{"id":"W2106394101","doi":"10.7202/029796ar","title":"The Unit of Translation: Statistics Speak","year":2009,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Macquarie University","keywords":"Sentence; Context (archaeology); Linguistics; Subject (documents); Identification (biology); Computer science; Natural language processing; Psychology; History; Philosophy; Library science","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":[0.0006633634,0.0001061482,0.000169916,0.00007590871,0.0002598907,0.000254289,0.0009854456,0.00002893643,0.000009352424],"category_scores_gemma":[0.00009188753,0.00006152508,0.00009730508,0.0003694792,0.0001085888,0.0004628667,0.00001438368,0.0002779834,0.000001584369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001314527,"about_ca_system_score_gemma":0.00005320075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000236251,"about_ca_topic_score_gemma":0.000003349888,"domain_scores_codex":[0.9989303,0.0001322113,0.0003064844,0.0001102198,0.0003305794,0.0001902384],"domain_scores_gemma":[0.9991324,0.0001571305,0.0001853823,0.0002578158,0.00019745,0.00006983947],"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":[0.000005906197,0.00001911895,0.00001120431,0.000004925068,0.00005645246,0.00002154613,0.0001617932,0.000009070179,0.001585297,0.1360201,0.000342471,0.8617621],"study_design_scores_gemma":[0.0001505044,0.0002033774,0.0009284187,0.00002154891,0.0001302293,0.0005238894,0.000007922519,0.0008305422,0.01712398,0.9629741,0.01697342,0.0001321068],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005264953,0.08623411,0.9112756,0.001596453,0.0001323203,0.0000485376,0.000002615745,0.0000632895,0.0001205752],"genre_scores_gemma":[0.05006795,0.003808158,0.945794,0.0001266736,0.0000661733,6.872664e-7,5.886311e-7,0.000005737071,0.0001300142],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.86163,"threshold_uncertainty_score":0.250892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04371525780886655,"score_gpt":0.3000459238541289,"score_spread":0.2563306660452624,"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."}}