{"id":"W4398708237","doi":"10.7910/dvn/eaxeet/jm9gdx","title":"Corpus_ngram3.tab","year":2019,"lang":"fr","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; Linguistics; Philosophy","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":[0.001120291,0.005853125,0.002304851,0.007353522,0.001954897,0.0036175,0.005376866,0.003603836,0.166929],"category_scores_gemma":[0.00669894,0.001488925,0.001894002,0.007897997,0.000820907,0.002658302,0.002758321,0.002594894,0.1958439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002022366,"about_ca_system_score_gemma":0.002611069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02391777,"about_ca_topic_score_gemma":0.03102315,"domain_scores_codex":[0.9986693,0.0002165037,0.0001549874,0.0004492779,0.000300896,0.000209131],"domain_scores_gemma":[0.99754,0.000796937,0.0001518019,0.0007664332,0.0005073201,0.0002374573],"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":[0.00006940034,0.00003003813,0.0002029132,0.0005335853,0.00002353781,0.00002257024,0.00001913176,0.0001392151,0.0002247855,0.0002967632,0.9954347,0.003003435],"study_design_scores_gemma":[0.0006365343,0.00005749509,0.001810611,0.0001965114,0.00004876432,0.0001470569,0.0001076876,0.001286707,0.001922584,0.001331528,0.9923998,0.0000547706],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0003324158,0.0001237331,0.00017788,0.0001002672,0.00005166571,0.00002860406,0.9942221,0.003501185,0.001462081],"genre_scores_gemma":[0.0005985424,0.00005087566,0.00056571,0.00004133386,0.00001350329,0.0001029212,0.9972293,0.0003298257,0.001067986],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.8330711,"threshold_uncertainty_score":0.558433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02778046832370235,"score_gpt":0.2750121536315191,"score_spread":0.2472316853078168,"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."}}