{"id":"W4385571031","doi":"10.18653/v1/2023.findings-acl.868","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Indonesian; Art; Artificial intelligence; Art history; Theology; Philosophy; Computer science; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004329977,0.00009257005,0.0001314741,0.0001053133,0.0001752466,0.0003823884,0.001700855,0.00004607086,0.00001784389],"category_scores_gemma":[0.00006359432,0.00008122323,0.00004136584,0.0004316719,0.00001843219,0.0004979055,0.001048471,0.00006525948,0.0001386385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001810722,"about_ca_system_score_gemma":0.00004489036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008412942,"about_ca_topic_score_gemma":0.00003341623,"domain_scores_codex":[0.9989839,0.00004031252,0.0001702947,0.0003713309,0.0001498688,0.0002843237],"domain_scores_gemma":[0.9991649,0.0002080758,0.00005082698,0.0004546616,0.00005091584,0.00007059203],"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":[0.00004218386,0.0001108557,0.004335511,0.0000858002,0.0001058405,0.00004027006,0.03518028,0.005115636,0.0007562019,0.4550124,0.0592166,0.4399984],"study_design_scores_gemma":[0.001093289,0.0001276061,0.003023004,0.00003632563,0.000005955304,0.000007540375,0.001426471,0.8006144,0.002331526,0.03202296,0.1588795,0.0004314301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02779658,0.000009214476,0.9493015,0.003827719,0.000162779,0.0004193656,0.000002045851,0.0004613311,0.01801943],"genre_scores_gemma":[0.8517942,0.000003046243,0.1348654,0.002314766,0.000170117,0.0001746685,0.00000486059,0.00002189932,0.010651],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8239977,"threshold_uncertainty_score":0.368738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08243536302076786,"score_gpt":0.3138575182029832,"score_spread":0.2314221551822154,"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."}}