{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001362532,0.0002664071,0.0003555993,0.001427286,0.0003554518,0.001605385,0.0007801151,0.0001562864,0.000462079],"category_scores_gemma":[0.0002210262,0.0002251745,0.000504142,0.0005419625,0.00007950753,0.0008468218,0.00009352712,0.0004950054,0.00002324856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009840934,"about_ca_system_score_gemma":0.00008266779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005147489,"about_ca_topic_score_gemma":0.00006198321,"domain_scores_codex":[0.9976018,0.0001132324,0.000727572,0.0004845441,0.000791952,0.0002808654],"domain_scores_gemma":[0.9972453,0.0003778436,0.0006797228,0.0002598284,0.001223465,0.0002138227],"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":[0.000136319,0.0003672923,0.002113721,0.00001285335,0.001378153,0.00005384174,0.0001530131,0.000006757163,0.005572138,0.008426438,0.0007035965,0.9810759],"study_design_scores_gemma":[0.00514888,0.001932615,0.009715371,0.0005506297,0.001722387,0.0006270172,0.000201329,0.03710374,0.3406563,0.5677398,0.03229599,0.002305891],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1375898,0.00001972081,0.8563049,0.003095828,0.0007885814,0.0003658862,0.00004322981,0.0003089543,0.001483019],"genre_scores_gemma":[0.8092663,0.0001211161,0.1881485,0.001318472,0.0005750312,0.0001258148,0.0001668903,0.00002047084,0.0002573234],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.97877,"threshold_uncertainty_score":0.9994311,"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."}}