{"id":"W66763315","doi":"10.1007/978-3-642-30217-6_2","title":"Active Learning for Hierarchical Text Classification","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Oracle; Text categorization; Categorization; Machine learning; Active learning (machine learning); Artificial intelligence; Multi-label classification; Hierarchical database model; Relation (database); Data mining; Information retrieval","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"],"consensus_categories":[],"category_scores_codex":[0.0006706305,0.0003996124,0.000377542,0.0008383607,0.0003854622,0.0004367229,0.002841511,0.0004394706,0.00002125961],"category_scores_gemma":[0.0002648336,0.0003638294,0.0001354586,0.0004797311,0.0007362014,0.0008989555,0.0008391087,0.0009726018,0.00007228899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003531161,"about_ca_system_score_gemma":0.0003169349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002546093,"about_ca_topic_score_gemma":0.000005976752,"domain_scores_codex":[0.9969997,0.00002981188,0.0004293226,0.001247503,0.000641312,0.0006523825],"domain_scores_gemma":[0.997391,0.0007796852,0.0003723138,0.001097546,0.0002281858,0.0001312668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005418295,0.00001781104,0.0000331372,0.00001303848,0.000005350169,0.000001095465,0.0002921579,0.0005185644,0.0003458747,0.2007328,0.0000218944,0.7980129],"study_design_scores_gemma":[0.0004532004,0.0002889725,0.00124942,0.0001645304,0.00001442573,0.00002314695,0.000001510298,0.4115851,0.005818869,0.5335995,0.04582787,0.0009734729],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00003960234,0.0003247517,0.9917894,0.002943871,0.0008529788,0.0005579271,0.000002773377,0.0005150079,0.00297371],"genre_scores_gemma":[0.5435845,0.0001188745,0.4537228,0.0005079936,0.0005149874,0.00009898123,0.00002113056,0.00004415368,0.001386622],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7970394,"threshold_uncertainty_score":0.9998814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03429201081498399,"score_gpt":0.2791535654519344,"score_spread":0.2448615546369504,"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."}}