{"id":"W2489491723","doi":"10.1007/978-3-319-41754-7_8","title":"Evaluating Multiple Summaries Without Human Models: A First Experiment with a Trivergent Model","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Task (project management); Set (abstract data type); Natural language processing; Artificial intelligence; Information retrieval; Source model; Programming language; Theoretical computer science; Systems engineering","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":[0.0009738225,0.0007532673,0.0006989684,0.000619748,0.0006613138,0.0005590231,0.003454894,0.0002708392,0.00001257999],"category_scores_gemma":[0.00005840763,0.0005545404,0.0001390697,0.0002728757,0.0006355805,0.001059209,0.001939681,0.0005714534,0.00001210543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006558468,"about_ca_system_score_gemma":0.000827011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005012424,"about_ca_topic_score_gemma":0.0003266552,"domain_scores_codex":[0.9942469,0.00004026937,0.000694396,0.002316838,0.001792534,0.000909036],"domain_scores_gemma":[0.9965417,0.0003108954,0.0004062522,0.002134346,0.0003578794,0.0002488658],"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":[0.00001593921,0.0000299364,0.00005486682,0.00003093294,0.00001776454,0.00002394615,0.00270219,0.8565735,0.0002963861,0.04009801,0.000003342703,0.1001531],"study_design_scores_gemma":[0.0007152419,0.0002252434,0.000002944542,0.0007327972,0.00001007338,0.0000204589,3.790854e-7,0.8651186,0.0009486687,0.1314717,0.00006269285,0.0006911663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009451354,0.0003792147,0.9947237,0.0004692602,0.0004903099,0.0007461395,0.000006974513,0.0002545362,0.001984767],"genre_scores_gemma":[0.3945659,0.00001515395,0.6043168,0.0003142988,0.0002116891,0.00004918365,0.000002068986,0.00004466185,0.0004802763],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3936208,"threshold_uncertainty_score":0.9996906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08502014523120585,"score_gpt":0.3093159256192198,"score_spread":0.2242957803880139,"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."}}