{"id":"W1560635010","doi":"10.1023/a:1007653929870","title":"Stochastic Grammatical Inference of Text Database Structure","year":2000,"lang":"en","type":"article","venue":"Machine Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Grammar induction; Computer science; Nesting (process); Markup language; Inference; Construct (python library); Semantics (computer science); Grammar; Artificial intelligence; Natural language processing; Theoretical computer science; Programming language; XML; Rule-based machine translation; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001536593,0.0001221794,0.0001599744,0.00008007927,0.00008690701,0.0000736852,0.0007071173,0.00005212107,0.0004100142],"category_scores_gemma":[0.0003327306,0.00009858245,0.00002972036,0.0003117051,0.00004975966,0.0003142184,0.000189349,0.0004304693,0.00001577606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001335261,"about_ca_system_score_gemma":0.00002965672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008668214,"about_ca_topic_score_gemma":0.00001096693,"domain_scores_codex":[0.9990522,0.00007806964,0.0001900482,0.0002425479,0.0002425468,0.0001945756],"domain_scores_gemma":[0.9993374,0.0001353575,0.00007761598,0.0003502637,0.00004222268,0.0000570828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001896119,0.0000495278,0.001096359,0.0001260178,0.00001611835,0.00003395863,0.001260695,0.006314202,0.01207959,0.05179463,0.00006570503,0.9271442],"study_design_scores_gemma":[0.0002996453,0.0001484544,0.0004048655,0.0001741139,0.00001254947,0.00005964027,0.000008980785,0.9551142,0.006100874,0.03662026,0.0007124164,0.0003440283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04429649,0.0007839841,0.9538499,0.0002157726,0.00003158504,0.00008216453,0.000005691332,0.000452473,0.0002819761],"genre_scores_gemma":[0.7306654,0.000002634991,0.2690635,0.00005866955,0.00001820938,0.000001636101,0.00001092828,0.000006665837,0.0001723092],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9488,"threshold_uncertainty_score":0.4489368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008191670648523592,"score_gpt":0.2716978941340115,"score_spread":0.2635062234854879,"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."}}