{"id":"W2964227218","doi":"10.33011/computel.v2i.437","title":"Towards a General-Purpose Linguistic Annotation Backend","year":2019,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"National Science Foundation","keywords":"Computer science; Documentation; Annotation; Natural language processing; Upload; Transcription (linguistics); Process (computing); Artificial intelligence; Natural language; Linguistics; World Wide Web; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004113893,0.0025534,0.001966397,0.002291038,0.001676971,0.009395057,0.00585702,0.002656582,0.02842044],"category_scores_gemma":[0.01110468,0.001785986,0.001920755,0.002032697,0.001235613,0.007935234,0.006993513,0.006179754,0.03751357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001628315,"about_ca_system_score_gemma":0.002119328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004864386,"about_ca_topic_score_gemma":0.005299547,"domain_scores_codex":[0.9973557,0.000327366,0.0002322298,0.000805807,0.0009864417,0.0002925174],"domain_scores_gemma":[0.9917462,0.001680248,0.0002354463,0.003346497,0.002595043,0.0003964684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002352205,0.0007312862,0.00307569,0.001098947,0.0002622862,0.001442962,0.00187037,0.008854385,0.08730184,0.03617347,0.2680476,0.588789],"study_design_scores_gemma":[0.0002685811,0.0003758268,0.002294685,0.0005093007,0.0002215129,0.0009367291,0.0008311059,0.2680045,0.2308281,0.06871634,0.4266862,0.0003271237],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004835037,0.0002320936,0.8069847,0.0006209088,0.0005885291,0.0003489932,0.0038756,0.1748613,0.00765289],"genre_scores_gemma":[0.07723614,0.0004809017,0.8181943,0.002525079,0.0005609943,0.001001841,0.03766362,0.02627282,0.03606421],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02842044,"threshold_uncertainty_score":0.09507585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009956162096114869,"score_gpt":0.273645230707116,"score_spread":0.2636890686110012,"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."}}