{"id":"W4408281372","doi":"10.1109/tpami.2025.3550032","title":"Correlated Topic Modeling for Short Texts in Spherical Embedding Spaces","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Hypersphere; Embedding; Knowledge graph; Graph; Word (group theory); Coherence (philosophical gambling strategy); Topic model; Information retrieval; Theoretical computer science; 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":[0.000214766,0.0001599545,0.0002901422,0.0004531196,0.0001263292,0.0001248897,0.000338976,0.00007443447,0.00002064088],"category_scores_gemma":[0.000006512906,0.0001485994,0.0001669138,0.0009740675,0.00001914073,0.0001634124,0.000007204547,0.0002266668,0.000002152688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004832565,"about_ca_system_score_gemma":0.00002319291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008342034,"about_ca_topic_score_gemma":0.001522376,"domain_scores_codex":[0.998706,0.0000407939,0.0003842282,0.000510759,0.0001346634,0.0002235035],"domain_scores_gemma":[0.9993837,0.0001329871,0.00003110258,0.0003474648,0.00004821322,0.0000565214],"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":[0.000004578699,0.00004251909,0.0007078925,0.00001066027,0.00009519665,0.000002029971,0.0001534723,0.5799474,0.00005211055,0.00015417,8.364676e-7,0.4188292],"study_design_scores_gemma":[0.00006970158,0.00002699317,0.00008921793,0.00004135689,0.0001264574,0.000001322663,0.0000486175,0.9929565,0.0057553,0.0007312715,0.00001701513,0.0001362829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01597541,0.0001385338,0.982846,0.0005164667,0.0002316333,0.0001574716,0.000004234348,0.00005968679,0.00007055369],"genre_scores_gemma":[0.9872903,0.0001016932,0.01209371,0.0002488079,0.000009083954,0.00003385057,0.000001439773,0.000005318627,0.000215781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9713149,"threshold_uncertainty_score":0.6059707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02601557484627677,"score_gpt":0.3029015206385235,"score_spread":0.2768859457922468,"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."}}