{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01420842,0.002550972,0.002889644,0.001452401,0.001616377,0.00418756,0.003925289,0.005463657,0.007610294],"category_scores_gemma":[0.07922464,0.0009881986,0.001818792,0.001542367,0.0008139679,0.007468726,0.002077429,0.003998816,0.003051451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001227206,"about_ca_system_score_gemma":0.001746225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007970866,"about_ca_topic_score_gemma":0.008521074,"domain_scores_codex":[0.9891397,0.006232912,0.001089479,0.00234388,0.0009921888,0.0002017983],"domain_scores_gemma":[0.8838366,0.09829517,0.00178641,0.009487526,0.003725401,0.002868962],"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":[0.04937421,0.01931606,0.02461856,0.008785616,0.005582627,0.002257394,0.008336811,0.152104,0.05569067,0.004821812,0.07579068,0.5933216],"study_design_scores_gemma":[0.007329451,0.02537986,0.01239416,0.0004235327,0.002776335,0.001384029,0.002166733,0.8927448,0.02147144,0.008260973,0.02514124,0.0005274968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8976561,0.006052726,0.06965659,0.001998378,0.001491599,0.001862121,0.005531675,0.009315999,0.006434829],"genre_scores_gemma":[0.8481977,0.001144008,0.1286877,0.0009006583,0.0004078479,0.0007975076,0.01274089,0.001024037,0.00609952],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01420842,"threshold_uncertainty_score":0.0751422,"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."}}