{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002067756,0.0001216616,0.0001347671,0.00007838255,0.0002156179,0.0002760153,0.0008930978,0.00003811389,0.00002200106],"category_scores_gemma":[0.00001187153,0.00009685473,0.00004186265,0.0001569844,0.00002313012,0.0008224086,0.000678724,0.00007518256,0.00004113155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004667411,"about_ca_system_score_gemma":0.00004135288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001378401,"about_ca_topic_score_gemma":0.00002927729,"domain_scores_codex":[0.9988773,0.00003176258,0.0002078815,0.0003053881,0.0003074559,0.0002702145],"domain_scores_gemma":[0.9989911,0.00005865367,0.00006928665,0.0007413491,0.00002740337,0.0001121977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003510739,0.00001756119,0.000006159176,0.00001250346,0.00001204843,0.000008661142,0.0001664976,0.004915731,0.0001331045,0.9778816,0.001685247,0.01515739],"study_design_scores_gemma":[0.000490991,0.00002685772,0.000006992954,0.00009308079,0.00000631844,0.00005014911,0.0005055442,0.9908932,0.0001279196,0.006720269,0.0009020223,0.0001765807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006422093,0.0001157491,0.9969528,0.0004001244,0.0003741432,0.000133499,0.00000229944,0.000258987,0.001120224],"genre_scores_gemma":[0.7829921,9.432945e-7,0.2166292,0.0001397059,0.0001040005,0.000002900247,0.000001278006,0.000006379504,0.0001235033],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9859775,"threshold_uncertainty_score":0.3949621,"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."}}