{"id":"W7117575766","doi":"10.18280/isi.301102","title":"Indonesian Sports Text Classification Modeling Based on Few-Shot NER","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":"Indonesian; Topic model; Feature (linguistics); Named-entity recognition; Acronym","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001089778,0.0006140598,0.0005188046,0.002120254,0.001074133,0.002070483,0.001512328,0.0006358949,0.0000907809],"category_scores_gemma":[0.0005245104,0.0006285476,0.0002292068,0.00289606,0.0003449584,0.007075433,0.0002830323,0.000576555,0.0003103222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00106763,"about_ca_system_score_gemma":0.0007924706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005254749,"about_ca_topic_score_gemma":0.00000513289,"domain_scores_codex":[0.9954677,0.0001524458,0.00194811,0.0006576672,0.00101374,0.0007603786],"domain_scores_gemma":[0.9961217,0.0001472216,0.001005733,0.00182505,0.0007529895,0.0001473056],"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":[0.0001112967,0.0001632406,0.002789254,0.0004893644,0.00003912147,0.000002637958,0.001747065,0.03845057,0.0001299734,0.2563088,0.001070638,0.698698],"study_design_scores_gemma":[0.0008117314,0.0001318599,0.01228282,0.0008800867,0.000041525,0.00000410244,0.001516087,0.9651105,0.001063067,0.01201545,0.005563944,0.0005787741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02723833,0.0001842799,0.9086042,0.00295537,0.001584319,0.001069726,0.00001575421,0.001121123,0.05722689],"genre_scores_gemma":[0.991986,0.0001109358,0.005704602,0.001315496,0.00005804432,0.000240068,0.0001348091,0.00002030034,0.0004297031],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9647477,"threshold_uncertainty_score":0.9996166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02922572258510529,"score_gpt":0.2616909532835031,"score_spread":0.2324652306983978,"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."}}