{"id":"W4401042368","doi":"10.18653/v1/2024.naacl-long.128","title":"First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Samsung; York University; Samsung Advanced Institute of Technology","keywords":"Parsing; Tragedy (event); Computer science; Natural language processing; Linguistics; Artificial intelligence; Literature; Philosophy; Art","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01858032,0.0008399253,0.001525157,0.002476979,0.004061761,0.01182329,0.002911126,0.004958698,0.01180967],"category_scores_gemma":[0.0709222,0.001531812,0.000623129,0.003398979,0.01778393,0.07509678,0.007558914,0.01296414,0.007643414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002911805,"about_ca_system_score_gemma":0.003342775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007673459,"about_ca_topic_score_gemma":0.01040831,"domain_scores_codex":[0.9934448,0.003370714,0.0003148507,0.001082268,0.001533971,0.0002533127],"domain_scores_gemma":[0.9420582,0.04205598,0.0009608478,0.009361784,0.00412217,0.001441007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003363341,0.00006810491,0.002436382,0.0004725047,0.0001087276,0.0002245591,0.004531654,0.002671948,0.0005365972,0.4767957,0.2380953,0.2737221],"study_design_scores_gemma":[0.00002531484,0.00002715788,0.0005153746,0.0003690776,0.00003608879,0.0002503368,0.001034154,0.008443809,0.0006906755,0.6918125,0.2966926,0.0001029099],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01398904,0.1225684,0.2021052,0.6030462,0.007662219,0.00006006091,0.002451319,0.004555758,0.04356172],"genre_scores_gemma":[0.4487328,0.113097,0.2286322,0.1071547,0.0227578,0.000471624,0.005246125,0.01548064,0.05842727],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01858032,"threshold_uncertainty_score":0.09826326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05173172708515712,"score_gpt":0.358601516974301,"score_spread":0.3068697898891439,"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."}}