Data Provenance

Ask about this topic

Overview

Data provenance studies the origins, transformations, and relationships of data and the outputs built from it, helping people reproduce analyses, assign credit, audit decisions, and manage privacy or reuse rights. Common approaches include workflow metadata and lineage graphs, structured claim-to-evidence records, cryptographic signatures and append-only logs, and watermarks or statistical fingerprints for identifying sources. Work increasingly applies these methods to AI training data, generated media, retrieval systems, and tool-using agents, where records can connect outputs to sources, actions, and versions. A central challenge is that tamper-evident records or plausible citations do not by themselves prove that an event occurred or that evidence supports a claim; provenance must balance completeness and verifiability with privacy, cost, and robustness to transformations.

Latest papers

CardsList

191 papers35 papers in the last four weeks, up 59% on the four weeks before. 0.2% of all new papers.

  1. Data Provenance and Ethics in the Curricula of U.S. Health AI Education Programs

    Oct 29, 2026Raffaele Giancotti, Francesca Santucci, Amama Anjum +5Data ProvenanceAI Ethics

    MIT Critical Data, Massachusetts Institute of Technology, Cambridge (MA), USA · The University of Texas at Austin, Austin (TX), USA · Center of Artificial Intelligence, Prince Mohammad Bin Fahd University, Dhahran, Saudi Arabia +6

  2. Enhanced image forensics through partial C2PA-based provenance information

    Oct 28, 2026Riccardo Ziglio, Eleonora Marchesini, Andrea Montibeller +3Digital Image ForensicsData Provenance

    Fondazione Bruno Kessler, Trento, Italy · University of Genoa, Italy · University of Trento, Italy +1

  3. GraphRAGProv: GraphRAG Meets How-Provenance

    Oct 27, 2026Wadie El Amrani, Luis GalárragaGraph Retrieval-Augmented GenerationData Provenance

    Independent Toulouse, France · INRIA Rennes, France

  4. Replication or Corroboration? An Axiomatic Framework for Evidential Dependence in Multi-Agent Debate

    Oct 26, 2026Hoang-Loc Cao, Truong Thanh Hung Nguyen, Phuc Truong Loc Nguyen +6Multi-Agent DebateComputational Argumentation

    University of New Brunswick Canada · FAU Erlangen-Nürnberg Germany · FPT Software Vietnam +3

  5. NumTrace: Auditing the Number Provenance of Financial Analyst Agents

    Oct 26, 2026Tianlei Zhu, Matt White, Xue Liu +1Financial Reasoning BenchmarksData Provenance

    Columbia University · University of California, Berkeley · Linux Foundation +3

  6. Arya Forge: Auditing Validation and Release Approval for Financial Instruction Data

    Oct 26, 2026Kushagra Bhatnagar, Deekshith MarlaAlgorithmic AuditingData Provenance

  7. Collection-Date Assignment Redirects Answers in Temporal QA

    Oct 23, 2026Minsu Oh, Seunghui Jwa, Soo Kyun Kim +1Temporal QATemporal Reasoning in Language Models

    Department of Artificial Intelligence, Jeju National University · Department of Computer Engineering, Jeju National University

  8. Agentic AI Defense: Decode-Time Provenance Binding for MCP

    Oct 22, 2026Eric Yocam, Varghese Vaidyan, Paris Kalathas +3AI Agent SecurityPrompt Injection Attacks on AI Agents

    Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA. · Information Networking Institute, Carnegie Mellon University, Pittsburgh, PA, USA.

  9. AgentTriage: Replayable Security Diagnosis Across Heterogeneous Agent Runtimes

    Oct 22, 2026Jie Ying, Xutao Zhang, Ningyuan Chen +4AI Agent AuditingAI Agent Security

    College of Information and Intelligence Engineering, Zhejiang Wanli University, Ningbo, China · College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China

  10. From Augmentation to Synthetic Evidence: Evaluating Generated Chest Radiographs at Dataset Intake

    Oct 21, 2026Shaikh Akib Shahriyar, Zinedine Sehili, Adam Arthur +1Data ProvenanceAI-Generated Image Detection

    Rochester Institute of Technology Rochester, NY, USA

  11. Reusing Assurance Evidence in AI Pipelines: Validity Conditions, a Fail-Closed Release Gate, and a Replay of 714 Public Data Version Control Pipelines

    Oct 20, 2026Atanu Mukhopadhyay, Shravya Reddy NallaIncremental ComputationAI Assurance

    Independent Researcher, New Jersey, USA · Independent Researcher, USA

  12. Minimum-Cost Robust Evidence Certificates for Horn Reasoning under Correlated Source Failures

    Oct 19, 2026Yukun YangData Provenance

    School of Management, Beijing Institute of Technology

  13. Same Data, Different Bytes: Serialization-Invariant Integrity Checks for Agent-Published Datasets

    Oct 17, 2026Jin Gao, Maura ClarkAI Agent ReliabilityData Provenance

    UOR Foundation, USA

  14. Data Provenance Aggregation and Structural Descriptors for Query-Template Identification

    Oct 15, 2026Paulo Pintor, Rogério Costa, José MoreiraData Provenance

    IEETA, University of Aveiro, Aveiro, Portugal . · CISUC, DEI, University of Coimbra, Coimbra, Portugal .

