SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.01432 · 2026

Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation

Daniel Khashabi, Benjamin Van Durme, Jingyu Zhang, Hexuan Wang

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 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/2604.01432.json · badge: /api/ran/2604.01432.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
JHU-CLSP/citation-granularity canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_f1 Ran
ran, honoured the contract we drafted
JHU-CLSP/citation-granularity/evaluate_stratification.py
pointer only (licence: NONE) · get_code("96f69f1680124fd8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JHU-CLSP/citation-granularity 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.

cat_qa_and_statement Ran
ran; our contract draft was wrong, not the code
JHU-CLSP/citation-granularity/auto_scorer.py
pointer only (licence: NONE) · get_code("74c6e7a74a15bcd5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JHU-CLSP/citation-granularity 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_buckets Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JHU-CLSP/citation-granularity/evaluate_stratification.py
pointer only (licence: NONE) · get_code("1a4eeaf5c9e4f807")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JHU-CLSP/citation-granularity 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_base_dir_from_path Ran
ran; our contract draft was wrong, not the code
JHU-CLSP/citation-granularity/evaluate_correctness.py
pointer only (licence: NONE) · get_code("67efce625e679365")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JHU-CLSP/citation-granularity 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_citations Ran
ran; our contract draft was wrong, not the code
JHU-CLSP/citation-granularity/predict.py
pointer only (licence: NONE) · get_code("d748339e76ad3acd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JHU-CLSP/citation-granularity 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.

need_citation_to_score Ran
ran, honoured the contract we drafted
JHU-CLSP/citation-granularity/auto_scorer.py
pointer only (licence: NONE) · get_code("e95c9dd1040dd845")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JHU-CLSP/citation-granularity 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.

postprocess Ran
ran; our contract draft was wrong, not the code
JHU-CLSP/citation-granularity/predict.py
pointer only (licence: NONE) · get_code("6ca42ed16d83c5d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JHU-CLSP/citation-granularity 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_llm Not yet run
unverified (harvested, no recorded run)
JHU-CLSP/citation-granularity/utils/llm_api.py
pointer only (licence: NONE) · get_code("5f1bd4130fb0e230")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JHU-CLSP/citation-granularity 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.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

Citation granularity-whether to cite individual sentences, paragraphs, or documents-is a critical design choice in attributed generation. While fine-grained citations are often preferred for precise human verification, their impact on model performance remains under-explored. We analyze four model scales (8B-120B) and demonstrate that enforcing fine-grained citations degrades attribution quality by 16-276% compared to the best-performing granularity. We observe a consistent performance pattern where attribution quality peaks at intermediate granularities (paragraph-level). Our analysis suggests that fine-grained (sentence-level) citations disrupt necessary semantic dependencies for attributing evidence to answer claims, while excessively coarse citations (multi-paragraph) introduce distracting noise. Importantly, the magnitude of this performance gap varies nonmonotonically with model scale: fine-grained constraints disproportionately penalize larger models, suggesting that atomic citation units disrupt the multi-sentence information synthesis at which these models excel. Strikingly, citation-optimal granularity leads to substantial gains in attribution quality while preserving or even improving answer correctness. Overall, our findings demonstrate that optimizing solely for human verification via fine-grained citation disregards model constraints, compromising both attribution faithfulness and generation reliability. Instead, effective attribution requires aligning citation granularity with the model's natural semantic scope. 1 * Equal advising. 1 github.com/JHU-CLSP/citation-granularity

For agents

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

get_harvested_code_for_paper("2604.01432")
get_code_for_paper("2604.01432")
have("2604.01432")

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

curl https://syntology.ai/api/ran/2604.01432.json

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

[![Syntology run record](https://syntology.ai/api/ran/2604.01432.svg)](https://syntology.ai/paper/2604.01432)

Connect an agent — have() is free.