{"id":"W2966345719","doi":"10.48550/arxiv.1804.08053","title":"Learning Sentence Embeddings for Coherence Modelling and Beyond","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Coherence (philosophical gambling strategy); Heuristics; Sentence; Artificial intelligence; Structuring; Embedding; Natural language processing; Task (project management)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003443345,0.000272166,0.0002861595,0.0001569886,0.0002793822,0.000199616,0.001223557,0.0002324921,0.00000573468],"category_scores_gemma":[0.00004317453,0.0003304397,0.000110855,0.0002010561,0.0001196201,0.0004162438,0.001882861,0.0004813593,0.00001286468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009204459,"about_ca_system_score_gemma":0.000116373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008175564,"about_ca_topic_score_gemma":0.000007118235,"domain_scores_codex":[0.9979452,0.00005951628,0.0001869986,0.001339544,0.0000855298,0.000383185],"domain_scores_gemma":[0.9985133,0.0001481706,0.0002311185,0.0007136505,0.0002421296,0.0001515944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001252928,0.00001458494,0.0009677112,0.00009964502,0.00003111257,0.00002538286,0.0007386587,0.940617,0.00002838902,0.05635589,0.0000511945,0.001057912],"study_design_scores_gemma":[0.0002289943,0.00005452335,0.00001515624,0.00009605923,0.00002808513,0.000004173309,0.0001094051,0.9214745,0.00008729351,0.07733548,0.0002432669,0.0003231085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2612892,0.00004615502,0.737156,0.00005585983,0.0002999255,0.0002413033,0.000003311398,0.0001732081,0.0007350353],"genre_scores_gemma":[0.928707,0.00009394086,0.06971838,0.00007277192,0.00009889581,0.000001893444,0.000004443928,0.00001629177,0.001286367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6674377,"threshold_uncertainty_score":0.9999148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0829964850624605,"score_gpt":0.2002490946187492,"score_spread":0.1172526095562887,"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."}}