{"id":"W7077903352","doi":"10.48448/zyk6-vj62","title":"Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Machine translation; Task (project management); Translation (biology); Unsupervised learning; Word (group theory); BLEU","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":[0.0007137489,0.0002298241,0.0003535742,0.0004805065,0.00009350511,0.0000551583,0.001048435,0.0001388879,0.00003635367],"category_scores_gemma":[0.000119782,0.0001854298,0.00004515889,0.001067824,0.0002597319,0.0001682793,0.0001190942,0.0001390169,0.000001477369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004787923,"about_ca_system_score_gemma":0.0004863715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002675298,"about_ca_topic_score_gemma":0.000829885,"domain_scores_codex":[0.9983873,0.00003912812,0.0002617733,0.0006750801,0.0003031954,0.0003335106],"domain_scores_gemma":[0.9987822,0.0003321627,0.0002039771,0.0004583788,0.0001694136,0.00005386907],"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":[0.00009284526,0.0005362804,0.004027959,0.00202005,0.0001688897,0.00002737208,0.006591726,0.002206894,0.004103661,0.05549456,0.002104379,0.9226254],"study_design_scores_gemma":[0.005250033,0.001042435,0.001450211,0.002692791,0.00009825997,0.00002741617,0.0009276199,0.8036068,0.01376479,0.007236627,0.1624238,0.001479198],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005962376,0.0008763453,0.7137014,0.0009732599,0.0002983287,0.001641717,0.00004074984,0.000310249,0.2815616],"genre_scores_gemma":[0.6326616,0.00002760371,0.3362241,0.0001993803,0.00009618208,0.0001533559,0.00004328938,0.00003637522,0.03055806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9211462,"threshold_uncertainty_score":0.7561607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01562179347362058,"score_gpt":0.2499795409563736,"score_spread":0.234357747482753,"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."}}