{"id":"W4393112045","doi":"10.1186/s40537-024-00898-6","title":"Multi-sample $$\\zeta $$-mixup: richer, more realistic synthetic samples from a p-series interpolant","year":2024,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Compute Canada; Simon Fraser University; Nvidia","keywords":"Algorithm; Computer science; Machine learning; Artificial intelligence; Series (stratigraphy)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007541192,0.0001554689,0.0002670012,0.0002112887,0.00009160002,0.0006868809,0.002110638,0.00005384419,0.00005697152],"category_scores_gemma":[0.001193753,0.000120523,0.00008641571,0.0003175712,0.00007606616,0.001137393,0.0006904796,0.0003766805,0.00005045704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004790119,"about_ca_system_score_gemma":0.0001962938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003848189,"about_ca_topic_score_gemma":0.0001163229,"domain_scores_codex":[0.9983478,0.0001342194,0.0005253986,0.0003575933,0.000415452,0.0002195822],"domain_scores_gemma":[0.9977788,0.0007614201,0.0002451088,0.0009665096,0.00009366071,0.0001545019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002011997,0.0004666362,0.001418642,0.0002447147,0.000961406,0.002646601,0.01675872,0.0005487728,0.009023111,0.02764556,0.05536313,0.8847215],"study_design_scores_gemma":[0.0006876604,0.0001955299,0.006126833,0.0009468712,0.0001298347,0.0007458985,0.001219316,0.4748622,0.0001680978,0.00501341,0.5094625,0.0004417592],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001912013,0.003248543,0.9898955,0.00223624,0.002016361,0.000052863,0.0004610408,0.00008114592,0.00009633015],"genre_scores_gemma":[0.5859845,0.0007112929,0.4114087,0.000505156,0.0008444877,0.000002100525,0.0001999347,0.0000344332,0.0003094186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8842797,"threshold_uncertainty_score":0.6623608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1817104695287353,"score_gpt":0.3345108908799068,"score_spread":0.1528004213511714,"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."}}