{"id":"W2946869570","doi":"10.48550/arxiv.1905.11912","title":"A Cross-Domain Transferable Neural Coherence Model","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Discriminative model; Coherence (philosophical gambling strategy); Computer science; Generalization; Artificial intelligence; Benchmark (surveying); Sentence; Readability; Domain (mathematical analysis); Generative grammar; Space (punctuation); Generative model; Machine learning; Natural language processing; Mathematics","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":[0.0002614043,0.0003616555,0.0003862046,0.0001708606,0.0001498098,0.0002841731,0.003082859,0.0003413162,0.00003782248],"category_scores_gemma":[0.00001089446,0.000429016,0.0002534771,0.0003129139,0.00009140823,0.0006358417,0.001538683,0.0008067313,0.0001149295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001888893,"about_ca_system_score_gemma":0.0003544954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001702351,"about_ca_topic_score_gemma":0.00002647601,"domain_scores_codex":[0.9974555,0.00009881228,0.0002449308,0.001545929,0.0001419552,0.000512818],"domain_scores_gemma":[0.9975091,0.00006079913,0.0001297643,0.001982766,0.0001426517,0.0001748807],"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":[0.00001292644,0.00003134523,0.002476527,0.00006019753,0.00002241809,0.00008879187,0.0002773445,0.9021034,0.00005247739,0.09456431,0.00003326367,0.0002769427],"study_design_scores_gemma":[0.0004507953,0.00002262511,0.0002284559,0.00004845135,0.00001558242,0.000004151757,0.0000120622,0.9213679,0.00006464201,0.07730854,0.00005855205,0.0004181702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3915008,0.00003201549,0.6036552,0.00006875551,0.0004098332,0.0002393538,0.000009418784,0.0001980938,0.003886636],"genre_scores_gemma":[0.9828336,0.00002708011,0.01059879,0.0001711986,0.0000463371,0.000001411495,0.000006097834,0.00002038963,0.00629506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5930563,"threshold_uncertainty_score":0.9998162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0924450073983217,"score_gpt":0.2040797425658147,"score_spread":0.1116347351674929,"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."}}