{"id":"W2573266127","doi":"10.63317/2z8qjf6d9e4t","title":"Evaluating a Topic Modelling Approach to Measuring Corpus Similarity","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Similarity (geometry); Natural language processing; Task (project management); Information retrieval; Artificial intelligence; Text corpus; Image (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":[],"consensus_categories":[],"category_scores_codex":[0.0007880136,0.0001179151,0.0001374226,0.00007614261,0.0001091892,0.0001005032,0.0007567631,0.00004689923,0.00000877014],"category_scores_gemma":[0.00008845275,0.00008055473,0.00004810023,0.0001739735,0.000008752341,0.0003609189,0.0003727084,0.00007458785,0.00004399704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008040486,"about_ca_system_score_gemma":0.00005355659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005817902,"about_ca_topic_score_gemma":0.000003380598,"domain_scores_codex":[0.9984218,0.00006033352,0.0002333209,0.0005326947,0.0004182576,0.0003335348],"domain_scores_gemma":[0.9989479,0.00008322371,0.00003944393,0.0006964931,0.00009843694,0.0001345555],"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":[0.000004894456,0.00006690976,0.0007491109,0.0000249807,0.00001629342,0.000002787214,0.001187257,0.2939247,0.007321505,0.229212,0.00005309737,0.4674365],"study_design_scores_gemma":[0.0001974714,0.00002111029,0.00005547783,0.00002712386,0.000002286242,0.000005090485,0.000007955224,0.9898996,0.002116113,0.007309779,0.0002058833,0.000152079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05167793,0.0000255285,0.9321786,0.0007833112,0.0001830653,0.000173918,2.149538e-7,0.0002540385,0.01472339],"genre_scores_gemma":[0.5116805,0.000001063322,0.4873894,0.0002305651,0.0000586057,0.00001315334,5.054517e-8,0.000004642364,0.0006220736],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6959749,"threshold_uncertainty_score":0.3284927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2631698706386932,"score_gpt":0.3149622874195979,"score_spread":0.05179241678090468,"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."}}