{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.01039058,0.001115723,0.001551583,0.008389806,0.001634603,0.004208154,0.00207344,0.002187163,0.002434107],"category_scores_gemma":[0.04555575,0.000909063,0.002014219,0.01019488,0.001608447,0.00830467,0.002259714,0.002778608,0.001764792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002386807,"about_ca_system_score_gemma":0.002723745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01647594,"about_ca_topic_score_gemma":0.0224506,"domain_scores_codex":[0.9956542,0.002215741,0.0003409135,0.0009961798,0.0005692671,0.0002236654],"domain_scores_gemma":[0.9745771,0.01974169,0.001525031,0.001826122,0.001884864,0.0004451852],"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":[0.0008235031,0.0007243739,0.0446758,0.000972366,0.0006577469,0.0006739224,0.003662061,0.552632,0.005015152,0.08699914,0.02890758,0.2742563],"study_design_scores_gemma":[0.00005478408,0.00003389429,0.003231131,0.00004069344,0.0000602016,0.00008290669,0.0001318459,0.9552019,0.0006297481,0.03624069,0.004258548,0.00003360718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3560072,0.007778679,0.6035477,0.003806041,0.0004533119,0.0005694352,0.008518483,0.005805213,0.01351399],"genre_scores_gemma":[0.8158143,0.002586906,0.1558871,0.000314413,0.001016593,0.0009815642,0.01500465,0.0006796211,0.007714904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9916102,"threshold_uncertainty_score":0.05495131,"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."}}