# Accuracy Correlation Analysis on ACE Forecaster-level Season 4 1.0 Source: [Accuracy Correlation Analysis on ACE Forecaster-level Season 4 1.0]() Collection index: [llms.txt]() Data updated: 2026-07-01T06:38:13.840Z Evaluation of model performance using correlation metrics (r values) and statistical significance (p-values) for Accuracy Correlation Analysis on the ACE Forecaster-level Season 4 1.0 dataset, covering EQM, Human Rating, and Between measures. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Accuracy Correlation Analysis | | Dataset (including any stated split) | ACE Forecaster-level Season 4 1.0 | | Metric | Human Rating Correlation Coefficient | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 4 of 4 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Human Rating Correlation Coefficient](): Higher is better; unit: SCALAR. - [EQM Correlation Coefficient](): Higher is better; unit: SCALAR. - [EQM P-Value](): Lower is better; unit: SCALAR. - [Human Rating P-Value](): Lower is better; unit: SCALAR. - [Between Measure Correlation Coefficient](): Higher is better; unit: SCALAR. - [Between Measure P-Value](): Lower is better; unit: SCALAR. - [EQM Better Comparison P-Value](): Lower is better; unit: SCALAR. ## Recorded results | Method | Human Rating Correlation Coefficient | Result date | Report paper | | --- | --- | --- | --- | | EQM composite score | 0.4 | Not recorded | 6a449f01e0224bd4f4992f93 | | Human Rating | 0.4 | Not recorded | 6a449f01e0224bd4f4992f93 | | EQM composite score | 0.36 | Not recorded | 6a449f01e0224bd4f4992f93 | | EQM composite score | 0.26 | Not recorded | 6a449f01e0224bd4f4992f93 | ### EQM composite score Human Rating Correlation Coefficient: 0.4. Result ID: 6a44b5d573d097d845bd8faf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"141","Metric (Ground Truth)":"ABSnorm","Training Set":"Seasons 1-3","Minimum Rationale Threshold":"at least 10 rationales with at least three human ratings"}. This record does not assert independent reproduction. ### Human Rating Human Rating Correlation Coefficient: 0.4. Result ID: 6a44b5d573d097d845bd8fb0. [Reporting paper]() Recorded evaluation configuration: {"n":"141","Metric (Ground Truth)":"ABSnorm","Minimum Rationale Threshold":"at least 10 rationales with at least three human ratings"}. This record does not assert independent reproduction. ### EQM composite score Human Rating Correlation Coefficient: 0.36. Result ID: 6a44b5d573d097d845bd8fb1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"242","Metric (Ground Truth)":"ABSnorm","Minimum Rationale Threshold":"at least 5 rationales"}. This record does not assert independent reproduction. ### EQM composite score Human Rating Correlation Coefficient: 0.26. Result ID: 6a44b5d573d097d845bd8fb2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"409","Metric (Ground Truth)":"ABSnorm","Minimum Rationale Threshold":"at least 1 rationale"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.