{"id":"W6891631026","doi":"10.48448/25w9-2r04","title":"Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Robustness (evolution); Dependency (UML); Parsing; Dependency grammar; Ensemble learning; Ensemble forecasting; Mean squared prediction error","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003607675,0.0008581508,0.0009661043,0.002381612,0.001724824,0.0004006766,0.003231725,0.0005452467,0.001375898],"category_scores_gemma":[0.0004320492,0.0008541475,0.0002317533,0.002118022,0.001111004,0.0007374447,0.001505775,0.0005352078,0.0006597383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009578518,"about_ca_system_score_gemma":0.002122924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005843744,"about_ca_topic_score_gemma":0.01364559,"domain_scores_codex":[0.9932576,0.000359961,0.00063654,0.00231476,0.001833433,0.001597724],"domain_scores_gemma":[0.9962645,0.0003367253,0.0005843367,0.001755158,0.0004958183,0.0005634709],"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":[0.0008098795,0.001775888,0.0006288944,0.0013518,0.0005168147,0.0001520467,0.002453912,0.0007489398,0.1370081,0.01569974,0.7880498,0.05080416],"study_design_scores_gemma":[0.008967905,0.001482668,0.0007348071,0.003142316,0.002395247,0.00006393214,0.006929465,0.2567554,0.00743862,0.02736815,0.6774783,0.007243273],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007307341,0.0008559939,0.708001,0.002662418,0.003725673,0.005861629,0.006207685,0.003327922,0.268627],"genre_scores_gemma":[0.013576,0.00001918156,0.7227309,0.002767133,0.0006058288,0.00009359275,0.0006823925,0.001334711,0.2581903],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2560064,"threshold_uncertainty_score":0.9995748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06551008915775577,"score_gpt":0.3664423061963543,"score_spread":0.3009322170385985,"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."}}