{"id":"W2997103344","doi":"10.48550/arxiv.1912.13082","title":"The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Automatic summarization; Paragraph; Natural language processing; Artificial intelligence; Set (abstract data type); Reading comprehension; Construct (python library); Exploit; Reading (process); Comprehension; Sentence; Exposition (narrative); Linguistics; World Wide Web; Literature; Art; Programming language","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":[0.0007547138,0.00127006,0.0005643666,0.00346335,0.001344903,0.001094366,0.001410758,0.00188241,0.01431604],"category_scores_gemma":[0.008480022,0.0003318634,0.0006861133,0.003907725,0.000761554,0.00182023,0.002026998,0.001263856,0.008592331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007182152,"about_ca_system_score_gemma":0.001203126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009326194,"about_ca_topic_score_gemma":0.02296783,"domain_scores_codex":[0.998947,0.0003561972,0.0001120563,0.0002531884,0.0002574685,0.00007410611],"domain_scores_gemma":[0.9966569,0.001844154,0.0002109063,0.0004509701,0.0006173,0.0002197033],"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":[0.000693859,0.0004710791,0.007552605,0.005149332,0.0001671302,0.001837826,0.003726103,0.003147255,0.008806587,0.004804012,0.8136317,0.1500126],"study_design_scores_gemma":[0.0004311272,0.0002484925,0.04176983,0.0005297911,0.0001163969,0.001813918,0.004015024,0.01371513,0.01022066,0.007465048,0.919533,0.0001414944],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1216943,0.004690554,0.01503675,0.002137636,0.0005311516,0.0008962261,0.8251634,0.007425357,0.02242464],"genre_scores_gemma":[0.05919181,0.0006554689,0.02204584,0.0001989175,0.0001268072,0.001150005,0.9099254,0.0004675693,0.006238087],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01431604,"threshold_uncertainty_score":0.04789197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06948629363307242,"score_gpt":0.1862907546288985,"score_spread":0.1168044609958261,"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."}}