{"id":"W2296700935","doi":"","title":"Grammar Inference for Web Documents","year":2011,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"XML validation; Computer science; Presentational and representational acting; Document Structure Description; XML Schema Editor; Efficient XML Interchange; Streaming XML; XML Schema (W3C); Information retrieval; SGML; XML Encryption; XML; XML Signature; Programming language; Natural language processing; World Wide Web; Linguistics","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":[0.0001304411,0.00005452553,0.00006956806,0.00004999527,0.0000508208,0.00007064927,0.0006432074,0.00001874191,0.00008941454],"category_scores_gemma":[0.00003532214,0.00004239739,0.0000423706,0.0001516337,0.00001216439,0.0003773242,0.0001399993,0.00002299644,0.0001263048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004895562,"about_ca_system_score_gemma":0.00002749392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009860789,"about_ca_topic_score_gemma":0.00002139097,"domain_scores_codex":[0.9994768,0.000009640166,0.00009244901,0.000195989,0.00007931115,0.0001458428],"domain_scores_gemma":[0.999467,0.00003452496,0.00002758581,0.0003832635,0.00003593198,0.00005165795],"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":[0.000007646411,0.0001868113,0.01664406,0.00001828331,0.0001107174,0.000007677996,0.001272127,0.000003295244,0.001251875,0.5698056,0.02347368,0.3872183],"study_design_scores_gemma":[0.002711164,0.000886297,0.01989731,0.00006872322,0.0001352924,0.00001307752,0.0002411697,0.5128822,0.03025815,0.1785717,0.2525516,0.001783313],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005325657,0.000007868924,0.9787247,0.000110429,0.00009400886,0.0000414761,0.000003185399,0.000115801,0.01557694],"genre_scores_gemma":[0.7342232,0.000003594043,0.2638049,0.0001845564,0.00001475346,0.00001155164,0.000003606127,0.000002122526,0.001751691],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7288976,"threshold_uncertainty_score":0.1728915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04948157682302046,"score_gpt":0.2802402359717129,"score_spread":0.2307586591486924,"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."}}