{"id":"W6957386035","doi":"10.60692/kk5ze-cry69","title":"Semantics of the Unwritten: The Effect of End of Paragraph and Sequence Tokens on Text Generation with GPT2","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Paragraph; Semantics (computer science); Sequence (biology); Code (set theory); Character (mathematics); Quality (philosophy)","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":[0.002766851,0.001500341,0.0005795587,0.000661392,0.0005174357,0.001228773,0.001020882,0.00103314,0.003637716],"category_scores_gemma":[0.01638507,0.0004992149,0.0004911232,0.0005108955,0.0005419354,0.001857973,0.001345106,0.002066749,0.001656823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000611165,"about_ca_system_score_gemma":0.0008678867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003604821,"about_ca_topic_score_gemma":0.00587649,"domain_scores_codex":[0.9984263,0.0007560492,0.0001111115,0.0004328049,0.0001740881,0.00009951721],"domain_scores_gemma":[0.9895453,0.008173813,0.0003304081,0.0009762069,0.0007208523,0.0002534243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002344462,0.0005457129,0.02376968,0.001048797,0.0002582177,0.001151791,0.001309389,0.2035487,0.09241459,0.002415704,0.01968826,0.6515046],"study_design_scores_gemma":[0.0003131583,0.0008016845,0.008511089,0.00009407812,0.0002045024,0.0005394485,0.0003622346,0.8924349,0.08458031,0.003931256,0.008152777,0.00007454217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7688987,0.002362247,0.1877791,0.00124575,0.0006699676,0.0004225254,0.002434837,0.02292557,0.01326137],"genre_scores_gemma":[0.9241624,0.0002415969,0.06518555,0.000367609,0.00007279078,0.000288664,0.004313277,0.001580797,0.003787316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003637716,"threshold_uncertainty_score":0.01463264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02798407300147498,"score_gpt":0.2024178508583835,"score_spread":0.1744337778569086,"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."}}