,0.002423982,0.001282386,0.7119194,0.08543219,0.06740991,0.1250472,0.0002516443],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01348895,0.00043284,0.9394773,0.0001926976,0.0002468286,0.0006504088,0.007850831,0.03302616,0.004633954],"genre_scores_gemma":[0.07027875,0.0003765993,0.878185,0.0001018996,0.0001028207,0.0009050324,0.04155602,0.00520091,0.003292924],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03031227,"threshold_uncertainty_score":0.1014047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01460440879270711,"score_gpt":0.2906842237893361,"score_spread":0.276079814996629,"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."}}