{"id":"W1926678298","doi":"","title":"A web application for filtering and annotating web speech data","year":2013,"lang":"en","type":"article","venue":"eCommons (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; McGill University; National Science Foundation","keywords":"Computer science; World Wide Web; Web application; Information retrieval","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0001353455,0.00009887271,0.0001014766,0.0001426791,0.0001529219,0.0001422514,0.001337803,0.00005240506,0.000006079144],"category_scores_gemma":[0.00003795472,0.0001067719,0.00001910439,0.0003435076,0.00003333534,0.001230391,0.001048326,0.0001049364,0.00001547354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003515999,"about_ca_system_score_gemma":0.00003714582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007661172,"about_ca_topic_score_gemma":0.00007837423,"domain_scores_codex":[0.9992329,0.00002317083,0.00008929557,0.0004339924,0.00004663603,0.0001739439],"domain_scores_gemma":[0.9989452,0.00009995948,0.00008199691,0.0007415307,0.00006717432,0.00006413236],"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":[0.00003416335,0.0002227289,0.008708925,0.0003906851,0.00009405482,0.00009570486,0.0007199013,0.0001166078,0.1565036,0.2775902,0.01763969,0.5378837],"study_design_scores_gemma":[0.0003693688,0.00004419798,0.0002144198,0.00003503795,0.00001261799,0.0000210177,0.00006912672,0.959726,0.003427925,0.02951588,0.006280011,0.0002843606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05562518,0.0001271075,0.9419678,0.0003424984,0.0000449163,0.0004020327,0.00002537994,0.0004987416,0.000966332],"genre_scores_gemma":[0.58333,0.000007070642,0.416368,0.00004943931,0.00002008947,0.000002370747,0.00001580722,0.000005918898,0.0002013062],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9596094,"threshold_uncertainty_score":0.435403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03677190477040208,"score_gpt":0.2325776897964137,"score_spread":0.1958057850260117,"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."}}