{"id":"W2621376330","doi":"10.1162/tacl_a_00055","title":"Joint Modeling of Topics, Citations, and Topical Authority in Academic Corpora","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science, ICT and Future Planning","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Citation; Search engine indexing; Information retrieval; Process (computing); Joint (building); Generative grammar; Data science; Artificial intelligence; World Wide Web","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":[0.0004619941,0.00006103636,0.0001506372,0.00006714269,0.0002436496,0.00003442957,0.0003748847,0.0000880679,5.708993e-7],"category_scores_gemma":[0.001880118,0.00005939988,0.00007151208,0.00006350628,0.0000324798,0.00008196546,0.0000336802,0.0001671056,1.788431e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000849045,"about_ca_system_score_gemma":0.0001014329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008015302,"about_ca_topic_score_gemma":0.00002417538,"domain_scores_codex":[0.9990754,0.00003563137,0.0004119432,0.0001403731,0.0002412849,0.00009534788],"domain_scores_gemma":[0.9985586,0.0002410533,0.0004191854,0.0002340909,0.0005232532,0.00002379704],"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":[0.000004232249,0.00003629311,0.01244041,0.00004274265,0.00002139249,7.598566e-8,0.000398296,0.5883651,0.00001501283,0.3967745,0.000009792241,0.001892188],"study_design_scores_gemma":[0.0002708126,0.00001243014,0.02045474,0.00002814577,0.00001346266,2.875677e-7,0.00001464572,0.803604,0.00005185032,0.1754325,0.00007048487,0.00004662848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02197316,0.00002458694,0.9753662,0.001515569,0.0006601588,0.0001722212,0.000028229,0.00001311197,0.000246794],"genre_scores_gemma":[0.8918392,0.000006371423,0.1079484,0.00001845469,0.00007301617,0.00000594277,0.000002290992,0.000003170025,0.0001031612],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8698661,"threshold_uncertainty_score":0.2422257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07106014512581252,"score_gpt":0.318250592846475,"score_spread":0.2471904477206625,"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."}}