{"id":"W7117547339","doi":"10.18280/isi.301114","title":"SHADO: A Semantics-Preserving Hybrid Framework for Automatic Text Classification Using Domain Ontology","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Domain (mathematical analysis); Ontology; Feature (linguistics); Identification (biology); Pattern recognition (psychology)","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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00136416,0.0006066492,0.000757824,0.001494325,0.001514439,0.00238441,0.002217918,0.0006651393,0.00007039481],"category_scores_gemma":[0.00262461,0.0006587208,0.0002946692,0.001995967,0.0006122687,0.007460319,0.0007776485,0.0005129367,0.0001101184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001345399,"about_ca_system_score_gemma":0.0007531813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005678148,"about_ca_topic_score_gemma":0.00001212011,"domain_scores_codex":[0.9952619,0.0002294384,0.002312278,0.0006569742,0.000529405,0.001010025],"domain_scores_gemma":[0.9946495,0.0007868499,0.001753456,0.001783577,0.0008979116,0.0001286971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004005638,0.00008453333,0.0009088272,0.001979743,0.0001288165,0.000001351539,0.00438009,0.0002879696,0.0004252794,0.67909,0.001273295,0.3114],"study_design_scores_gemma":[0.0005643331,0.000103686,0.003544375,0.001286591,0.00007721638,0.00002250606,0.002931056,0.6157586,0.001580536,0.3680889,0.00558729,0.0004548585],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06115233,0.0006296955,0.9268136,0.003586181,0.002089374,0.0020604,0.00004404111,0.001057989,0.002566395],"genre_scores_gemma":[0.7394071,0.00008068029,0.2594123,0.000462437,0.00006662817,0.0003473425,0.00006560778,0.00002001436,0.0001378939],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6782548,"threshold_uncertainty_score":0.9997855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03452624255051188,"score_gpt":0.2994413137071079,"score_spread":0.264915071156596,"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."}}