SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.19215 · 2024

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 8 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2406.19215.json · badge: /api/ran/2406.19215.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.

RepositoryRoleRan
thu-keg/seakr canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
async_request_deepspeed_mii Ran
ran on a synthesized input
thu-keg/seakr/vllm_uncertainty/benchmarks/backend_request_func.py
pointer only (licence: GPL-3.0) · get_code("5109c385e92b727e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

async_request_tgi Ran
ran; our contract draft was wrong, not the code
thu-keg/seakr/vllm_uncertainty/benchmarks/backend_request_func.py
pointer only (licence: GPL-3.0) · get_code("a58940aabfd794f9")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

async_request_trt_llm Ran
ran; our contract draft was wrong, not the code
thu-keg/seakr/vllm_uncertainty/benchmarks/backend_request_func.py
pointer only (licence: GPL-3.0) · get_code("fa581ebc13cb414d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

bm25search_search Ran
ran; our contract draft was wrong, not the code
thu-keg/seakr/SEAKR/retriever.py
pointer only (licence: GPL-3.0) · get_code("1a724cf510e5bb93")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

check_wheel_size Ran
ran, honoured the contract we drafted
thu-keg/seakr/vllm_uncertainty/.buildkite/check-wheel-size.py
pointer only (licence: GPL-3.0) · get_code("e8d1a899df6f301a")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

elasticsearch_lexical_multisearch Ran
ran; our contract draft was wrong, not the code
thu-keg/seakr/SEAKR/retriever.py
pointer only (licence: GPL-3.0) · get_code("0410394e1f61026a")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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_answer Ran
ran; our contract draft was wrong, not the code
thu-keg/seakr/main_simpleqa.py
pointer only (licence: GPL-3.0) · get_code("64fc92f1ad0464da")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

run Ran
ran; our contract draft was wrong, not the code
thu-keg/seakr/vllm_uncertainty/collect_env.py
pointer only (licence: GPL-3.0) · get_code("6b73fe0480a96ad9")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

run_and_parse_first_match Ran
ran; our contract draft was wrong, not the code
thu-keg/seakr/vllm_uncertainty/collect_env.py
pointer only (licence: GPL-3.0) · get_code("ce7a62e37fe78c0d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

run_and_read_all Ran
ran; our contract draft was wrong, not the code
thu-keg/seakr/vllm_uncertainty/collect_env.py
pointer only (licence: GPL-3.0) · get_code("5ae630bfc3821b6e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

elasticsearch_hit_template Not yet run
unverified (harvested, no recorded run)
thu-keg/seakr/SEAKR/retriever.py
pointer only (licence: GPL-3.0) · get_code("189363ca95998f9a")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

get_dataset Not yet run
unverified (harvested, no recorded run)
thu-keg/seakr/SEAKR/dataset.py
pointer only (licence: GPL-3.0) · get_code("c39d142cd9d5522d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, thu-keg/seakr, is not in the permissive set Syntology serves inline. 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.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 9 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 9 later) and 3 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.

FunctionAlso present inEarliest-datedOthers named
run_and_parse_first_match 14 other papers
6 dated earlier, 8 later
2109.04003 (2021-09)
Improving Deep Metric Learning by Divide and Conquer
2109.08267 (2021-09)
CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research
2202.04053 (2022-02)
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models
and 11 more not named here
run_and_read_all 14 other papers
6 dated earlier, 8 later
2109.04003 (2021-09)
Improving Deep Metric Learning by Divide and Conquer
2109.08267 (2021-09)
CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research
2202.04053 (2022-02)
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models
and 11 more not named here
run 6 other papers
1 dated earlier, 5 later
2405.16444 (2024-05)
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
2410.00428 (2024-10)
LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management
2411.04750 (2024-11)
SpectraFM: Tuning into Stellar Foundation Models
and 3 more not named here
elasticsearch_hit_template 3 other papers
2 dated earlier, 1 later
2305.06983 (2023-05)
Active Retrieval Augmented Generation
2403.10081 (2024-03)
DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models
2025.acl-long.548 (2025 (year only))
Improving Factuality with Explicit Working Memory
async_request_deepspeed_mii 2 other papers
1 dated earlier, 1 later
2405.16444 (2024-05)
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
2410.00428 (2024-10)
LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management
async_request_trt_llm 2 other papers
1 dated earlier, 1 later
2405.16444 (2024-05)
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
2410.00428 (2024-10)
LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management
bm25search_search 2 other papers
1 dated earlier, 1 later
2403.10081 (2024-03)
DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models
2025.acl-long.548 (2025 (year only))
Improving Factuality with Explicit Working Memory
elasticsearch_lexical_multisearch 2 other papers
1 dated earlier, 1 later
2403.10081 (2024-03)
DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models
2025.acl-long.548 (2025 (year only))
Improving Factuality with Explicit Working Memory
get_answer 1 other paper
1 later
2501.12835 (2025-01)
Adaptive Retrieval without Self-Knowledge? Bringing Uncertainty Back Home

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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper introduces Self-aware Knowledge Retrieval (SeaKR), a novel adaptive RAG model that extracts self-aware uncertainty of LLMs from their internal states. SeaKR activates retrieval when the LLMs present high self-aware uncertainty for generation. To effectively integrate retrieved knowledge snippets, SeaKR re-ranks them based on LLM's self-aware uncertainty to preserve the snippet that reduces their uncertainty to the utmost. To facilitate solving complex tasks that require multiple retrievals, SeaKR utilizes their self-aware uncertainty to choose among different reasoning strategies. Our experiments on both complex and simple Question Answering datasets show that SeaKR outperforms existing adaptive RAG methods. We release our code at https://github.com/THU-KEG/SeaKR.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.19215")
get_code_for_paper("2406.19215")
have("2406.19215")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.19215.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.19215.svg)](https://syntology.ai/paper/2406.19215)

Connect an agent — have() is free.