{"id":"W6893716360","doi":"10.5281/zenodo.4290719","title":"SSHOC Considerations for the Vocabulary Platforms - CLARIN: main requirements and best practices","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canarie","funders":"European Commission","keywords":"Best practice; Vocabulary","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":[0.05659317,0.001468614,0.002041881,0.004705687,0.006239145,0.02679384,0.007703801,0.01072207,0.1172869],"category_scores_gemma":[0.1286058,0.002221646,0.002034173,0.003659338,0.004946408,0.04717555,0.01286716,0.00878634,0.1150585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005025297,"about_ca_system_score_gemma":0.01591196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01938589,"about_ca_topic_score_gemma":0.01946764,"domain_scores_codex":[0.9608039,0.01193663,0.005202903,0.003299313,0.01483044,0.003926721],"domain_scores_gemma":[0.7951201,0.04636569,0.004936082,0.05016638,0.08960272,0.01380914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008597472,0.0003588969,0.001948915,0.001425711,0.00003899327,0.0004673368,0.003676739,0.0008269764,0.014141,0.1711666,0.6218398,0.1832492],"study_design_scores_gemma":[0.00009929674,0.0001532189,0.0009906145,0.001337799,0.00003261388,0.000413195,0.002239191,0.002330589,0.004519557,0.03176986,0.9559973,0.0001168795],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.01546952,0.004180712,0.326279,0.2013431,0.0154173,0.005932715,0.009598533,0.03290184,0.3888773],"genre_scores_gemma":[0.07982478,0.003212701,0.4700631,0.02780612,0.006513156,0.005602921,0.02782094,0.03194509,0.3472112],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1172869,"threshold_uncertainty_score":0.3923637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1291573733617981,"score_gpt":0.3159389149387414,"score_spread":0.1867815415769433,"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."}}