{"id":"W4398288000","doi":"10.7910/dvn/66hucd/cbummy","title":"metadata.xml","year":2019,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Metadata; Natural language processing; XML; Artificial intelligence; Information retrieval; World Wide Web","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001806874,0.004762641,0.002258686,0.01186093,0.001677897,0.005730662,0.004586475,0.002713564,0.2253857],"category_scores_gemma":[0.01033916,0.001376405,0.001607841,0.01444396,0.0008501787,0.004067915,0.004576596,0.002715074,0.3031872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002079706,"about_ca_system_score_gemma":0.004212871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01781427,"about_ca_topic_score_gemma":0.01793122,"domain_scores_codex":[0.9978778,0.0003255583,0.0003389472,0.0005896825,0.00056507,0.0003029552],"domain_scores_gemma":[0.9960448,0.0007086199,0.0002950884,0.001616602,0.0007521619,0.0005828137],"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":[0.00005638377,0.00002535373,0.0002563549,0.0005021284,0.00001707264,0.00001525202,0.00002819432,0.00009747,0.0002186213,0.001206593,0.9929391,0.004637432],"study_design_scores_gemma":[0.0001308655,0.00002246171,0.0008600733,0.0002238886,0.00001836827,0.00005010937,0.00007269229,0.0005166264,0.0009129576,0.002442711,0.9947237,0.00002559612],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001336338,0.00008660736,0.0002940024,0.0001443654,0.00006508372,0.00002903613,0.9925079,0.004312363,0.002427066],"genre_scores_gemma":[0.0004175171,0.0001065722,0.000586151,0.00007862646,0.00001378031,0.0000616889,0.996636,0.0006742511,0.001425446],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7746143,"threshold_uncertainty_score":0.7539903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0189639221150926,"score_gpt":0.2698429114328492,"score_spread":0.2508789893177566,"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."}}