{"id":"W4409637115","doi":"10.1007/978-3-031-90167-6_16","title":"Future Sight: Fine-Tuning Language Models for Dynamic Story Generation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Sight; Programming language; Astronomy; Physics","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":[0.001215251,0.001268854,0.0008871104,0.0006178375,0.0004664277,0.002030064,0.003036116,0.001699129,0.02298292],"category_scores_gemma":[0.006015826,0.0008544661,0.001086006,0.0004745204,0.0004947329,0.004722868,0.00222532,0.002429304,0.009167928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008411955,"about_ca_system_score_gemma":0.0008112951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004048639,"about_ca_topic_score_gemma":0.007047596,"domain_scores_codex":[0.99928,0.0001985613,0.00004400491,0.0002685569,0.0001421863,0.00006670759],"domain_scores_gemma":[0.9982262,0.001018534,0.0000537461,0.0003429381,0.0002479024,0.0001106031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001037413,0.0003835513,0.001138214,0.0004227564,0.0001687901,0.0002032778,0.0004569487,0.1044974,0.02924425,0.02143785,0.07782082,0.7631888],"study_design_scores_gemma":[0.00007354032,0.00004849827,0.0001106147,0.00001506968,0.00003035807,0.00005626585,0.00006579838,0.9677559,0.007393009,0.01532398,0.009107485,0.00001941705],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01292633,0.000520101,0.9177709,0.000392076,0.0003778632,0.0001252348,0.001362909,0.06142439,0.005100232],"genre_scores_gemma":[0.2758053,0.0004083816,0.694279,0.0005408991,0.0002027329,0.0003804547,0.006124069,0.007149581,0.01510968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02298292,"threshold_uncertainty_score":0.07688552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01860741596930173,"score_gpt":0.2512150235771715,"score_spread":0.2326076076078698,"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."}}