SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.09112 · NeurIPS · 2024

HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction

Yong Li, Jian Yuan, Qianyue Hao, Jingyang Fan, Fengli Xu

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2410.09112.json · badge: /api/ran/2410.09112.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
tsinghua-fib-lab/H-LM canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
average_pool Ran
ran; our contract draft was wrong, not the code
tsinghua-fib-lab/H-LM/code/model_train/functions.py
pointer only (licence: NONE); the stored copy get_code serves, from smallporridge/AssistRAG, is pointer only (licence: NONE) · get_code("da78af27b71bc211")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsinghua-fib-lab/H-LM 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.

loss_func Ran
ran; our contract draft was wrong, not the code
tsinghua-fib-lab/H-LM/code/model_train/functions.py
pointer only (licence: NONE) · get_code("df4f39f6cba1abae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsinghua-fib-lab/H-LM 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.

test_cp_logits_topk Ran
ran; our contract draft was wrong, not the code
tsinghua-fib-lab/H-LM/code/functions.py
pointer only (licence: NONE) · get_code("23ec52d5537994f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsinghua-fib-lab/H-LM 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
average_pool 5 other papers
4 dated earlier, 1 later
2306.03799 (2023-06)
Prompt Space Optimizing Few-shot Reasoning Success with Large Language Models
2308.10633 (2023-08)
RALLE: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models
2310.04678 (2023-10)
DORIS-MAE: Scientific Document Retrieval using Multi-level Aspect-based Queries
and 2 more not named here

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 networks are critical infrastructures of modern science, serving as intricate webs of past literature and enabling researchers to navigate the knowledge production system. To mine information hiding in the link space of such networks, predicting which previous papers (candidates) will a new paper (query) cite is a critical problem that has long been studied. However, an important gap remains unaddressed: the roles of a paper's citations vary significantly, ranging from foundational knowledge basis to superficial contexts. Distinguishing these roles requires a deeper understanding of the logical relationships among papers, beyond simple edges in citation networks. The emergence of large language models (LLMs) with textual reasoning capabilities offers new possibilities for discerning these relationships, but there are two major challenges. First, in practice, a new paper may select its citations from gigantic existing papers, where the combined texts far exceed the context length of LLMs. Second, logical relationships between papers are often implicit, and directly prompting an LLM to predict citations may lead to results based primarily on surface-level textual similarities, rather than the deeper logical reasoning required. In this paper, we introduce the novel concept of core citation, which identifies the critical references that go beyond superficial mentions. Thereby, we elevate the citation prediction task from a simple binary classification to a more nuanced problem: distinguishing core citations from both superficial citations and non-citations. To address this, we propose HLM-Cite, a Hybrid Language Model workflow for citation prediction, which combines embedding and generative LMs. We design a curriculum finetune procedure to adapt a pretrained text embedding model to coarsely retrieve high-likelihood core citations from vast candidate sets and then design an LLM agentic workflow to rank the retrieved papers through one-shot reasoning, revealing the implicit relationships among papers. With the two-stage pipeline, we can scale the candidate sets to 100K papers, vastly exceeding the size handled by existing methods. We evaluate HLM-Cite on a dataset across 19 scientific fields, demonstrating a 17.6% performance improvement comparing SOTA methods. Our code is open-source at https://github.com/tsinghua-fib-lab/H-LM for reproducibility.

For agents

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

get_harvested_code_for_paper("2410.09112")
get_code_for_paper("2410.09112")
have("2410.09112")

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

curl https://syntology.ai/api/ran/2410.09112.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.09112.svg)](https://syntology.ai/paper/2410.09112)

Connect an agent — have() is free.