{"id":"W1992795877","doi":"10.3115/1220835.1220896","title":"Language model-based document clustering using random walks","year":2006,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"McGill University; National Science Foundation","keywords":"Cluster analysis; Computer science; Random walk; Document clustering; Representation (politics); Graph; Artificial intelligence; Dimension (graph theory); Hierarchical clustering; Theoretical computer science; Mathematics; Combinatorics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001856718,0.00009513731,0.000108642,0.0000628286,0.00007048397,0.0001363888,0.0003609553,0.00003280832,0.00001958522],"category_scores_gemma":[0.000004233265,0.00008349349,0.00005060617,0.00009186925,0.000008993712,0.000241084,0.0001434001,0.00005709585,0.00001001578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006319294,"about_ca_system_score_gemma":0.00004369313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006065067,"about_ca_topic_score_gemma":0.00007184882,"domain_scores_codex":[0.9991227,0.00002310453,0.0001832624,0.0002574912,0.0001894672,0.0002239303],"domain_scores_gemma":[0.9994579,0.00002596478,0.00003609626,0.000420796,0.00002074205,0.000038531],"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":[0.000003257,0.00001007439,0.00003124992,0.000006534614,0.000001679641,0.000008226429,0.0001213468,0.9871829,0.003682048,0.004250931,0.0000317331,0.004670037],"study_design_scores_gemma":[0.0008058184,0.000004308052,0.00000984371,0.00001098742,0.000002607004,0.000003248987,0.000008748208,0.9936655,0.003906395,0.00142857,0.00004160552,0.0001123557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07046746,0.00005313594,0.9238583,0.0002072333,0.00012052,0.00009697107,2.029597e-7,0.0001953399,0.005000795],"genre_scores_gemma":[0.6238522,1.586966e-7,0.375471,0.0002256741,0.00004479825,0.000002763679,5.116084e-7,0.00000452247,0.0003983669],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5533847,"threshold_uncertainty_score":0.3404766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01630013396356433,"score_gpt":0.2558534587018628,"score_spread":0.2395533247382985,"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."}}