Skip to content
← Back to explorer

Code Fingerprints: Disentangled Attribution of LLM-Generated Code

Jiaxun Guo, Ziyuan Yang, Mengyu Sun, Hui Wang, Jingfeng Lu, Yi Zhang · Mar 4, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 4, 2026, 3:58 PM

Recent

Extraction refreshed

Mar 9, 2026, 5:20 PM

Fresh

Extraction source

Runtime deterministic fallback

Confidence 0.15

Abstract

The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale. While these systems improve productivity, they introduce new challenges for software governance, accountability, and compliance. Existing research primarily focuses on distinguishing machine-generated code from human-written code; however, many practical scenarios--such as vulnerability triage, incident investigation, and licensing audits--require identifying which LLM produced a given code snippet. In this paper, we study the problem of model-level code attribution, which aims to determine the source LLM responsible for generated code. Although attribution is challenging, differences in training data, architectures, alignment strategies, and decoding mechanisms introduce model-dependent stylistic and structural variations that serve as generative fingerprints. Leveraging this observation, we propose the Disentangled Code Attribution Network (DCAN), which separates Source-Agnostic semantic information from Source-Specific stylistic representations. Through a contrastive learning objective, DCAN isolates discriminative model-dependent signals while preserving task semantics, enabling multi-class attribution across models and programming languages. To support systematic evaluation, we construct the first large-scale benchmark dataset comprising code generated by four widely used LLMs (DeepSeek, Claude, Qwen, and ChatGPT) across four programming languages (Python, Java, C, and Go). Experimental results demonstrate that DCAN achieves reliable attribution performance across diverse settings, highlighting the feasibility of model-level provenance analysis in software engineering contexts. The dataset and implementation are publicly available at https://github.com/mtt500/DCAN.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.15 (below strong-reference threshold).
  • No explicit evaluation mode was extracted from available metadata.
  • No benchmark/dataset or metric anchors were extracted.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

Background context only.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Runtime deterministic fallback missing

No explicit feedback protocol extracted.

Evidence snippet: The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale.

Evaluation Modes

missing

None explicit

Confidence: Low Source: Runtime deterministic fallback missing

Validate eval design from full paper text.

Evidence snippet: The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale.

Quality Controls

missing

Not reported

Confidence: Low Source: Runtime deterministic fallback missing

No explicit QC controls found.

Evidence snippet: The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Runtime deterministic fallback missing

No benchmark anchors detected.

Evidence snippet: The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale.

Reported Metrics

missing

Not extracted

Confidence: Low Source: Runtime deterministic fallback missing

No metric anchors detected.

Evidence snippet: The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale.

Rater Population

missing

Unknown

Confidence: Low Source: Runtime deterministic fallback missing

Rater source not explicitly reported.

Evidence snippet: The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Coding
  • Extraction source: Runtime deterministic fallback

Evaluation Lens

  • Evaluation modes:
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.15
  • Flags: low_signal, possible_false_positive, runtime_fallback_extraction

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Deterministic synthesis

Existing research primarily focuses on distinguishing machine-generated code from human-written code; however, many practical scenarios--such as vulnerability triage, incident investigation, and licensing audits--require identifying which… HFEPX protocol signal is limited in abstract-level metadata, so treat it as adjacent context. Updated from current HFEPX corpus.

Generated Mar 9, 2026, 5:20 PM · Grounded in abstract + metadata only

Key Takeaways

  • Existing research primarily focuses on distinguishing machine-generated code from human-written code; however, many practical scenarios--such as vulnerability triage, incident…
  • Leveraging this observation, we propose the Disentangled Code Attribution Network (DCAN), which separates Source-Agnostic semantic information from Source-Specific stylistic…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Verify metric definitions before comparing against your eval pipeline.

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • Existing research primarily focuses on distinguishing machine-generated code from human-written code; however, many practical scenarios--such as vulnerability triage, incident investigation, and licensing audits--require identifying which…
  • Leveraging this observation, we propose the Disentangled Code Attribution Network (DCAN), which separates Source-Agnostic semantic information from Source-Specific stylistic representations.
  • To support systematic evaluation, we construct the first large-scale benchmark dataset comprising code generated by four widely used LLMs (DeepSeek, Claude, Qwen, and ChatGPT) across four programming languages (Python, Java, C, and Go).

Why It Matters For Eval

  • Existing research primarily focuses on distinguishing machine-generated code from human-written code; however, many practical scenarios--such as vulnerability triage, incident investigation, and licensing audits--require identifying which…
  • To support systematic evaluation, we construct the first large-scale benchmark dataset comprising code generated by four widely used LLMs (DeepSeek, Claude, Qwen, and ChatGPT) across four programming languages (Python, Java, C, and Go).

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Gap: Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Gap: Metric reporting is present

    No metric terms extracted.

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote