{"id":"W2106344701","doi":"10.1145/1871437.1871556","title":"Automatically suggesting topics for augmenting text documents","year":2010,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Complement (music); Ranking (information retrieval); Information retrieval; Context (archaeology); Key (lock); Natural language processing; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002726891,0.00007642939,0.00008451326,0.00003457781,0.0001167677,0.0002131813,0.000561303,0.00004655248,0.00004512256],"category_scores_gemma":[0.0002042316,0.00006712361,0.00003931245,0.00007348791,0.00001065764,0.000317734,0.0002146807,0.0001083903,0.00002619793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001050761,"about_ca_system_score_gemma":0.00003470652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001828151,"about_ca_topic_score_gemma":0.0000204136,"domain_scores_codex":[0.9991289,0.000008375241,0.0002082732,0.0002477776,0.0001497976,0.0002569068],"domain_scores_gemma":[0.9993224,0.0001148909,0.00004813204,0.0003925032,0.00005695353,0.00006513247],"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":[5.173097e-7,0.00002498118,0.00192966,0.00002775654,0.000008196474,0.000001822819,0.0002369321,0.000064213,0.005510972,0.6113744,0.0004663251,0.3803542],"study_design_scores_gemma":[0.000240288,0.00001746704,0.000467042,0.0000105756,0.000003087008,0.000006869395,0.00001662593,0.9708517,0.002267992,0.01802943,0.007955666,0.0001332707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06978601,0.000002655035,0.9143549,0.001668566,0.0006436184,0.0001588786,1.739123e-7,0.0002817635,0.01310349],"genre_scores_gemma":[0.2921144,1.425947e-7,0.7052175,0.000305157,0.0001428763,0.00001464163,3.844209e-7,0.000004451103,0.0022004],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9707875,"threshold_uncertainty_score":0.2737221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01665793086688343,"score_gpt":0.277368514942678,"score_spread":0.2607105840757946,"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."}}