SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.13647 · 2024

Weak-to-Strong Reasoning

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 0 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 2 failures of our instrument; 4 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/2407.13647.json · badge: /api/ran/2407.13647.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
gair-nlp/weak-to-strong-reasoning canonical (classifier label)
classifier basis: census
4 ran · 4 no recorded run
FunctionStatusWhere it lives
check_sympy_equivalence Ran
ran, violated the contract we drafted
gair-nlp/weak-to-strong-reasoning/src/eval/math_normalization.py
pointer only (licence: NONE) · get_code("33973ae45a70d4fe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gair-nlp/weak-to-strong-reasoning 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_prompts Ran
ran; our contract draft was wrong, not the code
gair-nlp/weak-to-strong-reasoning/src/inference_olympic.py
pointer only (licence: NONE) · get_code("1e4965b788c0a240")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gair-nlp/weak-to-strong-reasoning 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.

is_integer Ran
ran, violated the contract we drafted
gair-nlp/weak-to-strong-reasoning/src/eval/math_normalization.py
pointer only (licence: NONE) · get_code("b804c6d0a0ddb922")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gair-nlp/weak-to-strong-reasoning 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.

normalize_final_answer Ran
ran; our contract draft was wrong, not the code
gair-nlp/weak-to-strong-reasoning/src/eval/math_normalization.py
pointer only (licence: NONE) · get_code("31ee6b861ee71ef7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gair-nlp/weak-to-strong-reasoning 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.

answer_cleansing Not yet run
unverified (harvested, no recorded run)
gair-nlp/weak-to-strong-reasoning/src/eval/evaluation.py
pointer only (licence: NONE) · get_code("02ab9527f5129447")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gair-nlp/weak-to-strong-reasoning 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.

load_data Not yet run
unverified (harvested, no recorded run)
gair-nlp/weak-to-strong-reasoning/src/inference_olympic.py
pointer only (licence: NONE) · get_code("d3e33dd55abbfa65")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gair-nlp/weak-to-strong-reasoning 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.

parser_pred_ans Not yet run
unverified (harvested, no recorded run)
gair-nlp/weak-to-strong-reasoning/src/eval/evaluation.py
pointer only (licence: NONE) · get_code("6e9ec160ce05f73d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gair-nlp/weak-to-strong-reasoning 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.

test_answer Not yet run
unverified (harvested, no recorded run)
gair-nlp/weak-to-strong-reasoning/src/eval/evaluation.py
pointer only (licence: NONE) · get_code("ae9238672a6e13e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gair-nlp/weak-to-strong-reasoning 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, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 5 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
check_sympy_equivalence 2 other papers
2 later
2505.15404 (2025-05)
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
2506.12860 (2025-06)
QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
is_integer 2 other papers
2 later
2505.15404 (2025-05)
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
2506.12860 (2025-06)
QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
normalize_final_answer 2 other papers
2 later
2505.15404 (2025-05)
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
2506.12860 (2025-06)
QFFT, Question-Free Fine-Tuning for Adaptive Reasoning

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

When large language models (LLMs) exceed human-level capabilities, it becomes increasingly challenging to provide full-scale and accurate supervision for these models. Weak-to-strong learning, which leverages a less capable model to unlock the latent abilities of a stronger model, proves valuable in this context. Yet, the efficacy of this approach for complex reasoning tasks is still untested. Furthermore, tackling reasoning tasks under the weak-to-strong setting currently lacks efficient methods to avoid blindly imitating the weak supervisor including its errors. In this paper, we introduce a progressive learning framework that enables the strong model to autonomously refine its training data, without requiring input from either a more advanced model or human-annotated data. This framework begins with supervised fine-tuning on a selective small but high-quality dataset, followed by preference optimization on contrastive samples identified by the strong model itself. Extensive experiments on the GSM8K and MATH datasets demonstrate that our method significantly enhances the reasoning capabilities of Llama2-70b using three separate weak models. This method is further validated in a forward-looking experimental setup, where Llama3-8b-instruct effectively supervises Llama3-70b on the highly challenging OlympicArena dataset. This work paves the way for a more scalable and sophisticated strategy to enhance AI reasoning powers. All relevant code and resources are available in \url{https://github.com/GAIR-NLP/weak-to-strong-reasoning}.

For agents

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

get_harvested_code_for_paper("2407.13647")
get_code_for_paper("2407.13647")
have("2407.13647")

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

curl https://syntology.ai/api/ran/2407.13647.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.13647.svg)](https://syntology.ai/paper/2407.13647)

Connect an agent — have() is free.