{"id":"W4312706369","doi":"10.5334/johd.88","title":"The CONLIT Dataset of Contemporary Literature","year":2022,"lang":"en","type":"article","venue":"Journal of Open Humanities Data","topic":"Narrative Theory and Analysis","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Elite; Biography; Literature; History; Art","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":[0.001838102,0.001274797,0.001358192,0.02507523,0.001648565,0.004523055,0.002536519,0.002294369,0.03962712],"category_scores_gemma":[0.0146458,0.0004839173,0.0008549555,0.02888524,0.0006272218,0.002241835,0.003358843,0.001586995,0.04487808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002188561,"about_ca_system_score_gemma":0.004117466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01110686,"about_ca_topic_score_gemma":0.03207958,"domain_scores_codex":[0.9971751,0.000445496,0.0005753104,0.0005957326,0.0009179002,0.0002904288],"domain_scores_gemma":[0.9887495,0.00418743,0.001687154,0.001471604,0.002891211,0.001013128],"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":[0.000127195,0.0001060175,0.006906373,0.003140166,0.00006084327,0.0002565262,0.0003044465,0.0003928451,0.0005432754,0.003224214,0.9661364,0.01880166],"study_design_scores_gemma":[0.00009657253,0.0000234851,0.009474726,0.0007281545,0.00003414193,0.000249328,0.0004726537,0.0004517656,0.0003460702,0.000988518,0.9871047,0.0000298817],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002238865,0.001124955,0.0002177619,0.0002484567,0.00005692785,0.00005779086,0.9924901,0.0002479977,0.003317005],"genre_scores_gemma":[0.001761138,0.0003046152,0.0007418054,0.00008508625,0.00002769167,0.000188517,0.9959629,0.00003712007,0.0008910757],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03962712,"threshold_uncertainty_score":0.132566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2284273115647129,"score_gpt":0.3408972242918083,"score_spread":0.1124699127270954,"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."}}