{"id":"W4398751593","doi":"10.7910/dvn/eaxeet/wdhftj","title":"Corpus_ngram3_cleaned.csv","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":"McGill University","funders":"","keywords":"Natural language processing; Computer science","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":[0.001528976,0.004910557,0.002143325,0.006659062,0.002101307,0.003923411,0.005429366,0.003017198,0.1284233],"category_scores_gemma":[0.00800466,0.00132266,0.001838638,0.007538713,0.0009669008,0.002214529,0.003575126,0.002742701,0.1863078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001756627,"about_ca_system_score_gemma":0.003205252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02284435,"about_ca_topic_score_gemma":0.03580589,"domain_scores_codex":[0.9984797,0.0002882104,0.0001670886,0.000455583,0.0003635588,0.0002459662],"domain_scores_gemma":[0.9972671,0.0007576825,0.0001518268,0.0009663865,0.0006025432,0.0002545581],"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":[0.00006511516,0.00002671602,0.0002251961,0.0004581732,0.00002785486,0.00002350799,0.00002541296,0.0001366059,0.0002003358,0.0003802936,0.9954353,0.002995396],"study_design_scores_gemma":[0.0004795488,0.00003653607,0.001908758,0.0001749146,0.00004709029,0.0001104708,0.0001109495,0.0009641673,0.001631884,0.001536712,0.9929508,0.0000482955],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0004303326,0.0001617306,0.0002804889,0.0001216095,0.00007658462,0.00003147655,0.9927267,0.004377284,0.001793832],"genre_scores_gemma":[0.0006143626,0.0000594415,0.0007119738,0.00004004625,0.00001369234,0.000112968,0.9967775,0.000426153,0.001243951],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.8715767,"threshold_uncertainty_score":0.4296188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0167009465814043,"score_gpt":0.2633992847576551,"score_spread":0.2466983381762508,"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."}}