{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001037414,0.0005323379,0.0005247264,0.0008046401,0.0003893453,0.0007283149,0.001775994,0.001260722,0.003257772],"category_scores_gemma":[0.004261048,0.0003790187,0.0006362309,0.0009826157,0.0007666306,0.002712017,0.001475397,0.001732838,0.0008499269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000895097,"about_ca_system_score_gemma":0.0007103954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005313329,"about_ca_topic_score_gemma":0.008529317,"domain_scores_codex":[0.9995023,0.0001275719,0.00002466243,0.0002128326,0.00007674009,0.00005590254],"domain_scores_gemma":[0.9989125,0.0004919035,0.0001314907,0.0001644663,0.0002386878,0.00006103748],"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":[0.0004191062,0.0003978186,0.00605349,0.0002495763,0.000201996,0.0003497498,0.0008478953,0.5443875,0.01812483,0.08200318,0.01465577,0.3323092],"study_design_scores_gemma":[0.00001924344,0.000051248,0.0007101827,0.000009407176,0.00002315248,0.0000487679,0.00002692094,0.9795944,0.00086063,0.01724462,0.001401907,0.000009493317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.115306,0.0008938068,0.8714799,0.001291154,0.00009922691,0.0001242927,0.0008954633,0.001758774,0.008151487],"genre_scores_gemma":[0.9032283,0.0003663003,0.07908382,0.0005500696,0.0001317786,0.0002812229,0.001742639,0.0002173524,0.01439846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005313329,"threshold_uncertainty_score":0.01089835,"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."}}