{"id":"W4411119199","doi":"10.18653/v1/2025.wnu-1.1","title":"NarraDetect: An annotated dataset for the task of narrative detection","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Task (project management); Narrative; Natural language processing; Artificial intelligence; Information retrieval; Engineering; Art; Literature","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009771422,0.001708399,0.0006316716,0.003730684,0.001443207,0.001382397,0.001961953,0.002462467,0.01208302],"category_scores_gemma":[0.006670268,0.0003831771,0.0009340148,0.003283518,0.0006782752,0.002306379,0.001874666,0.00169535,0.01198208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001276282,"about_ca_system_score_gemma":0.001393905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0128894,"about_ca_topic_score_gemma":0.04591913,"domain_scores_codex":[0.9987784,0.0003232497,0.0001730027,0.0003846997,0.0002599444,0.00008072554],"domain_scores_gemma":[0.996376,0.001577058,0.000359557,0.0007548179,0.0006293237,0.0003033251],"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":[0.0004596685,0.0002969083,0.005465348,0.003596046,0.0001212285,0.001229349,0.00176996,0.002026375,0.008067206,0.002924754,0.9213638,0.05267933],"study_design_scores_gemma":[0.0002097285,0.0001558145,0.02484882,0.000560151,0.00008761734,0.001648592,0.001917922,0.01153188,0.006948177,0.00270779,0.9492416,0.0001419703],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02929295,0.001926784,0.006871371,0.0007417557,0.0004757009,0.0003747867,0.9410764,0.008106065,0.01113424],"genre_scores_gemma":[0.01554584,0.0002728577,0.01178405,0.0001348341,0.00006108512,0.0004238425,0.9677528,0.0003073063,0.003717317],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0128894,"threshold_uncertainty_score":0.04042172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02299859514699156,"score_gpt":0.2958161180799125,"score_spread":0.272817522932921,"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."}}