SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.01966 · 2026

Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior

Xinchao Wang, Qi Li, Bo Yin, Runpeng Yu

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 (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 2 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/2601.01966.json · badge: /api/ran/2601.01966.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
YinBo0927/RePro community
Papers with Code archive
7 ran · 1 no recorded run
FunctionStatusWhere it lives
AttackerArtifacts Ran
ran on a synthesized input · constructed an object; no result was computed
YinBo0927/RePro/repro/attacker.py
pointer only (licence: NONE) · get_code("03a626a2b907b17e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YinBo0927/RePro 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.

LinearHead Ran
ran on a synthesized input · constructed an object; no result was computed
YinBo0927/RePro/repro/attacker.py
pointer only (licence: NONE) · get_code("6407c57856c65394")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YinBo0927/RePro 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.

MLPEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
YinBo0927/RePro/repro/attacker.py
pointer only (licence: NONE) · get_code("1da9bbef0ddba734")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YinBo0927/RePro 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.

ProjectionHead Ran
ran on a synthesized input · constructed an object; no result was computed
YinBo0927/RePro/repro/attacker.py
pointer only (licence: NONE) · get_code("d91949fe33a1cb79")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YinBo0927/RePro 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.

Standardizer Ran
ran on a synthesized input
YinBo0927/RePro/repro/attacker.py
pointer only (licence: NONE) · get_code("798db8cfc97bae25")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YinBo0927/RePro 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.

compute_standardizer Ran
ran; our contract draft was wrong, not the code
YinBo0927/RePro/repro/attacker.py
pointer only (licence: NONE) · get_code("0945a27516e8d776")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YinBo0927/RePro 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.

supervised_contrastive_loss Ran
ran; our contract draft was wrong, not the code
YinBo0927/RePro/repro/attacker.py
pointer only (licence: NONE) · get_code("2c8f2775bd4f3adb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YinBo0927/RePro 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.

train_attacker Not yet run
unverified (harvested, no recorded run)
YinBo0927/RePro/repro/attacker.py
pointer only (licence: NONE) · get_code("d256fb42ad8a989a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YinBo0927/RePro 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

Instruction tuning increasingly relies on LLMbased prompt refinement, where prompts in the training corpus are selectively rewritten by an external refiner to improve clarity and instruction alignment. This motivates an instancelevel audit problem: for a fine-tuned model and a training prompt-response pair, can we infer whether the model was trained on the original prompt or its LLM-refined version within a mixed corpus? This matters for dataset governance and dispute resolution when training data are contested. However, it is nontrivial in practice: refined and raw instances are interleaved in the training corpus with unknown, source-dependent mixture ratios, making it harder to develop provenance methods that generalize across models and training setups. In this paper, we formalize this audit task as Refinement Provenance Inference (RPI) and show that prompt refinement yields stable, detectable shifts in teacher-forced token distributions, even when semantic differences are not obvious. Building on this phenomenon, we propose RePro, a logit-based provenance framework that fuses teacher-forced likelihood features with logit-ranking signals. During training, RePro learns a transferable representation via shadow fine-tuning, and uses a lightweight linear head to infer provenance on unseen victims without training-data access. Empirically, RePro consistently attains strong performance and transfers well across refiners, suggesting that it exploits refiner-agnostic distribution shifts rather than rewrite-style artifacts. The code is available at: https:// github.com/YinBo0927/RePro.

For agents

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

get_harvested_code_for_paper("2601.01966")
get_code_for_paper("2601.01966")
have("2601.01966")

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

curl https://syntology.ai/api/ran/2601.01966.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.01966.svg)](https://syntology.ai/paper/2601.01966)

Connect an agent — have() is free.