# Document Grounding on Hebrew Verdict Decisions human-annotated gold labels Source: [Document Grounding on Hebrew Verdict Decisions human-annotated gold labels]() Collection index: [llms.txt]() Data updated: 2026-06-12T06:59:22.795Z Evaluation of Document Grounding performance on the Hebrew Verdict Decisions human-annotated gold labels dataset, measured using Macro/Micro F1 scores (both partial and exact). 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 | Document Grounding | | Dataset (including any stated split) | Hebrew Verdict Decisions human-annotated gold labels | | Metric | Macro F1 (Partial) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 3 of 3 | | 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 - [Macro F1 (Partial)](): Higher is better; unit: PERCENT. - [Macro F1 (Exact)](): Higher is better; unit: PERCENT. - [Micro F1 (Partial)](): Higher is better; unit: PERCENT. - [Micro F1 (Exact)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Macro F1 (Partial) | Result date | Report paper | | --- | --- | --- | --- | | Doc-Structure-Parser | 78.1 | Not recorded | 68fa7ae41e209131cea85b4c | | Random | 21.6 | Not recorded | 68fa7ae41e209131cea85b4c | | Most frequent class | 8.3 | Not recorded | 68fa7ae41e209131cea85b4c | ### Doc-Structure-Parser Macro F1 (Partial): 78.1. Result ID: 6a2bae43fbc373592c297fd0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Random Macro F1 (Partial): 21.6. Result ID: 6a2bae43fbc373592c297fd2. [Reporting paper]() Recorded evaluation configuration: {"averaging":"100 different random seeds"}. This record does not assert independent reproduction. ### Most frequent class Macro F1 (Partial): 8.3. Result ID: 6a2bae43fbc373592c297fd1. [Reporting paper]() Recorded evaluation configuration: {"class\_strategy":"prosecution evidence"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.