{"id":"W4400653413","doi":"10.5267/j.ijdns.2024.6.012","title":"An improved multi-stage framework for large-scale hierarchical text classification problems using a modified feature hashing and bi-filtering strategy","year":2024,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Hierarchy; Reduction (mathematics); Hash function; Pattern recognition (psychology); Artificial intelligence; Dimensionality reduction; Data mining; Feature (linguistics); Multi-label classification; Feature hashing; Task (project management); Scale (ratio); Machine learning; Hash table; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001372165,0.0001129184,0.0001293709,0.0002534795,0.0002539653,0.002128607,0.00225574,0.00008098744,0.000001795982],"category_scores_gemma":[0.0001193621,0.00009001893,0.00002654009,0.0004102653,0.0001945202,0.004373912,0.0005541958,0.000319221,2.611737e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004315229,"about_ca_system_score_gemma":0.0002127918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003342004,"about_ca_topic_score_gemma":0.000007524277,"domain_scores_codex":[0.9985641,0.00002686219,0.0003076168,0.0004773417,0.0003774174,0.0002466342],"domain_scores_gemma":[0.9989184,0.000161425,0.0002149036,0.0003911681,0.0002042839,0.0001097814],"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":[0.00007476439,0.0001833019,0.001328302,0.00007444728,0.00008871795,0.00002138315,0.001809024,0.003999508,0.1204665,0.4217827,0.0003319035,0.4498395],"study_design_scores_gemma":[0.0002209654,0.00008703665,0.001454427,0.0001729027,0.00000762061,0.00006188142,0.0002310882,0.9839363,0.0002641263,0.01166945,0.001785063,0.0001092095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03591241,0.0007242339,0.9604787,0.001992671,0.0006413063,0.0001275886,0.00004493944,0.00006673705,0.00001136353],"genre_scores_gemma":[0.634934,0.0001572576,0.3646476,0.00005172498,0.0001796839,0.000002769254,0.000007199143,0.000004731312,0.0000149908],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9799367,"threshold_uncertainty_score":0.9989073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1216705230253449,"score_gpt":0.3933562205989736,"score_spread":0.2716856975736287,"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."}}