{"id":"W2160050794","doi":"10.1109/icdar.2005.93","title":"Document understanding system using stochastic context-free grammars","year":2005,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Natural language processing; Parsing; Artificial intelligence; Context-free grammar; Rule-based machine translation; Context (archaeology); Grammar; Document processing; Regular expression; Block (permutation group theory); Character (mathematics); 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":[0.0009571493,0.0005723679,0.0009418807,0.001027742,0.0006319917,0.001522619,0.001440269,0.001429901,0.003798317],"category_scores_gemma":[0.00364269,0.0004330686,0.001025232,0.0008004168,0.0004645461,0.002457737,0.00102851,0.001169191,0.001979612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009290875,"about_ca_system_score_gemma":0.00126212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005353516,"about_ca_topic_score_gemma":0.004397523,"domain_scores_codex":[0.9992687,0.0001337651,0.00007135255,0.0002208057,0.000258725,0.0000466323],"domain_scores_gemma":[0.9986732,0.0006680526,0.00008260543,0.0002619563,0.000268955,0.00004521128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004392967,0.0002635776,0.00200164,0.0003643252,0.0001724415,0.001010405,0.0008213493,0.2570948,0.03631735,0.08222274,0.02907374,0.5902182],"study_design_scores_gemma":[0.00005052953,0.00004285953,0.0002443797,0.00002432866,0.00004112518,0.0002203863,0.0000443612,0.9307047,0.01376108,0.03798224,0.01684252,0.00004161241],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01311102,0.000171439,0.9588426,0.0002152246,0.00003494837,0.00008639244,0.0006198866,0.02502248,0.001896057],"genre_scores_gemma":[0.2039639,0.0003441076,0.7862054,0.0002507927,0.00006443741,0.0002248049,0.002866985,0.001268671,0.004811],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005353516,"threshold_uncertainty_score":0.01270658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04866331483306063,"score_gpt":0.2597707139215462,"score_spread":0.2111073990884855,"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."}}