SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.05004 · 2024

Can't Remember Details in Long Documents? You Need Some R&R

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 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 0 have no contract verdict; 8 failures of our instrument; 0 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/2403.05004.json · badge: /api/ran/2403.05004.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
casetext/r-and-r canonical (classifier label)
classifier basis: census
9 ran · 0 no recorded run
FunctionStatusWhere it lives
fuzzy_match Ran
ran, honoured the contract we drafted
casetext/r-and-r/src/metrics.py
pointer only (licence: NONE) · get_code("841e9916ae689986")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, casetext/r-and-r 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_answer Ran
ran; our contract draft was wrong, not the code
casetext/r-and-r/src/prompts.py
pointer only (licence: NONE) · get_code("1aa6ab3d47a5bf82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, casetext/r-and-r 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_files Ran
ran; our contract draft was wrong, not the code
casetext/r-and-r/tables.py
pointer only (licence: NONE) · get_code("2be958fb9ab8b142")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, casetext/r-and-r 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_single_page Ran
ran; our contract draft was wrong, not the code
casetext/r-and-r/src/prompts.py
pointer only (licence: NONE) · get_code("33f4638415122885")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, casetext/r-and-r 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.

paginate Ran
ran; our contract draft was wrong, not the code
casetext/r-and-r/src/datasets.py
pointer only (licence: NONE) · get_code("3d1e818d7f65a61c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, casetext/r-and-r 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.

parse_json Ran
ran; our contract draft was wrong, not the code
casetext/r-and-r/src/parsers.py
pointer only (licence: NONE) · get_code("71a5af9ea11d13f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, casetext/r-and-r 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.

parse_page Ran
ran; our contract draft was wrong, not the code
casetext/r-and-r/src/parsers.py
pointer only (licence: NONE) · get_code("e7306a01494995f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, casetext/r-and-r 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.

parse_single_json Ran
ran; our contract draft was wrong, not the code
casetext/r-and-r/src/parsers.py
pointer only (licence: NONE) · get_code("14bb61c15d11669b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, casetext/r-and-r 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.

query_expansion Ran
ran; our contract draft was wrong, not the code
casetext/r-and-r/src/prompts.py
pointer only (licence: NONE) · get_code("2e07faa19f9232b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, casetext/r-and-r 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.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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.

Repositories linked to this paper

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

Abstract

Long-context large language models (LLMs) hold promise for tasks such as question-answering (QA) over long documents, but they tend to miss important information in the middle of context documents (arXiv:2307.03172v3). Here, we introduce $\textit{R&R}$ -- a combination of two novel prompt-based methods called $\textit{reprompting}$ and $\textit{in-context retrieval}$ (ICR) -- to alleviate this effect in document-based QA. In reprompting, we repeat the prompt instructions periodically throughout the context document to remind the LLM of its original task. In ICR, rather than instructing the LLM to answer the question directly, we instruct it to retrieve the top $k$ passage numbers most relevant to the given question, which are then used as an abbreviated context in a second QA prompt. We test R&R with GPT-4 Turbo and Claude-2.1 on documents up to 80k tokens in length and observe a 16-point boost in QA accuracy on average. Our further analysis suggests that R&R improves performance on long document-based QA because it reduces the distance between relevant context and the instructions. Finally, we show that compared to short-context chunkwise methods, R&R enables the use of larger chunks that cost fewer LLM calls and output tokens, while minimizing the drop in accuracy.

For agents

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

get_harvested_code_for_paper("2403.05004")
get_code_for_paper("2403.05004")
have("2403.05004")

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

curl https://syntology.ai/api/ran/2403.05004.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.05004.svg)](https://syntology.ai/paper/2403.05004)

Connect an agent — have() is free.