{"id":"W4388976713","doi":"10.1007/978-3-031-45043-3_2","title":"Building an NLIDB: The Basics","year":2023,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on data management","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Leverage (statistics); Sect; Construct (python library); Computer science; Baseline (sea); Rest (music); Programming language; Artificial intelligence; Political science","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.001048691,0.0004658048,0.0003355535,0.0002934839,0.0002990643,0.0006428882,0.009586269,0.0001700964,0.000070927],"category_scores_gemma":[0.00009839379,0.0003385287,0.0001051171,0.0000968696,0.0000543723,0.0003691991,0.004665022,0.0004586217,0.0003046171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009428449,"about_ca_system_score_gemma":0.0000333943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001934935,"about_ca_topic_score_gemma":0.00005311573,"domain_scores_codex":[0.9966372,0.00007654277,0.0003762414,0.001572034,0.0009142869,0.0004237508],"domain_scores_gemma":[0.9910089,0.0004545775,0.0002040614,0.008212619,0.00002900282,0.0000908429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002582377,0.000008514956,1.179813e-7,0.00004059569,0.0001364689,0.00006175913,0.00002622072,0.0009715314,8.255342e-7,0.7068097,0.006621129,0.2853206],"study_design_scores_gemma":[0.00006912711,0.00003356396,0.00001880588,0.0003501172,0.0001616986,0.000004718631,0.000008991105,0.0648379,0.00005254901,0.179032,0.7548281,0.0006024496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.000002074828,0.0001824495,0.7105517,0.003640099,0.001170416,0.0006801851,0.0001330205,0.0006803308,0.2829597],"genre_scores_gemma":[0.01301862,0.002788148,0.3530546,0.01193214,0.00359854,0.0003717903,0.0005353203,0.0008072766,0.6138935],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.748207,"threshold_uncertainty_score":0.9999067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09428031179532508,"score_gpt":0.2902417105555458,"score_spread":0.1959613987602207,"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."}}