{"id":"W2293026843","doi":"10.3115/v1/n15-1115","title":"Encoding World Knowledge in the Evaluation of Local Coherence","year":2015,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Zhàng; Coherence (philosophical gambling strategy); Encoding (memory); Computer science; Computational linguistics; Linguistics; Artificial intelligence; Natural language processing; Cognitive science; China; History; Philosophy; Psychology; Physics; Quantum mechanics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002562801,0.00003407536,0.00005005202,0.00006069564,0.00001106495,0.00002144086,0.0005030081,0.00001226798,0.00001140914],"category_scores_gemma":[0.00004346393,0.00002240487,0.00001073111,0.0003344031,0.00001699545,0.0001554462,0.00008253776,0.00005145431,0.00001806091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004742319,"about_ca_system_score_gemma":0.0001476355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009161893,"about_ca_topic_score_gemma":0.0006787049,"domain_scores_codex":[0.9991926,0.0001558562,0.0001270505,0.0001135256,0.0003322552,0.00007872199],"domain_scores_gemma":[0.999467,0.00007588437,0.00002709756,0.0002735576,0.000136929,0.00001951206],"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":[0.000001953963,0.00008687063,0.002646619,0.000008413944,0.000002917528,0.000001276959,0.01174753,0.02211476,0.0001403151,0.3768759,0.001297264,0.5850762],"study_design_scores_gemma":[0.0001906434,0.00001012774,0.001035881,0.00001219291,0.000001704279,0.000001105235,0.0004613167,0.9880124,0.0006574334,0.009360426,0.0002236033,0.00003320459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04645395,0.0001326358,0.8468799,0.0002903851,0.0001364789,0.0001051732,3.17769e-8,0.00001625487,0.1059852],"genre_scores_gemma":[0.9906459,2.292458e-7,0.009119073,0.00005909579,0.00001830997,0.00000838178,9.253567e-8,8.864708e-7,0.0001480421],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9658976,"threshold_uncertainty_score":0.09347226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.229125963995789,"score_gpt":0.369885533238639,"score_spread":0.1407595692428501,"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."}}