{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001664279,0.00005449985,0.0001072603,0.00005900884,0.0000752725,0.00002667802,0.0002138378,0.00003693499,0.001265857],"category_scores_gemma":[0.00007149528,0.00003505586,0.0001037097,0.0003265927,0.00004602294,0.0001309954,0.00001934054,0.0001343677,0.00001634336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008073857,"about_ca_system_score_gemma":0.0002212762,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007897408,"about_ca_topic_score_gemma":0.01463761,"domain_scores_codex":[0.998982,0.0002800555,0.0001583845,0.0001396496,0.0003082745,0.0001316308],"domain_scores_gemma":[0.9992974,0.00051995,0.00002516043,0.0001035716,0.00001985535,0.00003403345],"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":[0.000004175322,0.00006563823,0.00007476656,0.00001791092,0.00003375782,0.00002501711,0.3380134,0.001199618,0.00002291602,0.6024999,0.02531546,0.03272749],"study_design_scores_gemma":[0.0003286472,0.00003297472,0.0024434,0.0001023841,0.00009602036,0.000002346634,0.04024004,0.09395896,0.00003483723,0.2084272,0.6540411,0.0002921307],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1252279,0.02566143,0.09457505,0.03353413,0.000721026,0.0004705534,0.00001201661,0.000254698,0.7195432],"genre_scores_gemma":[0.9800448,0.00009272851,0.002083301,0.0003189841,0.0001525677,0.00000415838,0.000002801545,0.000004281131,0.01729639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8548169,"threshold_uncertainty_score":0.9996471,"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."}}