Tao Ge, Furu Wei, Dongyan Zhao, Huishuai Zhang, Si-Qing Chen, Xun Wang, Xin Cheng, Xingxing Zhang
3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2405.13792.json · badge: /api/ran/2405.13792.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| Hannibal046/xRAG | canonical (classifier label) classifier basis: classifier_2025 |
3 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| Projector | Ran ran on a synthesized input · constructed an object; no result was computed |
Hannibal046/xRAG/src/model/xMistral/modeling_xmistral.py pointer only (licence: NONE) · get_code("049569a103f41bb3") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, Hannibal046/xRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| create_prompt_with_mistral_chat_format | Ran ran; our contract draft was wrong, not the code |
Hannibal046/xRAG/src/eval/run_eval.py pointer only (licence: NONE) · get_code("f32346bc3e2dcdc9") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, Hannibal046/xRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| get_start_prompt | Ran ran; our contract draft was wrong, not the code |
Hannibal046/xRAG/src/eval/run_eval.py pointer only (licence: NONE) · get_code("b07caba17b6e0392") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, Hannibal046/xRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| XMistralForCausalLM | Not yet run unverified (harvested, no recorded run) |
Hannibal046/xRAG/src/model/xMistral/modeling_xmistral.py pointer only (licence: NONE) · get_code("159faffa7ba9a59e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, Hannibal046/xRAG when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded. |
Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper introduces xRAG, a novel context compression method designed specifically for retrieval-augmented generation. xRAG redefines the use of document embeddings in dense retrieval-traditionally limited to retrieval purposes-by integrating them as features from the retrieval modality. Through a modality fusion approach, xRAG effectively merges these embeddings into the language model's representation space, eliminating the need for their textual counterparts and achieving an extreme compression rate. In xRAG, the modality bridge is the only trainable component, while the retriever and language model remain frozen. This design choice allows for the reuse of offline-constructed document embeddings and preserves the plug-and-play nature of retrieval augmentation. Experimental results demonstrate that xRAG achieves an average improvement of over 10% across six knowledge-intensive tasks, compatible with various language model backbones, ranging from a dense 7B model to an 8x7B Mixture of Experts configuration. xRAG not only significantly outperforms previous context compression methods but also matches the performance of uncompressed models on several benchmarks, while reducing overall FLOPs by a factor of 3.53. This work pioneers new avenues in retrieval-augmented generation through multimodal fusion, potentially setting a groundwork for future developments in efficient and scalable retrieval systems. How might we mitigate the costs associated with extended context while maintaining the benefits of retrieval augmentation? Recent research interest has converged on a promising direction: Context Compression. This concept is pursued through two primary strategies: soft-prompting methods, such as Gist [58], AutoCompressor [14], and ICAE [19], which compress the context into dense memory slots, and hard-prompting methods, such as LLMLingua [28] and RECOMP [79], where
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2405.13792")
get_code_for_paper("2405.13792")
have("2405.13792")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2405.13792.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2405.13792)
Connect an agent — have() is free.