{"id":"W1535384510","doi":"10.16995/dscn.138","title":"Corpus Linguistics beyond Google: the WebCorp Linguist’s Search Engine","year":2009,"lang":"en","type":"article","venue":"Digital Studies / Le champ numérique","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Disk formatting; Computer science; World Wide Web; Information retrieval; Search engine; Web standards; Web search engine; Web page; Web search query","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004356829,0.0003432284,0.0003636158,0.0001044222,0.000443246,0.0006395652,0.00154382,0.0001148101,0.000001021641],"category_scores_gemma":[0.00240193,0.0002403379,0.000124883,0.0006487764,0.0002180185,0.0002813224,0.000692347,0.0005328571,0.00002575917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000125853,"about_ca_system_score_gemma":0.0001413312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002349203,"about_ca_topic_score_gemma":0.00001483456,"domain_scores_codex":[0.9979812,0.00005384765,0.0003705394,0.0005565405,0.0004659936,0.000571911],"domain_scores_gemma":[0.9978127,0.000319283,0.0001341727,0.0007831564,0.0008370342,0.0001136234],"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":[0.00008699425,0.0008866041,0.0007792726,0.0002675559,0.0004413031,0.001096036,0.2565865,0.0001638031,0.001209312,0.1920093,0.0358191,0.5106542],"study_design_scores_gemma":[0.0009157133,0.0009817216,0.0001916618,0.0003715786,0.000001184512,0.0002120909,0.02127548,0.004457899,0.04520152,0.7553267,0.1692802,0.001784241],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07258514,0.1419193,0.6137052,0.04022106,0.005885833,0.002682856,0.0001330148,0.008918867,0.1139488],"genre_scores_gemma":[0.9888657,0.0003476131,0.007715849,0.00119554,0.0007670589,0.00002192433,0.00001121488,0.00002392879,0.001051153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9162806,"threshold_uncertainty_score":0.9800695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01986126175897783,"score_gpt":0.2839510981054043,"score_spread":0.2640898363464265,"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."}}