docs: pin compaction study references to reviewed results

This commit is contained in:
jinli.yl 2026-10-16 16:48:55 +08:00
parent 11317634e5
commit eb816361d8
2 changed files with 2 additions and 2 deletions

View file

@ -140,4 +140,4 @@ this is an incremental-evidence curve, not an equal-length comparison or proof t
The panel has 336 contexts and 672 answers, with the controls reported separately. Hermes collects source trajectories;
answering calls Qwen directly without tool continuation or recovery. These few synthetic tasks do not establish general
superiority or statistical equivalence. The hybrid and native adapter remain benchmark-only.
See the [exact queries, answers and settings](https://github.com/jinliyl/ReMe/blob/feat/decision-model-compaction/benchmark/compaction/STUDY.md) and [results, controls and audit](https://github.com/jinliyl/ReMe/blob/feat/decision-model-compaction/benchmark/compaction/RESULTS.md).
See the [exact queries, answers and settings](https://github.com/jinliyl/ReMe/blob/11317634e5e255a7c7b13492f048f8ca0c90ab3a/benchmark/compaction/STUDY.md) and [results, controls and audit](https://github.com/jinliyl/ReMe/blob/11317634e5e255a7c7b13492f048f8ca0c90ab3a/benchmark/compaction/RESULTS.md).

View file

@ -129,4 +129,4 @@ Top N 按完整证据块计数,超过可用数量时保留全部。原支付
共 336 个上下文、672 次回答,短任务对照单独报告。Hermes 负责采集,评分时直接调用 Qwen,没有继续工具循环或
恢复原文。少量合成任务不能证明通用优势或统计等价;融合和原生摘要适配器均仅用于 benchmark。
详见[完整 query、answer 与实验设定](https://github.com/jinliyl/ReMe/blob/feat/decision-model-compaction/benchmark/compaction/STUDY.md)和[结果、对照与审计](https://github.com/jinliyl/ReMe/blob/feat/decision-model-compaction/benchmark/compaction/RESULTS.md)。
详见[完整 query、answer 与实验设定](https://github.com/jinliyl/ReMe/blob/11317634e5e255a7c7b13492f048f8ca0c90ab3a/benchmark/compaction/STUDY.md)和[结果、对照与审计](https://github.com/jinliyl/ReMe/blob/11317634e5e255a7c7b13492f048f8ca0c90ab3a/benchmark/compaction/RESULTS.md)。