{"id":"W3194884147","doi":"10.1145/3447548.3470791","title":"Language Scaling","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Scaling; Taxonomy (biology); Pragmatics; Natural language processing; Natural language; Artificial intelligence; Data science; 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":[0.00004978498,0.00002290867,0.00003024804,0.00001012762,0.00001993714,0.00005553544,0.0001714741,0.00001120444,0.00007670915],"category_scores_gemma":[0.00001640359,0.00002058685,0.00001557428,0.00008524326,0.000002126888,0.00009562315,0.0001282864,0.00002820871,0.00007200598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005299822,"about_ca_system_score_gemma":0.00002233002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001226409,"about_ca_topic_score_gemma":0.000005277462,"domain_scores_codex":[0.9996756,0.000009661451,0.00004707852,0.0001238685,0.0000682106,0.00007562225],"domain_scores_gemma":[0.9996688,0.00001365929,0.000005630479,0.0002710433,0.00001757331,0.00002330385],"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":[1.59252e-7,0.0000204643,0.0004103946,0.000007092439,0.000005872638,0.0002057095,0.00216199,0.0004721312,0.0136252,0.638468,0.0006064092,0.3440166],"study_design_scores_gemma":[0.0002070194,0.000004673147,0.0006553572,0.00001347459,0.000001740674,0.00006951483,0.0004066825,0.8585963,0.1261747,0.006374811,0.007303966,0.0001917384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03781373,0.0001225074,0.9236378,0.0008221899,0.0001285989,0.000007731153,4.051681e-8,0.0001137611,0.03735361],"genre_scores_gemma":[0.6798601,0.000001239682,0.3162698,0.0007450144,0.00003892865,5.304241e-7,2.171151e-7,0.00000133452,0.003082886],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8581242,"threshold_uncertainty_score":0.09255152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01814573464516618,"score_gpt":0.2556594184063437,"score_spread":0.2375136837611775,"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."}}