Fine-Grained Traceability for Transparent ML Pipelines

• URL: http://arxiv.org/abs/2601.14971v1
• Date: Wed, 21 Jan 2026 13:21:30 GMT
• Title: Fine-Grained Traceability for Transparent ML Pipelines
• Authors: Liping Chen, Mujie Liu, Haytham Fayek,
• Abstract summary: FG-Trac is a model-agnostic framework that establishes fine-grained sample-level traceability throughout machine learning pipelines.<n>It defines an explicit mechanism for capturing and verifying sample lifecycle events across preprocessing and training.<n>It computes contribution scores explicitly grounded in training checkpoints, and anchors these traces to tamper-evident cryptographic commitments.
• Score: 10.182692014427909
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern machine learning systems are increasingly realised as multistage pipelines, yet existing transparency mechanisms typically operate at a model level: they describe what a system is and why it behaves as it does, but not how individual data samples are operationally recorded, tracked, and verified as they traverse the pipeline. This absence of verifiable, sample-level traceability leaves practitioners and users unable to determine whether a specific sample was used, when it was processed, or whether the corresponding records remain intact over time. We introduce FG-Trac, a model-agnostic framework that establishes verifiable, fine-grained sample-level traceability throughout machine learning pipelines. FG-Trac defines an explicit mechanism for capturing and verifying sample lifecycle events across preprocessing and training, computes contribution scores explicitly grounded in training checkpoints, and anchors these traces to tamper-evident cryptographic commitments. The framework integrates without modifying model architectures or training objectives, reconstructing complete and auditable data-usage histories with practical computational overhead. Experiments on a canonical convolutional neural network and a multimodal graph learning pipeline demonstrate that FG-Trac preserves predictive performance while enabling machine learning systems to furnish verifiable evidence of how individual samples were used and propagated during model execution.

Related papers

• Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior [58.751981587234916]
  This paper formalizes the Refinement Provenance Inference (RPI) audit task as Refinement Provenance Inference (RPI)<n>We propose RePro, a logit-based framework that fuses teacher-forced likelihood features with logit-ranking signals.<n>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.
  arXiv  Detail & Related papers  (2026-01-05T10:16:41Z)
• Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis [40.047195497231584]
  Tampering Synthesis (FSTS) is a structured and interpretable framework for synthesizing tampered text images.<n>FSTS collects 16,750 real-world tampering instances from five representative tampering types.<n>FSTS synthesizes diverse and realistic training data that better reflect real-world forgery traces.
  arXiv  Detail & Related papers  (2025-11-16T15:43:18Z)
• Interpretable Early Failure Detection via Machine Learning and Trace Checking-based Monitoring [9.565145785280452]
  We develop a framework for interpretable early failure detection based on vectorized trace checking.<n>The framework shows a 2-10% net improvement in key performance metrics compared to the state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-25T08:30:01Z)
• Large Language Models as Realistic Microservice Trace Generators [48.730974361862366]
  This paper proposes a first-of-a-kind approach that relies on training a large language model (LLM) to generate synthetic workload traces.<n>We show that TraceLLM produces diverse, realistic traces under varied conditions, outperforming existing approaches in both accuracy and validity.<n>TraceLLM adapts to downstream trace-related tasks, such as predicting key trace features and infilling missing data.
  arXiv  Detail & Related papers  (2024-12-16T12:48:04Z)
• COMPILED: Deep Metric Learning for Defect Classification of Threaded Pipe Connections using Multichannel Partially Observed Functional Data [6.688305507010403]
  We focus on defect classification where each sample is represented as partially observed multichannel functional data.<n>The available samples for each defect type are limited and imbalanced.<n>We propose an innovative classification approach named as COMPILED based on deep metric learning.
  arXiv  Detail & Related papers  (2024-04-04T09:55:11Z)
• Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt [80.43623986759691]
  We introduce a novel Unsupervised Continual Anomaly Detection framework called UCAD. The framework equips the UAD with continual learning capability through contrastively-learned prompts. We conduct comprehensive experiments and set the benchmark on unsupervised continual anomaly detection and segmentation.
  arXiv  Detail & Related papers  (2024-01-02T03:37:11Z)
• Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization [87.21285093582446]
  Diffusion Generative Flow Samplers (DGFS) is a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments. Our method takes inspiration from the theory developed for generative flow networks (GFlowNets)
  arXiv  Detail & Related papers  (2023-10-04T09:39:05Z)
• A hybrid feature learning approach based on convolutional kernels for ATM fault prediction using event-log data [5.859431341476405]
  We present a predictive model based on a convolutional kernel (MiniROCKET and HYDRA) to extract features from event-log data. The proposed methodology is applied to a significant real-world collected dataset. The model was integrated into a container-based decision support system to support operators in the timely maintenance of ATMs.
  arXiv  Detail & Related papers  (2023-05-17T08:55:53Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• Scanflow: A multi-graph framework for Machine Learning workflow management, supervision, and debugging [0.0]
  We propose a novel containerized directed graph framework to support end-to-end Machine Learning workflow management. The framework allows defining and deploying ML in containers, tracking their metadata, checking their behavior in production, and improving the models by using both learned and human-provided knowledge.
  arXiv  Detail & Related papers  (2021-11-04T17:01:12Z)
• Forensicability of Deep Neural Network Inference Pipelines [68.8204255655161]
  We propose methods to infer properties of the execution environment of machine learning pipelines by tracing characteristic numerical deviations in observable outputs. Results from a series of proof-of-concept experiments give rise to possible forensic applications, such as the identification of the hardware platform used to produce deep neural network predictions.
  arXiv  Detail & Related papers  (2021-02-01T15:41:49Z)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)
• Deep Multi-Shot Network for modelling Appearance Similarity in Multi-Person Tracking applications [0.0]
  This article presents a Deep Multi-Shot neural model for measuring the Degree of Appearance Similarity (MS-DoAS) between person observations. The model has been deliberately trained to be able to manage the presence of previous identity switches and missed observations in the handled tracks. It has demonstrated a high capacity to discern when a new observation corresponds to a certain track, achieving a classification accuracy of 97% in a hard test.
  arXiv  Detail & Related papers  (2020-04-07T16:43:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.