{"id":"W7092497460","doi":"10.5281/zenodo.17390924","title":"War roudoù an dorneganed – Parallel Corpus (Breton Vannetais / French) – KorpusGW_FINAL_DATA v1.0","year":2025,"lang":"br","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"History of Computing Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Linguistic Association","funders":"","keywords":"Sentence; Section (typography); Metadata; Front (military); Corpus linguistics; Object (grammar)","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","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.001981608,0.001069301,0.001040263,0.001650337,0.006615823,0.003625191,0.02168752,0.0008209128,0.00541592],"category_scores_gemma":[0.002923059,0.001244162,0.0002664001,0.002768821,0.001147724,0.001437451,0.01867013,0.002286353,0.01745173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008967298,"about_ca_system_score_gemma":0.00008676698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003903991,"about_ca_topic_score_gemma":0.00001187802,"domain_scores_codex":[0.9908166,0.001617747,0.001268129,0.003007744,0.001629595,0.00166018],"domain_scores_gemma":[0.9899176,0.0001500752,0.0009249871,0.006780177,0.001605964,0.0006212484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007459702,0.0004994209,6.677025e-7,0.0003276593,0.0001391106,0.0002398044,0.0005574056,0.0002172299,0.00010423,0.002944529,0.8937957,0.1010996],"study_design_scores_gemma":[0.0008883994,0.001397702,0.0001006361,0.0003818882,0.0001062946,0.0003763546,0.00009658581,0.006094227,0.0000598713,0.0008208647,0.9884867,0.001190469],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0007470752,0.003001661,0.1188403,0.004740618,0.004800648,0.003450912,0.8290299,0.01356672,0.02182218],"genre_scores_gemma":[0.002215018,0.001438384,0.01023486,0.0005636651,0.0005072113,3.089853e-7,0.9788311,0.001704691,0.004504774],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1498012,"threshold_uncertainty_score":0.9990008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03619296995267359,"score_gpt":0.2515432038026172,"score_spread":0.2153502338499436,"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."}}