{"id":"W4398347418","doi":"10.7910/dvn/eaxeet/kltm0y","title":"goetheUnread_ReadMe.txt","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":"Mathematics; Computer science; Database; Statistics","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":[0.001184588,0.003880915,0.001923948,0.005577161,0.001203298,0.004579262,0.0048228,0.002750086,0.2073112],"category_scores_gemma":[0.007296334,0.0009708456,0.001706614,0.008165538,0.0007496579,0.002332561,0.00386807,0.00215431,0.3137922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001633806,"about_ca_system_score_gemma":0.002360535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0173521,"about_ca_topic_score_gemma":0.02621681,"domain_scores_codex":[0.9986979,0.0002014723,0.0001409373,0.0004045312,0.000277479,0.0002776391],"domain_scores_gemma":[0.9970301,0.0006677226,0.0002305403,0.00101265,0.000683056,0.0003757767],"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":[0.00003730655,0.00001164521,0.0001630389,0.0003110221,0.00001373844,0.000009311707,0.00001306665,0.00007123724,0.00006097016,0.0002579952,0.997906,0.001144644],"study_design_scores_gemma":[0.0002544237,0.00002266493,0.001284289,0.0002117255,0.00002132327,0.00003943935,0.00008275595,0.000346414,0.0005212602,0.001572787,0.9956158,0.00002716198],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00007704347,0.00004337376,0.00005450149,0.00006724602,0.00003232992,0.00001144073,0.9976171,0.00114556,0.0009514638],"genre_scores_gemma":[0.0002686591,0.00004167613,0.0001946419,0.00004879599,0.00001090808,0.00006843374,0.9981819,0.0002381121,0.0009468367],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7926888,"threshold_uncertainty_score":0.6935251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01801581548594115,"score_gpt":0.2721007757911034,"score_spread":0.2540849603051622,"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."}}