{"id":"W4400617758","doi":"10.1016/j.patcog.2024.110779","title":"Few-shot relational triple extraction with hierarchical prototype optimization","year":2024,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Major Basic Research Project of the Natural Science Foundation of the Jiangsu Higher Education Institutions","keywords":"Computer science; Shot (pellet); Extraction (chemistry); Artificial intelligence; Pattern recognition (psychology); Computer vision; Chromatography; Chemistry","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":[0.0002862408,0.0001278966,0.00009004414,0.0002116988,0.0001479714,0.0003406723,0.0001233027,0.00007749981,0.0004549882],"category_scores_gemma":[0.00003747418,0.0001139969,0.0000460729,0.0004453983,0.00002681665,0.001070525,0.00002614361,0.0002949752,0.0004711108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006428864,"about_ca_system_score_gemma":0.00007826566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008857701,"about_ca_topic_score_gemma":0.000005725575,"domain_scores_codex":[0.9987301,0.0001169,0.0002180331,0.000401032,0.0003525033,0.0001814139],"domain_scores_gemma":[0.9994828,0.0001199306,0.00006698925,0.00014793,0.0001055294,0.00007682004],"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":[0.00007527094,0.0000914194,0.000578109,0.00007448612,0.00003954689,0.00005288628,0.0007627413,0.01086024,0.0002733071,0.002095965,0.0003110107,0.984785],"study_design_scores_gemma":[0.0004645556,0.0002402648,0.004049674,0.0001829172,0.00001627162,0.0001318194,0.00003118996,0.986107,0.000304124,0.001845585,0.006370147,0.0002564431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004073183,0.00004864166,0.9884779,0.001148448,0.0004590809,0.0004286864,0.000006007353,0.0004552156,0.004902875],"genre_scores_gemma":[0.871922,0.00002758125,0.1262458,0.0004081878,0.0002736615,0.0002255337,0.0003434992,0.00003103445,0.0005226969],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9845286,"threshold_uncertainty_score":0.6055334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05194468542505946,"score_gpt":0.2807868888145493,"score_spread":0.2288422033894898,"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."}}