{"id":"W3100889051","doi":"10.48550/arxiv.2011.05723","title":"CalibreNet: Calibration Networks for Multilingual Sequence Labeling","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"People's Government of Jilin Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Benchmark (surveying); Sequence labeling; Task (project management); Sequence (biology); Named-entity recognition; Phrase; Natural language processing; Artificial intelligence; Obstacle; Boundary (topology); Resource (disambiguation); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002133527,0.002310513,0.001081079,0.002086717,0.001230547,0.001373043,0.003376425,0.002986632,0.007507518],"category_scores_gemma":[0.009836225,0.001002247,0.00138311,0.002037374,0.001025938,0.004913172,0.003517503,0.004204549,0.005728864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001262391,"about_ca_system_score_gemma":0.00182924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007122373,"about_ca_topic_score_gemma":0.01348431,"domain_scores_codex":[0.9983515,0.0004714679,0.00006461141,0.0007695248,0.000207185,0.0001356873],"domain_scores_gemma":[0.9968311,0.001445631,0.0001984648,0.0007692858,0.0006175705,0.0001379119],"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":[0.0004603384,0.0003332334,0.003319406,0.0003696908,0.0002125583,0.0003763465,0.0007838989,0.1579281,0.01495332,0.01932181,0.05421987,0.7477214],"study_design_scores_gemma":[0.00003121747,0.00007123704,0.0004737119,0.00005456971,0.0000325745,0.0001048024,0.000133482,0.9489894,0.006105681,0.03208698,0.0118811,0.00003516699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01277017,0.0007105884,0.9612263,0.000382008,0.0001566145,0.0001776616,0.001724416,0.01910316,0.003748972],"genre_scores_gemma":[0.2456741,0.000762455,0.7093514,0.001185986,0.000282191,0.001053819,0.02379536,0.002910114,0.01498459],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007507518,"threshold_uncertainty_score":0.02511519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1565945791399868,"score_gpt":0.2257898305062738,"score_spread":0.06919525136628696,"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."}}