{"id":"W2979474259","doi":"10.22148/001c.13147","title":"NovelTM Datasets for English-Language Fiction, 1700-2009","year":2020,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"English language; Computer science; Non-fiction; Resilience (materials science); Fragility; History; Linguistics; Literature; Art; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001407966,0.0001322877,0.0002479926,0.00004422431,0.0001903499,0.0007363522,0.0002566087,0.00003149056,0.0007397504],"category_scores_gemma":[0.0003013466,0.00008750244,0.0002374618,0.00003861452,0.00008070723,0.001175287,0.00002877543,0.0002096326,0.00001332607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002667174,"about_ca_system_score_gemma":0.00002738194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006058723,"about_ca_topic_score_gemma":0.00003945186,"domain_scores_codex":[0.999015,0.00001314211,0.0004520359,0.00009495837,0.0002518944,0.0001729216],"domain_scores_gemma":[0.9988045,0.0000550131,0.0003005854,0.00007950664,0.0006070635,0.0001533053],"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":[0.0001726288,0.0001097899,0.0000347509,0.00008681264,0.0002468129,0.00004216115,0.1139312,0.0001209023,0.000116434,0.06238067,0.8211472,0.00161064],"study_design_scores_gemma":[0.0005261612,0.0003828309,0.00001570277,0.00002939787,0.0001180291,0.00001193488,0.04807862,0.0002390538,0.00009164299,0.0003934756,0.9499643,0.0001488402],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7058294,0.00361364,0.0007659327,0.01116564,0.005655103,0.0007503128,0.007693315,0.0002152811,0.2643114],"genre_scores_gemma":[0.9878774,0.00003071578,0.0001609492,0.001757169,0.005481763,9.614287e-7,0.000169152,0.0000143099,0.004507555],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.282048,"threshold_uncertainty_score":0.8099748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07261985779052788,"score_gpt":0.2707456352499021,"score_spread":0.1981257774593742,"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."}}