{"id":"W4409678925","doi":"10.22148/001c.128010","title":"The “Mapping German fiction in translation” dataset: Data collection, scope, and data quality","year":2025,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Scope (computer science); German; Computer science; Translation (biology); Data quality; Quality (philosophy); Data collection; Information retrieval; Data science; History; Statistics; Engineering; Operations management; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001665168,0.00007890882,0.0001510219,0.0001219451,0.000231511,0.0004255852,0.002042356,0.00004320404,8.853096e-7],"category_scores_gemma":[0.0003797809,0.00004635326,0.00001604295,0.000795803,0.00005289254,0.002107254,0.000523468,0.0002832629,2.485465e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004536223,"about_ca_system_score_gemma":0.0001140278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006658443,"about_ca_topic_score_gemma":0.0002186094,"domain_scores_codex":[0.9988386,0.0001089877,0.0005085457,0.0002015347,0.0002336047,0.0001087149],"domain_scores_gemma":[0.9985343,0.0001819685,0.0002968801,0.0007666526,0.0001893147,0.00003089375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001130875,0.0001597442,0.002817828,0.0002174746,0.0003131308,0.00005260783,0.002529097,0.0001202369,0.003924206,0.01799916,0.5959398,0.3758136],"study_design_scores_gemma":[0.001448549,0.00009060881,0.00899726,0.0007590202,0.0001464103,0.0002776452,0.0008072426,0.5656325,0.00134736,0.02724032,0.3927546,0.0004984748],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005491335,0.03145424,0.9347625,0.02685158,0.0005973803,0.0002480942,0.0001822023,0.00007743648,0.0003351955],"genre_scores_gemma":[0.3826688,0.006791061,0.6076771,0.001171676,0.0003192507,0.00000192014,0.0007243883,0.00001105361,0.00063475],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5655123,"threshold_uncertainty_score":0.4103928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1018037993760922,"score_gpt":0.4145446143603592,"score_spread":0.312740814984267,"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."}}