{"id":"W4400281282","doi":"10.32473/flairs.37.1.135043","title":"Latent Beta-Liouville Probabilistic Modeling for Bursty Topic Discovery in Textual Data","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Burstiness; Perplexity; Computer science; Topic model; Natural language processing; Language model; Word (group theory); Probabilistic logic; Dirichlet distribution; Artificial intelligence; Range (aeronautics); 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":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.003142123,0.0001829019,0.0002204546,0.0001660733,0.0001949708,0.001225096,0.005549003,0.0001076647,0.00001596333],"category_scores_gemma":[0.0009565125,0.0001419386,0.0001885461,0.0007648363,0.0002272503,0.001776091,0.002578678,0.0006386988,0.00001034233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003128054,"about_ca_system_score_gemma":0.0005189169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003185786,"about_ca_topic_score_gemma":0.000078407,"domain_scores_codex":[0.9965472,0.00002205514,0.0006833407,0.0009447889,0.001272038,0.0005306039],"domain_scores_gemma":[0.9976671,0.000459392,0.0000836039,0.0005144729,0.001200746,0.00007470678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001907495,0.00006642524,0.0001723045,0.0001940899,0.00005303942,7.760107e-7,0.002008849,0.005353256,0.005118276,0.9666145,0.0005144654,0.01988494],"study_design_scores_gemma":[0.0000248913,0.00003015866,0.00001269038,0.0003087107,0.000005351504,0.000002257806,0.001020272,0.7982248,0.007001175,0.1929307,0.0003196842,0.0001193319],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1313938,0.0002585897,0.8482869,0.01547656,0.001745381,0.001103062,0.00008164008,0.0001083274,0.001545716],"genre_scores_gemma":[0.9875429,0.0001400643,0.0112946,0.00004332557,0.0004225125,0.0001148155,0.000009648156,0.00001416519,0.0004179628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8561491,"threshold_uncertainty_score":0.9998314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.312632176089768,"score_gpt":0.4053127273422721,"score_spread":0.09268055125250407,"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."}}