{"id":"W2899387524","doi":"10.46430/phes0040","title":"Introducción a Topic Modeling y MALLET","year":2018,"lang":"es","type":"article","venue":"The Programming Historian en español","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Carleton University","funders":"","keywords":"Mallet; Humanities; Computer science; Philosophy; Physics; Acoustics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001000885,0.0003171559,0.0002742003,0.0001113044,0.0009259627,0.0007153862,0.002316598,0.0001423901,0.00005246513],"category_scores_gemma":[0.0001143422,0.0002578846,0.0001233477,0.0005328601,0.0003057322,0.0003238268,0.0006589441,0.0004162033,0.0008204912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003277071,"about_ca_system_score_gemma":0.0002249893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001776601,"about_ca_topic_score_gemma":0.00003688051,"domain_scores_codex":[0.9975677,0.0001325752,0.0004314202,0.0008004545,0.0004175576,0.0006503149],"domain_scores_gemma":[0.9974385,0.0001041149,0.0001821771,0.001877469,0.0002268462,0.0001708876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009429643,0.0001131442,0.00003193919,0.00002718911,0.00005414302,0.000005549377,0.008928343,0.00004402357,0.00008915476,0.135842,0.003550567,0.8513045],"study_design_scores_gemma":[0.0001940061,0.0001799603,0.00002361144,0.00006069963,0.00005144772,0.00002085516,0.00009680438,0.2326106,0.00004027954,0.001922902,0.7645113,0.0002874872],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006981431,0.001329952,0.9573497,0.01944255,0.004455767,0.001054241,0.00001948986,0.000660545,0.00870629],"genre_scores_gemma":[0.6175768,0.0001024415,0.3316,0.0007170396,0.01674138,0.00035295,0.0000312947,0.0001245419,0.03275358],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.851017,"threshold_uncertainty_score":0.9999874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0174250920619393,"score_gpt":0.2677993453107185,"score_spread":0.2503742532487792,"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."}}