{"id":"W2054808906","doi":"10.1145/2494266.2494279","title":"Interactive text document clustering using feature labeling","year":2013,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cluster analysis; Term (time); Discriminative model; Document clustering; Heuristic; Selection (genetic algorithm); Artificial intelligence; Cluster (spacecraft); Information retrieval; Data mining; Pattern recognition (psychology)","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":[0.00006692224,0.0001069551,0.00009196781,0.0001129966,0.0001055448,0.000494062,0.0006244449,0.00005915971,0.00017868],"category_scores_gemma":[0.0000265563,0.00008472516,0.00003400589,0.0002440657,0.0000243828,0.001540276,0.0004787715,0.0001340393,0.0002999292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008388819,"about_ca_system_score_gemma":0.00001691942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008930331,"about_ca_topic_score_gemma":0.000005606342,"domain_scores_codex":[0.9992352,0.00001688806,0.0001319212,0.0002697685,0.0001413698,0.0002048433],"domain_scores_gemma":[0.9993508,0.00004478387,0.00007322018,0.0004194794,0.00007131827,0.00004042949],"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":[0.000004963001,0.00009493405,0.00117758,0.00002860167,0.00007371306,0.000007121733,0.001796362,0.0006604068,0.1020262,0.1563406,0.01693035,0.7208592],"study_design_scores_gemma":[0.0007856205,0.0001284627,0.003437927,0.0001200845,0.00001241875,0.00005053147,0.002818645,0.8144624,0.108475,0.04701686,0.02175243,0.0009396164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02755098,0.00007876521,0.9571991,0.007198466,0.0003223914,0.0002369319,1.541615e-7,0.0008965668,0.00651664],"genre_scores_gemma":[0.7348149,0.000007649077,0.2625473,0.0003204443,0.00001917868,0.00002104807,4.584192e-7,0.000004962542,0.002264055],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8138019,"threshold_uncertainty_score":0.4764251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01998905261782122,"score_gpt":0.2722645220177291,"score_spread":0.2522754693999079,"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."}}