{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002055797,0.002359601,0.001204949,0.006727159,0.001473305,0.002288724,0.001746313,0.001726088,0.004941119],"category_scores_gemma":[0.01266374,0.0009755972,0.001228412,0.00433718,0.0007135879,0.004269669,0.001615021,0.001547355,0.004338415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005321066,"about_ca_system_score_gemma":0.001515526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001892287,"about_ca_topic_score_gemma":0.004197342,"domain_scores_codex":[0.9977486,0.0006972528,0.0001691896,0.0007143089,0.0005597163,0.0001110418],"domain_scores_gemma":[0.9924483,0.004397994,0.0004874967,0.0009528733,0.001550141,0.0001631566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004245203,0.0002914025,0.004297736,0.001178018,0.000158553,0.0004888458,0.002273373,0.01423992,0.05235697,0.008697785,0.02646007,0.8891328],"study_design_scores_gemma":[0.0002041031,0.000442114,0.004702654,0.0003969197,0.0005572734,0.001603624,0.001146413,0.6403437,0.1330266,0.04282764,0.174381,0.0003678476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01868705,0.001221623,0.962472,0.0004155567,0.0002419377,0.0003325692,0.0008527483,0.01335682,0.002419588],"genre_scores_gemma":[0.07130361,0.0005502005,0.9215353,0.0000956056,0.0002883542,0.0004481453,0.001790582,0.0009242631,0.003064049],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006727159,"threshold_uncertainty_score":0.01652962,"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."}}