  15. vst-bench-ml: Auditable Dataset Generation for Audio Plugins

    Oct 14, 2026Youssef HemimyData ProvenanceML Reproducibility

    St. Thomas University

  16. MemeTrace: A Multimodal LLM-Based Agent for Safety-Aware Meme Provenance Analysis

    Oct 13, 2026Bo Shao, Yihan Ma, Yiting Qu +2Fake News DetectionHarmful Meme Detection

    CISPA Helmholtz Center for Information Security

  17. Complex materials engineering via Provenance Action Graphs: potential, structure and demonstration

    Oct 13, 2026Yevgeny Rakita, Paul Todd, James R. Neilson +1Materials DiscoveryMaterials Science

    Department of Materials Engineering, Ben Gurion University of the Negev, Beer-Sheva, Israel · Department of Chemistry, Colorado State University, Fort Collins, CO 80523 · Department Materials, University of California, Santa Barbara, Santa Barbara, CA 93106

  18. Keep Your Receipts: Trustworthy Cleanup of Agent-Built Knowledge Graphs

    Oct 13, 2026Vishisht ChoudharyKnowledge GraphsData Provenance

    Technical University of Munich

  19. AIPOCH Open-Science: An Open-Source AI Research Workbench with Reproducible .science Packages

    Oct 12, 2026Wen Ouyang, Bocheng Huang, Qianyu Yao +76Scientific ReproducibilityAI-Assisted Scientific Research

  20. RegExtract: A Benchmark for PFAS Regulatory Information Extraction with LLMs

    Oct 10, 2026Defne Circi, Krystelle Lionti, Sarathkrishna Swaminathan +8Document Information ExtractionLLM Information Extraction

    Duke University, USA · IBM Research, USA · IBM Research, UK

  21. Traceable World State: A Provenance-Aware State Representation and Deterministic Replay Framework for Robotic Systems

    Oct 8, 2026Zoe LiData Provenance

    Independent Researcher Seattle, WA, USA

  22. GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity

    Oct 8, 2026Chiara Bonfanti, Cataldo BasileAI Agent AuditingData Provenance

    Politecnico di Torino

  23. OOM-RL II: Reality Is an Oracle, Not a Debugger Provenance-Constrained Diagnosis in Continually Evolving Agent-Engineered Systems

    Oct 7, 2026Kun Liu, Liqun ChenData ProvenanceAI Agent Auditing

  24. Correct Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent Logs

    Oct 7, 2026Taehyeon Yun, Dongho Kim, Geonwoo Kim +3Digital ForensicsData Provenance

    aSungkyunkwan University, Republic of Korea

  25. Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering

    Oct 6, 2026Zheng Gao, Xiaoyu Li, Zhicheng Bao +1Data ProvenanceAI-Generated Image Detection

    UNSW Sydney

  26. Who Wrote It Is Not Enough: Detecting Who Contributed the Insight

    Oct 5, 2026Zhuoyang Zou, Abolfazl Ansari, Jiaxi Yang +4Data ProvenanceScholarly Peer Review

    Pennsylvania State University, USA · University of Sheffield, United Kingdom

  27. Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents

    Oct 5, 2026Venkata M Sangaraju, Sudhir VissaData LeakageData Provenance

    Independent Researcher · SAGE7 AI, Georgetown, Texas, USA

  28. IdeaLens: Detecting AI Ideas in Long-form Writing

    Oct 5, 2026Rishanth Rajendhran, Minjoon Choi, Jenna Russell +5AI-Generated Text DetectionData Provenance

    University of Maryland · Simon Fraser University · Google DeepMind

  29. Proof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning

    Oct 5, 2026Surajit DasData ProvenanceEvidence-Grounded Reasoning

  30. Auditable Clinical Timeline Reconstruction with Provenance-Aware Evidence Graphs

    Oct 5, 2026Judith Jeyafreeda AndrewData ProvenanceClinical QA

    Public Health Unit, Medical Information Department, Bordeaux University Hospital (CHU Bordeaux), Bordeaux, France.