{"id":"W4415096412","doi":"10.34010/jati.v15i1.15219","title":"Pengembangan Aplikasi Sido Chatbot sebagai Aplikasi Pengenalan Objek Wisata Kediri Menggunakan Rule-Based Pattern Matching","year":2025,"lang":"id","type":"article","venue":"Jurnal Teknologi dan Informasi","topic":"Information Retrieval and Data Mining","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"WiLAN (Canada)","funders":"","keywords":"Chatbot; Informatics engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002440238,0.001126915,0.0009771228,0.002272051,0.001109478,0.004186112,0.001551336,0.001457171,0.01429916],"category_scores_gemma":[0.007233188,0.0006554039,0.001154639,0.002605594,0.0007970284,0.004414042,0.001795709,0.001099557,0.008234384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009533491,"about_ca_system_score_gemma":0.002496646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006903597,"about_ca_topic_score_gemma":0.008816046,"domain_scores_codex":[0.9956454,0.0007549676,0.0004966599,0.001071269,0.001721239,0.0003104703],"domain_scores_gemma":[0.9944066,0.001906144,0.0004065949,0.001124283,0.001930805,0.000225535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008197356,0.0006296713,0.03340019,0.001881902,0.0002026755,0.001482787,0.002406367,0.004845769,0.07387654,0.008788946,0.01146333,0.8602021],"study_design_scores_gemma":[0.0002405941,0.001814572,0.1026943,0.001579896,0.001264769,0.008739351,0.01179476,0.1526981,0.2418817,0.04267483,0.4341559,0.0004611001],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2602015,0.00433914,0.6018894,0.002367305,0.0007374533,0.001803569,0.00471615,0.01187168,0.1120737],"genre_scores_gemma":[0.5308094,0.002511675,0.3774969,0.0008648229,0.0000977585,0.0006743008,0.005582316,0.0008990862,0.08106367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01429916,"threshold_uncertainty_score":0.04783541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01904902378667674,"score_gpt":0.2579374973155952,"score_spread":0.2388884735289185,"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."}}